Healthentia has recently published two papers on the topic of COPD (Chronic Obstructive Pulmonary Disease) exacerbation management, highlighting innovative approaches to real-time detection and risk prediction using digital health tools and machine learning. You can read the full publications here: 10.1109/ICHI64645.2025.00109 & https://doi.org/10.1183/13993003.congress-2024.PA2319

Real-Time Exacerbation Detection

Using the Healthentia app, patients complete a daily symptom questionnaire (DSQ) covering COPD and comorbid conditions like heart failure and anxiety. The algorithm scores symptoms and classifies patients into Stable, Unstable, or Exacerbation states, triggering notifications for patients and alerts for clinicians.

• Study across three European sites (232 patients, 656 days average use) detected 238 exacerbation events.
• Validation showed 46% of emergency visits and 32% of hospitalizations aligned with algorithm-detected exacerbations.
• Key challenge: patient adherence affects detection reliability, highlighting the need for user-friendly engagement.

Predicting Future Exacerbation Risk: RE‑SAMPLE

The RE-SAMPLE platform uses federated learning to train machine learning models across hospitals without sharing raw data. It integrates app-collected real-world data and clinical records to provide personalized risk predictions on a clinician dashboard.

• Simple predictors like prior exacerbations achieved 75% accuracy.
• Supports shared decision-making, empowering clinicians and patients with actionable insights.
• Maintains privacy and security, crucial for real-world implementation.

Why It Matters

• Early warnings help prevent severe exacerbations and reduce hospitalizations.
• Federated ML enables collaborative model training while protecting patient data.
• Real-world data integration captures the complexity of multi-morbid patients.
• Actionable insights support personalized care plans and patient engagement.

Looking Ahead

Future improvements may include better adherence strategies, wearable integration, richer predictive models, larger trials, and targeted behavioral interventions — all moving toward proactive, patient-centered COPD care.

Healthentia’s work demonstrates how real-time monitoring and predictive analytics together can transform COPD management, giving patients and clinicians the tools to act earlier and smarter.

The post Early Detection and Prediction of COPD Exacerbations with Healthentia appeared first on Healthentia.

SOURCE: 13th International Conference on Healthecare Informatics, July 22nd 2025, 10.1109/ICHI64645.2025.00109

A Real-Time COPD Exacerbation Detection Algorithm Using multi-morbid symptom diaries: Insights from a Multi-Site Study

Abstract:

I. INTRODUCTION

Respiratory diseases are considered as one of the major causes of global morbidity and mortality [1] and, as reported by the World Health Organization [2], Chronic Obstructive Pulmonary Disease (COPD) is the fourth leading cause of death worldwide. Due to symptoms such as chronic cough or breathing difficulty, this condition has a great impact on daily life and habits. Additionally, COPD is often accompanied by concurrent cardiac, psychological, or other comorbidities [3], which require specific and tailored care plans for patients, as well as frequent follow-up visits and care services. For these reasons, the health burden associated with this chronic condition is considered significant [4].

Patients with COPD may experience a worsening of symptoms, defined as an exacerbation [5], associated with acute systemic inflammation and clinical status changes [6]. Such events might be triggered by a specific event or other physiological causes [7], occur rapidly from hours to days [8] and often require medical consultations or even hospitalization with a consequent change in the regular treatment of the chronic condition [9]. In more serious cases, exacerbations can lead to death. For these reasons, a prompt identification of symptom worsening is of utmost importance in limiting the rise of potential moderate exacerbations while lowering the number of hospital admissions.

Since COPD is a chronic condition, patients usually adhere to a tailored therapy plan to be followed at home while they report their health status to doctors during follow-up visits. In this setting, timely identification of symptom worsening can only happen if patients are able to recognize any relevant change in their clinical condition and decide to call clinicians or seek additional hospital care. Self-management and remote monitoring and care might make the difference in the treatment of this pathology by having access to information such as the daily health status of a patient or specific symptoms related to COPD and concurrent comorbidities. Several studies have been published in the virtual coaching domain as well, with the aim to actively assist the patient in their disease self-management process [10][11].

The importance of early detection of COPD exacerbations is reported in other works, as in [10], [12] and [13]. Approaches that have been explored include self and remote monitoring, as well as symptom identification, with the use of daily questionnaires [14], or wearable devices [15], and the potential inclusion of prognostic models [16] in COPD patient care. The detection of exacerbations can rely on heterogeneous data, depending on a given modelling approach, and may include parameters such as Forced Vital Capacity (FVC) or Forced Expiratory Volume in 1 second (FEV1), as well as other clinical data, real-world data or self-reported symptoms. Digital tools and telemonitoring are presented in several works: in [17], the authors present a telemonitoring system along with models predicting COPD exacerbation, whereas in [18] daily remote monitoring of symptoms and k-means clustering is described. In [14], daily scores from questionnaires combined with spirometry, pulse oximeter and clinical data are used to identify the occurrence of a health-worsening event, whereas in [15] the authors describe an approach including the recorded heart rate. Emerging technologies, such as machine learning (ML) and artificial intelligence (AI) approaches for predicting COPD exacerbations are presented in different papers, e.g., the authors in [19] describe a decision tree forest classifier for the prediction of symptom worsening episodes, whereas a comparison of ML algorithms for acute exacerbation identification is presented in [20].

As described in [14], a challenge on the actual use of remote monitoring and digital tools is the large number of alerts, which may result in an unmanageable number of notifications and additional workload for healthcare professionals (HCPs). Moreover, low adherence, missing data and errors in data collection might affect the robustness and reliability of the output produced by the system.

To overcome these limitations, the REal-time data monitoring for Shared, Adaptive, Multi-domain and Personalised prediction and decision making for Long-term Pulmonary care Ecosystems (RE-SAMPLE) project (accessible at https://www.re-sample.eu/) has developed a digital framework to support both patients with COPD and Comorbid Chronic Conditions (CCCs) in self-management of their diseases and Healthcare Practitioners (HCPs) in providing personalised care through shared decision making. With the use of a mobile application, patients can be followed remotely by self-reporting any symptom changes and they can receive tailored suggestions to improve their lifestyle and enhance their disease awareness. Additionally, a clinical dashboard allows for patient monitoring by HCPs thanks to the direct access to information from several sources, including clinical records, answers to questionnaires, exacerbations and risk predictions.

The clinical protocol and the algorithm used in the RE-SAMPLE study to detect the start (referred to as onset) and end (referred to as offset) of a COPD exacerbation have been adapted from the COPE-III study in [21] and [22]. In these previous works, the authors aimed at introducing and evaluating an innovative treatment approach based on self-management and action plans, on the basis of self-reported data including the use of daily symptom diaries and the definition of a stable condition versus an exacerbation state. Additionally, other works implemented part of these clinical protocols into algorithms for digitized diaries within e-health solutions, showing high adherence rates and feasibility for use as part of COPD disease management [23][24]. However, further research is necessary for the full implementation, the validation and eventually the improvement of the COPE-III protocol, using richer data sources, and facilitating larger-scale studies.

Therefore, an algorithm has been implemented for the identification of exacerbations based on patient answers to questionnaires and daily interactions with the app. Preliminary results on the use of this algorithm in the RE-SAMPLE multicentric study are presented in this paper, along with a comparison with actual emergency accesses and hospitalizations from Electronic Health Records (EHR) as a primary validation scheme. Even if the model is designed to support CCCs, the analysis of algorithm performance for the concurrent presence of COPD and other pathologies will be described in another work. Details on the pilot sites infrastructure, as well as data collection processes, are beyond the scope of this paper and can be found in [25], [26] and [27].

In the following sections, a description of the algorithm used for the identification of exacerbation events is reported, along with the study protocol, data sources and the preliminary results obtained by its application in a real-world scenario. Conclusions and future directions are finally presented to outline the next steps in the validation of this approach.

II. METHODS

A. Data collection and management

In the RE-SAMPLE study, Healthentia SaMD (Software-as-Medical-Device) [28], is used to collect data from patients and enable their interaction with a virtual coach. Healthentia is a Class IIa medical device software intended for: a) the collection and transmission of physiological data including heart rate, blood pressure, oxygen saturation, and weight directly to care providers via automated electronic means in combination with validated IoT devices; b) the visualization (subjects-based dashboards) and the mathematical treatment of data (trends analysis, alerts) related to the monitored parameters; c) the collection of patient reported outcomes related to health-related quality of life, disease knowledge and adherence to treatment through validated questionnaires; d) the user (subject/patient) interaction with a conversational virtual coach for informative and motivational purposes, in order to support subject telemonitoring, decision making and virtual coaching. Healthentia consists of two parts: the smartphone-app for chronic disease patients and the clinical dashboard for HCPs [29].

In this study, HCPs monitor patients through the Healthentia clinical dashboard. It displays aggregated metrics including vital signs and activity levels and helps identifying trends. The system can automatically flag potential issues and calculate risk scores to help providers take timely action. It also includes tools for creating and sending custom health questionnaires to patients [30].

The Healthentia mobile app helps patients actively participate in their healthcare by collecting RWD. It connects with fitness devices – particularly Garmin trackers in the RE-SAMPLE study – as well as other health apps to gather information, while allowing patients to answer health questionnaires and track their treatment progress. A virtual coach provides personalized guidance and motivation based on the patient’s data [30].

The detection of exacerbations is based on the comparison between the symptoms reported by patients in What Are My Symptoms Questionnaire (USQ) during the enrollment visit and the ones self-reported on a daily basis via the multi-morbid Daily Symptoms Questionnaire (DSQ). This composite questionnaire consists of multiple sub-questionnaires, each addressing specific conditions such as COPD, Chronic Heart Failure (CHF), Anxiety, Depression and Ischemic Heart Disease (IHD) [22]. Patients complete the DSQ through the Healthentia mobile app. The DSQ is adaptive and can be dynamically adjusted based on patient responses and health status. Every morning patients receive one question about whether they have experienced any worsening of symptoms, the questionnaire is completed. If it is positive, they proceed to questions related to COPD symptoms, followed by assessments of anxiety and depression. The system then continues with condition-specific questions based on the patient’s reported comorbidities. If any worsening of symptoms is detected, patients are asked a final free-text question to reflect on potential contributing factors.

The daily score generated from the COPD symptoms questionnaire, part of the DSQ, is used by the algorithm to detect symptom fluctuations, forming the foundation for detecting COPD exacerbations. The scoring encompasses changes in major symptoms: breathlessness, sputum volume, sputum color, and minor symptoms: fever, cough and wheezing and is detailed in Table 1. Each day the algorithm checks the overall summed score; a moderate symptom increase is defined as a score of 10-110 and a significant symptom increase as a score of more than 110. This condition means that at least one of the major symptoms and one of the minor ones are reported as “Significantly more than usual”.

Table 1: COPD Symptoms questionnaire scoring used in exacerbation detection algorithm

B. Algorithm design

The algorithm design employs the COPE-III protocol [22] to systematically detect the onset and resolution of COPD exacerbations. An exacerbation is defined as a period of symptom deterioration, identified through at least two consecutive deviations for at least two COPD symptoms from baseline symptomatology. Criteria are also reported in [31] and [32].

At any given moment patients are classified into one of three mutually exclusive states: COPD Stable, COPD Exacerbation, and COPD Unstable. Transitions between states are dictated by DSQ responses and follow a structured multi-stage process, incorporating sub-state transitions necessary for automated system actions. These types of actions are sending app notifications (e.g., contacting their HCP for support) and/or additional questionnaires to patients, sending dashboard alerts to HCPs, and applying the tag of the current state to the patients.

The Stable state is the default state patients present upon enrollment in the RE-SAMPLE study. They receive the DSQ every morning, and their transition to another state depends on their COPD symptom scores. A score exceeding 110, which indicates the presence of a significant change of breathlessness, sputum volume change or sputum color and fever or cough and wheezing symptoms, triggers a transition to the Unstable state as defined in the COPE-III protocol. At this state if a patient does not answer DSQ for more than four consecutive days first a reminder is sent to the mobile app and finally a dashboard alert is sent to the HCP to contact the patient.

The Unstable state represents the first day of a significant COPD symptom deviation and is an intermediate state. The next day, if COPD questionnaire score is again higher than 110 the patient transitions to the “COPD Exacerbation Onset”-state. If the score is less than 110 the patient returns to the Stable state since 2 consecutive days of two significant symptom deviations are required to transition to Onset. Finally, if patients fail to complete the DSQ the following day, the system checks if 3 days have passed while in the Unstable state, and if this is true, patients return to the Stable state.

The Exacerbation state consists of the following sub-states: 1) the Onset state, that signals the first day of exacerbation, 2) the “Super”-states for ongoing monitoring of symptoms, and 3) the Offset state, that represents recovery and transition back to stability. These sub-states are only required for the systemic actions and the correct implementation of the algorithm. In the clinical dashboard patients in these states retain the status tag “COPD Exacerbation” as for HCPs the sub-states do not have any clinical value. The Onset state is bounded with some systemic actions: the patient receives a notification alert in the mobile app prompting them to perform a blood sample test and a dashboard alert is sent to the HCP via the Healthentia portal. Subsequent DSQ responses dictate transitions to Super state with no symptoms, Super state with moderate symptoms or Super state with significant symptoms. If the DSQ is not answered the following day, then significant symptoms deviation is assumed, and the Super state is assigned as such. If a patient remains in the Super state but stops answering for four consecutive days, a web alert is sent to the HCP.

The exacerbation ends when predefined conditions are met, transitioning the patient back to the Stable state. At this point, their status tag updates to Stable and they receive assessment questionnaires for further evaluation. The two conditions for the Stable transition are either 7 consecutive days with a score lower than 10 or 3 consecutive days with a score of 0 are observed which clinically represents the absence of symptoms or the presence of moderate changes in symptoms such as fever, cough or wheezing. These conditions are based on [22], [31] and [32]. If neither condition is met, the patient remains in exacerbation for a maximum of 30 days, assuming that no exacerbation can last longer. Following this approach, the minimum duration of exacerbation is 4 and maximum duration 30 days.

The described transitions and their conditions are visualized in the following figures:

• Fig. 1 demonstrates the conditions to transition from Stable state to Unstable
• Fig. 2 the conditions to transition from Onset to one of the Super sub-states
• Fig. 3 the conditions to transition from a Super state back to Stable Systemic actions can be either an app notification destined for the patient or a dashboard alert destined for the portal user.

Fig. 1. Flow diagram showing conditions for transitioning from Stable state to Unstable state, actions related to each condition and specific score checking. Blue boxes represent states while yellow ones represent systemic actions related to a condition.

Fig. 2. Flow diagram showing conditions for transitioning from Onset to one of the Super sub-states: no symptoms, moderate or significant, systemic actions and specific score checking. Blue boxes represent states and the yellow ones represent systemic actions related to a condition.

Fig. 3. Flow diagram showing conditions for transitioning from Super to Offset and finally back to Stable, systemic actions and specific score checking. Blue boxes represent states while yellow ones represent systemic actions related to a condition.

C. Study design

The RE-SAMPLE project includes both retrospective and prospective studies performed in three European pilot sites, the Fondazione Policlinico Agostino Gemelli IRCCS in Italy (GEM), the Stichting Medisch Spectrum Twente (MST) in the Netherlands and the Sihtasutus Tartu Ulikooli Kliinikum (TUK) in Estonia. RE-SAMPLE’s major objective is to increase the understanding of COPD and CCCs by creating a knowledge base of multimodal data from EHR, RWD collection, patient knowledge and guidelines. To reach this goal, the consortium designed and implemented a Virtual Companionship Program (VCP) for the patients and an Active Support Program (ASP) for HCPs using the Healthentia infrastructure and developing a dedicated dashboard and shared decision-making tools.

The retrospective studies have been focused on creating a COPD related knowledge base of patient phenotypes. The prospective studies instead included two sub-studies, an observational cohort study and an interventional study with the introduction of the VCP. The observational study has the objective of analyzing the predictors of exacerbations of COPD, as well as assessing technology adoption by patients and HCPs. Furthermore, a fine tuning of the various functionalities of the patient application, including e.g. the use of daily symptom diaries and answering questionnaires, has been included. The interventional study instead implements the VCP and the ASP programs and is still ongoing. The enrolled patients are diagnosed with COPD and concurrent CCCs such as CHF, IHD and diabetes, whereas patients with cognitive impairment or serious other diseases (including severe psychiatric illness or low survival rate) were not included in the studies to avoid confounding factors.

The implementation of the COPE-III protocol in a digital application has been integrated and tested since the beginning of the prospective studies while being adapted over time to account for low adherence rates and data availability. Additionally, the calculated exacerbation events are one of the main outcomes used as a disease deterioration indicator by the models trained in the federated RE-SAMPLE platform. Such models are trained on both hospital and self-reported data aiming to assess risk levels and provide relevant clinical explanations. Alerts and risk predictions related to exacerbation events feed the clinical dashboard that supports clinicians in monitoring the enrolled patients during the interventional study. Moreover, this approach fosters better self-management through the recognition of symptoms and actions suggested to patients. Therefore, evaluating the algorithm effectiveness in detecting COPD exacerbations through patient-reported data is crucial for several components of the project both technical and clinical.

D. Dataset and algorithm validation methodology

In total 232 patients fulfilled the inclusion criteria and participated in the RE-SAMPLE prospective study, with 55 patients dropping out. 30.6% of the entire cohort were female with a mean age of 71 ± 9.2 years. A more comprehensive overview of the cohort characteristics is reported in Table 2. Enrolled patient number differs slightly per pilot site, with GEM presenting 86 patients, TUK 75 and MST 71. Overall, enrolled patients demonstrated a mean actual usage of the tool up to 656 days, while patients at TUK appear to have been using the app for a longer time period. Data covering an approximately 3 years period from 2022-01-25 to 2025-02-14 has been extracted to analyse patient enrolment and compliance aspects, exacerbation number, frequency and duration overall and among pilot sites.

Table 2: General study characteristics across sites in Healthentia database. Categorical variables are reported as counts and percentages while numerical variables as mean values and standard deviations.

The validation of the proposed algorithm outcomes follows an external validation scheme: firstly, we investigate the number of identified events, based on the self-reported symptoms, and secondly, we include EHR data on hospitalizations, emergency accesses and death events available in a dedicated COPD datamart. We report in detail the results on the GEM pilot site in the next section.

III. RESULTS

In this section we provide preliminary results on the dataset and the algorithm validation methodology we presented in the previous section.

A. Patient compliance

A key aspect for the validation of the proposed algorithm is patient response rate and compliance with the prospective study. As demonstrated in Table 3, 50% of the patients enrolled show 50% adherence to the DSQ across their entire usage period. Additionally, patients appear to be more compliant in providing answers in the first 6 months of the study while they tend to reply less over time. Moreover, as shown in Fig. 4, median adherence seems to vary among pilot sites with TUK presenting 56% overall median adherence, MST 60% and GEM 35%. Such an effect could be explained by the fact that GEM patients are older and thus face challenges with digital literacy. Moreover, they can be in a more progressed disease phase that contributes to further reducing engagement and compliance. Research nurses have reported such observations during enrolment and follow-up visits. Additional analyses on the education level are outside the scope of this work and might be further explored in the future.

Table 3: DSQ Adherence over time

DSQ Adherence (%) (median, q1, q3)

Regarding the COPD Symptoms questionnaire, 50% of patients in both the entire cohort and the single pilot sites were 100% adherent in providing answers for the specific symptom changes once replying positively to symptom worsening through the DSQ.

Fig. 4. DSQ adherence per pilot site for the entire observation period

B. Exacerbation detection, frequency and duration

In Table 4, COPD exacerbations are reported as COPD Exacerbation Onset states. Overall, 71 patients (31% of the entire cohort) presented exacerbation events during the observation period. The algorithm detected a total of 238 events, with 149 occurring in 32 patients at MST pilot site, 68 in 32 patients at GEM, and only 21 events in 7 patients at TUK. At the same time, multiple COPD Unstable states are detected for a total number of 116 patients.

Exacerbation events appear to be more frequent for some patients compared to others. As can be seen in Fig. 5, most patients experienced a single exacerbation event while the number of patients with higher exacerbation frequency is limited. The exacerbation frequency profile differs significantly between pilot sites, with MST including the most frequently exacerbating patients while TUK the least ones. At GEM, instead, most patients experienced between 1 and 3 exacerbations. This variation in exacerbation rates across sites may be due to differences in patient populations and care models.

Table 4: COPD Exacerbations per pilot site

Exacerbations (Patients)

Fig. 5. Exacerbation frequency distribution per pilot site

As demonstrated in Fig. 6, most exacerbation events get concluded within 15 days while others can last from 30 and up to 65 days. More specifically, the mean duration for the entire cohort is 11 days and remains comparable across pilot sites; 10 days at MST, 11 at GEM and 14 at TUK. As detailed in the previous section, the algorithm ensures that when patients do not report on their condition daily, event duration gets limited to a maximum of 30 days. However, it was observed that few exacerbations exceeded this duration, comprising outliers, and were reported before the 30-day limit applied to the algorithm. These observed prolonged exacerbations were the reason why we needed to add such time limit. At all pilot sites there are events that last only 5 days, duration that holds for the minimum exacerbation duration by definition according to the COPE-III protocol considering 4 days in Exacerbation state and 1 day in Unstable state. Interestingly, the more patients are compliant in reporting their health condition, the more accurate seems to be the event detection mechanism. This can be observed in Fig. 6 for MST site.

C. Algorithm validation at GEM pilot site

As discussed previously, the proposed algorithm detects COPD exacerbation events based on patient reported symptom changes on daily basis.

Fig. 6. Exacerbation duration distribution per pilot site.

As shown in Table 5 at GEM pilot site 26 patients present in total 64 clinical events such as emergency accesses, hospitalizations, death, considering the entire observation period. 59% of the reported events correspond to hospitalizations, 34% emergency accesses and only 6% death. Please note that each patient can fall in more than one event categories and therefore the total patient number represents the distinct number across all event types.

Table 5: Events at GEM pilot site

To validate whether an exacerbation event detected by the algorithm corresponds to an actual health deterioration incident, we match COPD states including Exacerbation Onset and Unstable to reported clinical events under the condition that both events occurred within a 30-day temporal window with the algorithm-detected states preceding the clinical events. Such an assumption allows for the validation of early detection of acute clinical events that usually remain less frequent compared to moderate ones. It is important to note that the COPE-III protocol aims to capture mainly moderate events and prevent exacerbations at an early stage. In this work, we do not validate moderate events since the required medication data for performing such a task is currently not available.

In Table 6 we report all algorithm detected states matched to clinical events. Considering both Unstable and Onset states, the algorithm is able to detect 22 disease deterioration events and more specifically 46% of the emergency accesses and 32% of hospitalizations reported at the GEM pilot site. Considering that the adherence of patients has been as low as 33%, such results are promising. On the contrary, death events are not matched to detected COPD states as adherence to symptoms questionnaire has been on average only 13%. Finally, it is worth mentioning that 4 additional clinical events were matched to a positive answer to symptoms change (DSQ) without providing further answers to COPD symptoms questionnaire and thus they are not included in this analysis, but they could be accounted for in future work.

Table 6: Algorithm detected states matched to events at GEM pilot site

In Fig. 7 we also analyzed the time interval at which patients declared symptom changes and how those are associated to clinical events. It is observed that detected COPD Unstable states can be crucial in detecting disease deterioration more often than COPD Exacerbation Onset states. Such findings, confirm that data availability assumptions can be further explored with the aim to better define a minimum sufficient patient input to detect exacerbation events timely and more efficiently.

Fig. 7. Exacerbation states associated to events at the GEM pilot site.

D. Exacerbation profiles at GEM pilot site

In Fig. 8 we provide an example of a patient that presents clinical events at the GEM pilot site. The patient gets through three hospitalization events and one emergency access before the last hospitalization. The first hospitalization event (in red) is preceded by a COPD Unstable state (in blue) while the emergency access (in yellow) and successive hospitalization event (in red) is preceded by an Exacerbation Onset state (in purple). The second hospitalization event is not matched to change in his COPD symptoms. This example showcases in a direct manner the potential of the proposed system and at the same time its limitations in engaging the patient in using the technology. Further evaluation is needed to explore these limits and to tackle them.

IV. DISCUSSION

A. Challenges and limitations
The protocol and algorithm design present limitations in accurately capturing the diverse manifestation of COPD exacerbations and the unique per patient symptomatology. The pre-set score thresholds and scoring system, while based on expert judgment, may not adequately capture all possible symptom changes or their relative clinical significance. It also seems that the algorithm is too sensitive for some patients as facing over 10 COPD exacerbations per year is clinically not plausible. Additionally, some patients’ symptom patterns might not align well with the selected categories present in the DSQ, making it hard to properly classify their condition or detect their deterioration. Therefore, the initial algorithm design and threshold settings will require iterative refinement as more real patient data becomes available. Despite the possibility that the system will not perform optimally in its early implementations, the settings and algorithm will be validated and adjusted continuously as the study progresses.

The algorithm may struggle when patients skip completing the DSQ for several days as it relies on consistent data input. Without consistent data, it becomes difficult to accurately track changes in their condition. Patients naturally do not maintain perfect day-to-day adherence. However, in the initial implementation of the algorithm this was not very well accounted for. The algorithm presented in this paper is refined based on validation during the observational cohort study, to better handle missing data, ensuring more robust performance in real-world conditions where data gaps are common. Obviously, since the system can only analyse data that patients actually input, missing or irregularly completed questionnaires can make it impossible for the algorithm to accurately monitor how symptoms are changing and identify when a patient’s condition is getting worse. Therefore, in RESAMPLE the outcomes of the algorithm are used as a support to HCPs informing them accordingly whenever patients stop reporting on their health condition to recover missing
information and ensure patient safety.

The overall reliability of the system in maintaining consistent performance and accuracy over time remains a significant concern, as any instability, especially if counting only on the automated system, could impact patient care. Technical limitations that include system downtime or malfunctions cannot be guaranteed to be 100% eliminated. Processing delays or challenges in combining data from different sources can also affect the accurate and quick This is the reason why HCPs should consider automated monitoring systems as supportive tools rather than complete replacements for clinical
judgment. While these systems can provide valuable insights, their clinical expertise and direct understanding of patient conditions should remain the primary basis for medical decisions, with the automated system serving as a complementary aid to enhance their professional assessment and care delivery.

Finally, the algorithm validation methodology we presented, aims to assess outcomes in a pragmatic way making
use of the currently available clinical data at one pilot site. An interesting future direction of work could be a comprehensive clinical evaluation on the entire cohort using all pilot clinical data for both severe but especially moderate events.

V. CONCLUSIONS

In this work, we introduced an algorithm, based on the COPE-III protocol, for the real-time identification of COPD exacerbations. Even though data collection in a real-world setting remains challenging, particularly with patient adherence averaging 49.8% across all sites, the developed model has the potential of detecting a major worsening of the health status of a patient based on self-reported data. The timely identification of COPD exacerbations, validated with respect to hospitalizations and emergency accesses, appears to be promising for the actual use and implementation of the algorithm in clinical practice together with the adoption of the RE-SAMPLE platform. However, data availability remains a bottleneck. Adherence is not always high and sufficient to detect these events. Therefore, it is important to establish a comprehensive validation approach using independent clinical data collected in the scope of this study for the enrolled COPD patients. Future work directions may include algorithm improvements to overcome the limitations and barriers
identified in the previous discussion. Additionally, further validation across MST and TUK pilot sites with additional data is required in order to have clear evidence of the robustness of the implemented protocol. More specifically, a benchmark including exacerbation events should be created and carefully validated by medical experts from all three pilot sites. Such benchmark can permit a systematic analysis of the sensitivity and the specificity of the proposed algorithm given certain adherence levels. Refinements to the protocol scoring system might be suggested from an in-depth investigation on the correlation between the detection of exacerbation events and hospital admissions, which should be discussed and tested before their actual deployment. The expansion of the study to the interventional VCP, along with the inclusion of additional
patients and end-users, might be a key factor for the final refinement of the model and its consequent future use.

ACKNOWLEDGMENT

This work is supported by the RE-SAMPLE project that has received funding from the European Horizon 2020 research and innovation program under grant agreement No 965315. This result reflects only the author’s view and the European Commission is not responsible for any use that may be made of the information it contains.

REFERENCES
[1] Global burden of COPD. Respirology, 2016, 21.1: 14-23.
[2] WHO, Chronic obstructive pulmonary disease (COPD) (accessed February 2025)
[3] HILLAS, Georgios, et al. Managing comorbidities in COPD. International journal of chronic obstructive pulmonary disease, 2015, 95-109.
[4] VINIOL, Christian; VOGELMEIER, Claus F. Exacerbations of COPD. European Respiratory Review, 2018, 27.147.
[5] KIM, Victor; AARON, Shawn D. What is a COPD exacerbation? Current definitions, pitfalls, challenges and opportunities for improvement. European Respiratory Journal, 2018, 52.5.
[6] SEEMUNGAL, Terence AR, et al. Time course and recovery of exacerbations in patients with chronic obstructive pulmonary disease. American journal of respiratory and critical care medicine, 2000, 161.5: 1608-1613.

[7] WEDZICHA, Jadwiga A.; SEEMUNGAL, Terence AR. COPD exacerbations: defining their cause and prevention. The lancet, 2007, 370.9589: 786-796..
[8] American Thoracic Society Patient Education Series. of COPD Am J Respir Crit Care Med Vol. 198, P21-P22, 2018. Available online at https://www.thoracic.org/patients/patientresources/resources/copd exacerbation-ecopd.pdf (accessed February 2025)
[9] AGUSTÍ, Alvar, et al. GOLD 2023 executive summary: responses from the GOLD scientific committee. The European Respiratory Journal, 2023, 61.6: 2300616.
[10] TABAK, Monique; OP DEN AKKER, Harm; HERMENS, Hermie. Motivational cues as real-time feedback for changing daily activity behavior of patients with COPD. Patient education and counseling, 2014, 94.3: 372-378.
[11] BEINEMA Tessa, et at. Tailoring coaching strategies to users’ motivation in a multi-agent health coaching application. Computers in Human Behavior, 2021, 121: 106787.
[12] JUNG, Tony; VIJ, Neeraj. Early diagnosis and real-time monitoring of regional lung function changes to prevent chronic obstructive pulmonary disease progression to severe emphysema. Journal of Clinical Medicine, 2021, 10.24: 5811.
[13] OLIVEIRA, A. S., et al. Identification and assessment of COPD exacerbations. Pulmonology, 2018, 24.1: 42-47.
[14] COOPER, Christopher B., et al. Remote patient monitoring for the detection of COPD exacerbations. International Journal of Chronic Obstructive Pulmonary Disease, 2020, 2005-2013.
[15] TIWARI, Abhishek, et al. Remote copd severity and exacerbation detection using heart rate and activity data measured from a wearable device. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, 2021. p. 7450-7454.
[16] BELLOU, Vanesa, et al. Prognostic models for outcome prediction in patients with chronic obstructive pulmonary disease: systematic review and critical appraisal. Bmj, 2019, 367.
[17] SHAH, Syed Ahmar, et al. Exacerbations in chronic obstructive pulmonary disease: identification and prediction using a digital health system. Journal of medical Internet research, 2017, 19.3:e7207.
[18] SANCHEZ-MORILLO, Daniel; FERNANDEZ-GRANERO, Miguel Angel; JIMÉNEZ, Antonio León. Detecting COPD exacerbations early using daily telemonitoring of symptoms and k-means clustering: a pilot study. Medical & biological engineering & computing, 2015, 53: 441-451.
[19] FERNANDEZ-GRANERO, Miguel Angel; SANCHEZMORILLO, Daniel; LEON-JIMENEZ, Antonio. An artificial intelligence approach to early predict symptom-based exacerbations of COPD. Biotechnology & Biotechnological Equipment, 2018, 32.3: 778-784.

[20] WANG, Chenshuo, et al. Comparison of machine learning algorithms for the identification of acute exacerbations in chronic obstructive pulmonary disease. Computer methods and programs in biomedicine, 2020, 188: 105267.
[21] LENFERINK, Anke, et al. A self-management approach using self-initiated action plans for symptoms with ongoing nurse support in patients with chronic obstructive pulmonary disease (COPD) and comorbidities: the COPE-III study protocol. Contemporary clinical trials, 2013, 36.1: 81-89.
[22] LENFERINK, Anke, et al. Exacerbation action plans for patients with COPD and comorbidities: a randomised controlled trial. European respiratory journal, 2019, 54.5.
[23] SLOOTS, Joanne, et al. Adherence to an eHealth selfmanagement intervention for patients with both COPD and heart failure: results of a pilot study. International journal of chronic obstructive pulmonary disease, 2021, 2089-2103.
[24] TABAK, Monique, et al. A telehealth program for selfmanagement of COPD exacerbations and promotion of an active lifestyle: a pilot randomized controlled trial. International journal of chronic obstructive pulmonary disease, 2014, 935-944.
[25] ACEBES, Alberto, et al. Re-sample platform for training and use of copd exacerbation risk prediction models. European Respiratory Journal, 2024, 64.
[26] LEHMANN, Jakob, et al. Federated learning in multi-center, personalized healthcare for copd and comorbidities. In Proceedings 18th International Conference on Health Informatics (HEALTHINF 2025), 20-22 February 2025, Porto, Portugal, 2025. SCITEPRESS
[27] PAGLIARI, Giulio, et al. A multiple source data collection and integration paradigm for the creation of a dynamic COPD data mart. In Proceedings 18th International Conference on Health Informatics (HEALTHINF 2025), 20-22 February 2025, Porto, Portugal, 2025. SCITEPRESS
[28] Healthentia SaMD, “Healthentia Software as Medical Device”.  Available at https://healthentia.com. Accessed on 2/20/2025
[29] PNEVMATIKAKIS, Aristodemos, et al. Risk assessment for personalized health insurance based on real-world data. Risks, 2021, 9.3: 46.
[30] KYRIAZAKOS, Sofoklis, et al. Benchmarking the clinical outcomes of Healthentia SaMD in chronic disease management: a systematic literature review comparison. Frontiers in Public Health, 2024, 12: 1488687.
[31] NR, Anthonisen. Antibiotic therapy in exacerbations of chronic obstructive pulmonary disease. Ann Intern Med, 1987, 106.2:196-204.
[32] RODRIGUEZ-ROISIN, Roberto. Toward a consensus definition for COPD exacerbations. Chest, 2000, 117.5: 398S-401S. Fig. 8.

More Publications

The post A Real-Time COPD Exacerbation Detection Algorithm Using multi-morbid symptom diaries: Insights from a Multi-Site Study appeared first on Healthentia.

CATEGORY: Poster

SOURCE: European Respiratory Journal 2024 64(suppl 68), https://doi.org/10.1183/13993003.congress-2024.PA2319

RE-SAMPLE Platform for training and use of COPD exacerbation risk prediction models

Alberto Acebes, Serge Autexier, Marjolein Brusse-Keizer, Agni Delvinioti, Thrasyvoulos Giannakopoulos, Christiane Grünloh, Florian Hahn, Rain Jögi, Christos Kalloniatis, Konstantina Kostopoulou, Sofoklis Kyriazakos, Kostas Lamprinoudakis, Jakob Lehmann, Danae Lekka, Anke Lenferink, Federico Mazzone, Giulio Pagliari, Stefano Patarnello, Aristodemos Pnevmatikakis, Jarno Raid, Monique Tabak, Job Van Der Palen, Gesa Wimberg

More Publications

The post RE-SAMPLE Platform for training and use of COPD exacerbation risk prediction models appeared first on Healthentia.

CATEGORY: Health Informatics Journal

SOURCE: Sage Journals, October 15, 2025, https://doi.org/10.1177/14604582251387969

Advanced monitoring, alerting and feedback in early risk mitigation for pancreatic cancer

George Manias^1,2, Nelina Angelova³, Diana Kirova⁴, Aristodemos Pnevmatikakis³, Pencho Stefanov⁴, Fabio Melillo⁵, Oscar Garcia Perales⁶, Konstantina Kostopoulou³, Sofoklis Kyriazakos³, Dimosthenis Kyriazis¹

 

Abstract

A novel patient monitoring system is introduced, designed to support early risk mitigation in pancreatic cancer through personalized health interventions. The system aims to strengthen patient engagement and proactive care by enabling healthcare practitioners (HCP) to assign dynamic, data-driven and personalized mitigation plans. Central to this system is a user interface that allows HCP to review and assign tailored mitigation plans to patients. These plans are formulated based on primary clinical data and enriched with secondary behavioral data, such as wearable-derived metrics and self-reported inputs. These inputs are continuously collected, transformed into Holistic Health Records (HHRs), and stored in a scalable platform for integration with ML-based trend analysis and visualization. The article outlines the system’s technical architecture, patient data evaluation logic, and user experience across both the HCP interface and patient app. Evaluation by end users via questionnaires demonstrated improved adherence to plans and higher-quality behavioral data. This monitoring platform offers a promising tool for facilitating early risk intervention in pancreatic cancer care. By integrating multi-source patient data into actionable strategies and fostering bidirectional engagement, it bridges the gap between clinical insight and patient participation, contributing to holistic health management.

 

Introduction

The integration of internet and technology into healthcare has opened new horizons for patient care and disease management, marking a significant shift from traditional methods to more personalized and proactive approaches.^1–3 The iHelp platform⁴ is one such comprehensive solution designed to augment the capabilities of HCPs across various domains of patient management. This innovative system consolidates multiple components to offer a range of functionalities aimed at enhancing patient care, predicting health outcomes, and promoting healthier lifestyles. The patient Monitoring, Alerting and Feedback (MA&F) subsystem is the part of the iHelp platform that tailors and delivers the treatment plans.

To arrive at this point though, iHelp involves a data collection and processing subsystem⁵ that provides the patient MA&F subsystem with the patient context, as it is mapped into proprietary Holistic Health Records (HHRs) stored in the BDP.⁶ The HHR data is analyzed towards early risk predictions and personalized prevention measures.^7,8

Both raw and processed data is visualized in the Decision Support System (DSS) at the core of the iHelp platform. DSS is designed to support the dynamic needs of healthcare professionals and their patients. It acts as a central hub, providing seamless access to the platform’s diverse functionalities. HCPs can efficiently manage patient information, access predictive analytics, and implement personalized care plans without navigating through multiple applications or interfaces. Via DSS, the iHelp platform empowers HCPs to make informed decisions, tailor treatment plans, and manage potential risks more effectively.

Mitigation and action plans form the backbone of this patient care delivery and focus on promoting a healthier lifestyle and behavioral change in patients, while also tackling known comorbidities of the disease. Recognizing the impact of lifestyle choices on overall health, and the impact digital therapeutics have in managing, preventing and treating various conditions in the modern world,^1–3 the MA&F subsystem of iHelp enables the assignment of customized action plans. These plans are designed to encourage positive health behaviors and are delivered through Healthentia,^9–12 a patient companion app and its associated supporting backend services. The data collected and visualized through the Healthentia app includes both real world data (RWD) measurements (from integrated IoT devices like activity trackers) and self-reports (questionnaires, manual input records). Observed fluctuations on the latest data entries connected to an action plan shape future personalized care giving. Care delivery is also done via the Healthentia mobile app, namely its virtual coach⁹ that delivers dialogues to the patients. These dialogues offer continuous support and motivation, information on achievement or failure for the past period’s actions, and educational content. All dialogues are curated by experts and are triggered by the MA&F subsystem of iHelp and the supervision of the HCPs. This aspect of the iHelp system is instrumental in engaging patients in their own health management, fostering adherence to health recommendations, and ultimately leading to improved health outcomes.

The integration of these diverse functionalities within a single DSS represents a significant advancement in healthcare technology. The iHelp platform exemplifies how digital solutions can transform patient care, offering a more personalized, predictive, and participatory approach to healthcare. By equipping HCPs with the tools to remotely manage their patients and promote healthier lifestyles, the iHelp platform addresses the multifaceted nature of patient care in the digital age. This introduction sets the stage for a detailed exploration of the iHelp platform’s monitoring, alerting and feedback components, showcasing their operation and impact on healthcare delivery.

 

Methodology

The MA&F subsystem is used in different studies of iHelp related to pancreatic cancer. The studies have diverse aims falling into two groups: (i) individuals that are coached into healthier lifestyles to reduce their risk, and (ii) patients that are coached towards improved quality of life.

 

The MA&F subsystem functionality is delivered by four components. Two of them, the Monitoring & Alerting and the impact evaluator components are located in the iHelp BDP. The other two, the Smart Profiler and Virtual Coach components are part of Healthentia and are utilized by iHelp. The Monitoring & Alerting component is the starting point, as it manages the personalized care plans. Then, the Smart Profiler understands the patient context and the Virtual Coach handles the interaction of the patient with the delivered content. Finally, the Impact Evaluator understands the effect of the content delivered to the patient. These components are detailed in the following sub-sections.

 

Monitoring and alerting

The Monitoring and Alerting component facilitates the management and improvement of patient health through personalized action plans, leveraging both primary and secondary data sources. Primary data includes direct inputs from healthcare providers, whereas secondary data is gathered from wearable devices and questionnaires, tracking a range of configurable metrics such as physical activity, smoking habits, pain intensity and more. Although not all patients in the iHelp pilot studies are adhering to the data collection plans, it is established that the majority of patients would share their data with their HCP in long-term prevention activities.¹³ Figure 1 depicts the iHelp platform architecture and within it the Monitoring and Alerting component.

 

Figure 1. Overall iHelp Architecture, highlighting the two iHelp components of the MA&F subsystem, the Monitoring & Alerting and the Impact evaluator.

 

On the frontend side, the Monitoring and Alerting mechanism offers HCPs a React-based user interface (UI) to define offline rules and thresholds as part of the risk mitigation plans. The online evaluation of these rules in near real-time leads to dialogue proposals for the consideration of the HCPs, and the UI facilitates HCPs to make final selections for delivering the dialogues to patients. In that context, its main objective is to empower HCPs to assign mitigation plans and respective recommendations to a specific individual and then to monitor and assess the effect of these recommendations and plans in the lifestyle of the person. A mitigation plan is essentially an action plan assigned to a patient and typically the execution of this plan aims to bring concrete health improvements and to lower the risk of developing pancreatic cancer. It is comprised of several rules, some of which can be turned off, depending on the personalized configuration for the patient. The HCP will assign a goal value to each active rule of the mitigation plan selected for the patient. For example, a goal for a given patient can be to decrease the cigarettes smoked per day or to increase physical activity on a weekly basis. Then, the component will monitor and evaluate the progress of the patients by collecting and aggregating secondary (behavioral) data collected via the Healthentia mobile app, as self-reports or measurements, and then compare them with personalized targets issued by HCPs. To this end, Monitoring & Alerting enables the set of mitigation rules and facilitates the personalized interactions with the patients as depicted in Figure 3.

 

Figure 3. Inter-component communication.

 

The user journey begins when an HCP accesses the monitoring system’s UI through the DSS. This access point is the gateway to functionalities tailored to enhance patient care. It is also secured in compliance with the respective legal regulations towards an efficient access control and trustworthy data processing as described in Ref. 15. As shown in Figure 4, the HCP embarks on this process by assigning tailored mitigation plans and rules for each patient, which are crucial for guiding the patients towards healthier lifestyle choices and managing their health conditions effectively. After filling in all the settings, the HCP can see an overview of the assigned mitigation plan(s) for the current patient (Figure 5).

 

Lowering or increasing one of the secondary data metrics is a feasible goal that can be assigned to a case. Such an example is the increase of the patient’s physical activity, by setting an attainable threshold (e.g., walking at least 10,000 steps a day), and trace it through physical data progress monitoring. Secondary data collection fluctuations of the past days/weeks, give information on the goal’s accomplishment or failure and drive possible re-evaluations from the health expert’s side or the machine learning algorithms of other components. The patients are informed of their progress or new assignments through the app dialogues served as push notifications to the Healthentia mobile app, and can also track their progress from the numerous widgets.

The iHelp platform supports two modes of communication of the outcomes derived from the evaluation of these rules: automatic communication of the evaluation results to the patient via the Healthentia API, or placing the outcomes in a pending state, requiring HCP’s approval before communication. This decision is pivotal as it dictates the subsequent flow of information and involves considerations of patient sensitivity, the gravity of the health information, and the need for personalized HCP intervention.

Following the initial setup, the monitoring system embarks on a continuous cycle of evaluation, operating in the background without the need for manual intervention. At every predefined interval, the system evaluates the patient’s data in relation to the assigned actions and rules. This automated process ensures timely assessment of the patient’s progress or adherence to personalized health goals.

If the HCP has opted for automatic communication, the system proceeds to inform the patient of their progress through the Healthentia API immediately after each evaluation cycle. This message or dialogue, encapsulating the outcome of the evaluation, is designed to be informative and motivational, fostering patient engagement with their health objectives. Furthermore, this continuous approach enables the iHelp platform to promote a way to enhance patient communication with an intelligent coaching element.¹⁰ In contrast, if the HCP prefers to review the evaluation outcomes before the patient communication, the system stores an overview of the potential message in the BDP with a “proposed” status. This holding pattern allows for HCP oversight, ensuring that all patient communications are vetted for accuracy, appropriateness, and clinical relevance.

Concurrently, an overview of this communication is archived within the Big Data Platform (BDP) for record-keeping and future reference, ensuring a comprehensive health history is maintained.

The next phase involves HCP interaction with the DSS, where proposed communications are presented for review. The HCP accesses these messages through the DSS interface, where each message is accompanied by a “Send” button. This interface offers HCPs the flexibility to approve or reject the communication based on clinical judgment and patient-specific considerations.

Upon clicking “Send,” the approved message is dispatched to the patient via the Healthentia API, with its status in the BDP updated to “approved.” Conversely, if the HCP decides against sending the message, its status is updated to “rejected” in the BDP, and the message is withheld from patient communication. This step underscores the critical role of HCPs in curating and validating health information communicated to patients.

This overall workflow should be also supported by low response times that are essential for maintaining engagement, clinical utility, and the wider adoption of the system. Given the dynamic interaction model involving both automated and HCP-reviewed messaging workflows, any delays in patient feedback (either automatic or HCP-approved) could compromise timely intervention or behavior change momentum. Hence, the evaluation tests of the system were critical and it should be highlighted that they demonstrated an average response time of approximately 300 ms for HCP interface operations (e.g., assigning a mitigation plan, reviewing patient alerts, approving message dispatch). Moreover, the backend service availability exceeded 99.35% in high-demand simulations, supporting real-time communication with patients via the Healthentia API.

 

Virtual coach

The Virtual Coach is a Healthentia component⁹ that offers patients the UI for receiving and interacting with the delivered content at the mobile application. As such the component runs on the Healthentia mobile app, which is used as the iHelp patient companion app (facilitating data collection and advice delivery^10–12). Behind the scenes, it exposes an endpoint for receiving requests for dialogue delivery from the M&A component. In that call, the receiving patient and the intended dialogue are identified. Upon receiving the request, Healthentia pushes a notification to the mobile operating system (Android or iOS). The patient can tap either on the notification of the operating system, or on the notification at the dedicated application page. Then, the mobile view of the virtual coach is displayed, and the patient can go through the dialogue (Figure 6). After dialogue playback, the patient can still see the notification in the dedicated page, along with a summary of what it was about as a reference. The dialogues are handled (authored and played back) in the virtual coach using the open-source WOOL platform.¹⁶

 

 

Figure 6. Handling dialogues at the Healthentia mobile app. A notification is sent to the patient (left), which leads to the dialogue playback UI (right).

 

The dialogue selection procedure depends on the nature of the message to be delivered, and can be carried out both by the iHelp system (health experts and ML models) or Healthentia’s decision making smart component – the Smart Profiler,¹⁷ detailed below. Both components leverage the patterns of the newly collected secondary data and perform evaluations on thresholds and goal achievements. The Monitoring and Alerting (M&A) component is responsible for triggering communications on achievements/failures of mitigation plans and introducing new actions to the end users. The dialogue content is triggered when the M&A rules indicate so. The Smart Profiler is responsible for choosing and triggering educational content, that appears to the users as tips on coping with the disease, the importance of their assigned actions, and the ways of achieving their goals adopting a healthier lifestyle. The educational content is also delivered in dialogues, daily selected by the Smart Profiler.

 

Smart profiler

The Smart Profiler is the intelligent system that makes decisions on advice delivery inside Healthentia.¹⁷ It decides which educational dialogue should be triggered for a given user, based on the user’s data. The Smart Profiler is an expert system, evaluating rules associated with each educational item. These rules allow enumerating the importance of each item, based on the user data at the given time. Each rule is represented in the database as a mathematical expression (see example below) and is associated with one or more dialogues.

Dialogue selection starts with the evaluation of all the rules associated with the candidate dialogues, returning the initial playback probability of each dialogue. These initial probabilities are further weighted based on frequency of dialogue repetition and on dialogue impact. The probability of a dialogue selected frequently in the recent past is penalized for the future, to avoid the repetition of the same content for the same user, and thus make the dialogues more interesting and engaging. Impact is calculated through evaluating the short-term effect of the dialogue. If the. This is calculated as the ratio of the probability evaluation at the time of selection, and the average probability in the coming 3 days. If the probabilities in at least short-term are reduced, then the Smart Profiler decides the dialogue has a positive impact. The initial probabilities are weighted by that ratio calculated the previous time the dialogue was played back, increasing them for impactful dialogues.

Besides rule evaluation, the Smart Profiler also considers the optimal time within the day for sending a notification to the user, based on app usage logging. The system maintains a histogram of interactions with the mobile app versus time of day. Given a time interval, the histogram yields the optimum time for the next communication. This feature ensures that the notification will reach the end-user at the most optimal time, for them to pay attention and interact with the app and the coach. Figure 7 shows the conceptual architecture of content delivery decisions and triggers in iHelp. Decisions and recommendations are made either internally by the Smart Profiler, or externally by the iHelp M&A, and the dialogue ID selected for triggering is eventually passed to the VC service, responsible to make the request for serving the content. The serving itself is managed via WOOL.

Figure 7. Internal and external decision making and triggering of a feedback dialogue for the Alerting component.

 

The mechanism described in Figure 7 works towards achieving changes in the lifestyle of patients. These changes are interrelated with better self-management when dealing with chronic diseases. Factors ranging from education and understanding of the principles of a condition to limiting behavioral risk factors in different domains of behavior enable a defense against multi-sided chronic illnesses effects: comorbidities, diminished mental health and exacerbations. The Smart Profiler focuses on six domains: Physical activity, sleep, nutrition, self-care, smoking cessation and emotional health. Healthentia’s dialogues delivered by the Virtual Coach address factors and habits that may lead to risk behaviors, aiming at extended lifespan and health span of patients. Successful interventions for life-changing actions must be underpinned by theoretically-driven behavior change models for long lasting results,¹⁸ the Smart Profiler implements the Behavior Change Wheel (BCW) intervention design by Michie et al., for delivering life changing content and advice.¹⁹ Out of the various frameworks designed to serve and drive behavioral change,²⁰ BCW is an incorporation of 19 frameworks into a single coherent tool (Figure 8). The tool assesses the patient’s capability (C), opportunity (O), and motivation (M) for behavior (B) change (the COM-B model²¹). The behavioral change framework implemented within the Smart Profiler works along these three sources of human behavior, capability, opportunity and motivation, considering five intervention functions, namely Education, Training, Persuasion, Enablement and Incentivisation (out of the out of the nine functions introduced by the BCW). Different techniques can be applied for each intervention function, and Healthentia’s dialogues are assigned to these techniques. The Smart Profiler uses each patient’s contextual profile, including behavioral trends, current health goals, historical responses to dialogue types, and wearable/self-report data, to prioritize which intervention function (e.g., Persuasion vs Enablement) should be emphasized ensuring personalized behavioral alignment. For instance, a patient struggling with adherence might receive more persuasive and incentivizing dialogues, while one already engaged may receive educational reinforcement. This adaptive logic ensures that each dialogue delivered is behaviorally aligned and clinically relevant. The Smart Profiler ranks the domains, intervention functions and finally techniques, effectively selecting dialogues.

 

Figure 8. The Behavioral Change Wheel: The inner disk features the three sources of behavior, while the outer ring depicts the nine intervention functions, of which only the five in black are implemented within the Smart Profiler.

 

Discussion

The personalized dialogue and coaching system is an impactful innovation of the iHelp platform. It breaks the communication barriers between healthcare providers and receivers and facilitates behavioral change in patients and citizens by empowering them to understand their condition and providing easy to understand directions on how to manage their health. The rule-based dialogue selection system implemented in the Monitoring and Alerting mechanism effectively delivers personalized education and advice, thus impacting the everyday life of the patient or citizen at risk of developing cancer. Improved emphasis and understanding of the behavioral data can lead to improvements on the clinical condition of the patient, and change their lives for the better, as reported by the end-users of the solutions during the impact assessment performance. However, it is important to note that the questionnaires used to gather impact data were adapted from existing tools and pilot-tested but not formally validated for this specific study. To this end, there is the need to highlight that while the preliminary insights remain valuable, further validation in real-world setting and other use cases is envisioned to ensure the robustness and generalizability of the findings. Another limitation of this research work is that a thorough assessment of system usability, especially in the context of the HCP interface and patient-facing mobile app, was not feasible within the project’s timeline and this important dimension will be considered for inclusion in future work and projects.

 

Impact evaluator

The Impact Evaluator is responsible for evaluating the impact of the advice sent to groups of citizens/patients, as this advice is carried out via dialogues related to mitigation plans stemming from risk factors. It is shown in the overall iHelp architecture in Figure 1. The main goal is to monitor the behavior of citizens/patients and highlight to the HCPs how and if the specific type of advice changed the lifestyle of the recipients. For doing that, the citizens/patients are clustered using common characteristics (e.g. age, gender, BMI, or risk factors, if available) to compare the advice sent to a similar population). The result of this analysis should contribute to better finetune the model for generating the advice and the user to be reached. The input data is collected on demand of the HCP, both from the Monitoring and Alerting component (the goals, thresholds and their achievement) and the collected data (from the HHR using the standard FHIR API⁸). The impact is then evaluated, and the result is shown to the HCP through the dedicated iHelp platform interface.

The process is depicted in Figure 9. After clustering the advice recipients, the Impact Evaluator highlighted that for Topic1, a Cluster1 of people had a positive and healthy behavior after they received some prevention-based messages, but that was not the case for the promotion-based messages. Completely the opposite behavior was observed in Cluster2. Cluster3 of Topic1 remained unaffected. The percentage represented on the ordinate axis is the delta percentage of the achieved goal between the period before and after receiving the messages.

 

 

Figure 9. Clustering and Results. (a) Depicts the user journey and clustering approach of the Impact Evaluator; (b) Showcases an initial example of the final outcome.

 

Results

iHelp was evaluated during pilot studies that focused on the applicability of the clinical and technical outcomes through representative scenarios, while providing useful feedback about the iHelp concepts and technologies. Five pilot studies, carried out during the progress of the project, aimed to address three different aspects of the management of cancer: Primary prevention, Secondary prevention and Monitoring of treatments, while widening the field of types of cancers tackled to four, namely prostate, breast, anal and liver cancer. All pilots and technical partners worked in performing impact assessments (qualitative and quantitative) on both technological implementations and social factors, in the scope of prevention, early detection and treatment of cancer.

In all three cases the MA&F subsystem of iHelp delivered content to the patients. In total 600 items of content have been delivered. These span six domains: alcohol consumption (5.17% of the total content), general health including smoking cessation (9.83%), nutrition (15.5%), physical activity (23.5%), sleep (8.67%) and stress (37.3%). The patient then has the option to ignore or go through the content (complete it). Then they can choose to offer feedback on completed content. Some of it is positive. The volume of delivered, completed and positively received content across the different domains is shown in Figure 10.

 

 

Figure 10. Volume of delivered, completed and positively received content across the six domains.

 

While technological assessment is of high priority for any component made and destined to serve clinical studies, health experts and patients, the assessment of the impact of iHelp outcomes on socio-physical, mental and societal factors positively influencing a person’s health and life, remains the ultimate challenge. The evaluation of the program involved reports (questionnaires) to both clinicians participating in the study and end-users of the solution offered, on four main domains: physical, psychosocial, health knowledge and social aspects. Questionnaires were distributed online or on hospital premises after a specific timeframe of enrolment into the study or upon study completion, and the results are shown in Figure 11. It should be noted that these questionnaires were created and adapted based on existing instruments but were not validated for this specific study. They were, however, pilot-tested before deployment.

 

 

Figure 11. Evaluation of the iHelp solution impacts on patients’ lives.

 

 

Discussion

The personalized dialogue and coaching system is an impactful innovation of the iHelp platform. It breaks the communication barriers between healthcare providers and receivers and facilitates behavioral change in patients and citizens by empowering them to understand their condition and providing easy to understand directions on how to manage their health. The rule-based dialogue selection system implemented in the Monitoring and Alerting mechanism effectively delivers personalized education and advice, thus impacting the everyday life of the patient or citizen at risk of developing cancer. Improved emphasis and understanding of the behavioral data can lead to improvements on the clinical condition of the patient, and change their lives for the better, as reported by the end-users of the solutions during the impact assessment performance. However, it is important to note that the questionnaires used to gather impact data were adapted from existing tools and pilot-tested but not formally validated for this specific study. To this end, there is the need to highlight that while the preliminary insights remain valuable, further validation in real-world setting and other use cases is envisioned to ensure the robustness and generalizability of the findings. Another limitation of this research work is that a thorough assessment of system usability, especially in the context of the HCP interface and patient-facing mobile app, was not feasible within the project’s timeline and this important dimension will be considered for inclusion in future work and projects.

 

Conclusions

This research work introduced the conceptual design and prototype development of a novel patient monitoring system applied on advancing the early risk mitigation of pancreatic cancer. The prototype integrates a core Monitoring and Alerting component, supported by several sub-components and microservices based on a modular architecture. This design ensures interoperability and demonstrates the system’s ability to integrate with divergent mechanisms and components and a seamless deployment into real-world settings and environments. The latter is facilitated through the utilisation of clinical, behavioral, and patient-reported data, enabling HCPs to design and assign tailored mitigation plans, while supporting patients through adaptive coaching and continuous feedback.

Initial pilot evaluations presented in this manuscript highlighting the feasibility of the system in real-world healthcare environments. The qualitative and quantitative analysis of the results suggest that the platform can effectively deliver actionable insights and promote adoption of healthier behaviors by the individuals following personalized mitigation plans designed by their HCPs. Moreover, the clustering-based Impact Evaluator offers an evidence-driven approach to understanding how tailored feedback influences patient subgroups, thereby informing future refinements.

These achievements highlight the importance of designing and deploying scalable and patient-centered solutions in the modern healthcare landscape that also focus on integrating predictive analytics with personalized interventions and recommendations. This will further result to a more preventive, participatory, and data-driven model of care as HCPs will be empowered with advanced monitoring tools and patients will be engaged into a better management of their own health.

 

References
1. Paschou M and Sakkopoulos E. Personalized assistant apps in healthcare: a systematic review. In: Proceedings of the 2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA), PATRAS, Greece, July 2019. IEEE, pp. 1–8.

2. Anthonia Okolo C, Babawarun O, Arowoogun JO, et al. Rawlings chidi the role of Mobile health applications in improving patient engagement and health outcomes: a critical review. Int J Sci Res Arch 2024; 11: 2566–2574.

3. Dhar E, Bah AN, Chicchi Giglioli IA, et al. A scoping review and a taxonomy to assess the impact of Mobile apps on cancer care management. Cancers 2023; 15: 1775.

4. Manias G, Op Den Akker H, Azqueta A, et al. iHELP: personalised health monitoring and decision support based on artificial intelligence and holistic health records. In: Proceedings of the 2021 IEEE Symposium on Computers and Communications (ISCC). Athens, Greece, September 5 2021: IEEE, pp. 1–8.

5. Manias G, Azqueta-Alz´uaz A, Damiani A, et al. An enhanced standardization and qualification mechanism for heterogeneous healthcare data. In: H¨agglund M, Blusi M, Bonacina S, et al. (eds). Studies in Health Technology and Informatics. IOS Press, 2023. ISBN 978-1-64368-388-1.

6. Manias G, Kouremenou E, Alz´uaz AA, et al. An optimized pipeline for the processing of healthcare data towards the creation of holistic health records. In: Proceedings of the 2023 International Conference on Applied Mathematics & Computer Science (ICAMCS), Lefkada Island, Greece, August 8 2023. IEEE, pp. 50–56.

7. Ke TM, Lophatananon A and Muir KR. Risk factors associated with pancreatic cancer in the UK bioban cohort. Cancers 2022; 14: 4991.

8. Manias G, Azqueta-Alz´uaz A, Dalianis A, et al. Advanced data processing of pancreatic cancer data integrating ontologies and machine learning techniques to create holistic health records. Sensors 2024; 24: 1739.

9. Op Den Akker H, Cabrita M and Pnevmatikakis A. Digital therapeutics: virtual coaching powered by artificial intelligence on real-world data. Front Comput Sci 2021; 3: 750428.

10. Kyriazakos S, Pnevmatikakis A, Cesario A, et al. Discovering composite lifestyle biomarkers with artificial intelligence from clinical studies to enable smart eHealth and digital therapeutic services. Front Digit Health 2021; 3: 648190.

11. Pnevmatikakis A, Kanavos S, Matikas G, et al. Risk assessment for personalized health insurance based on real-world data. Risks 2021; 9: 46.

12. Kyriazakos S, Pnevmatikakis A, Op Den Akker H, et al. The role of big data and artificial intelligence in clinical research and digital therapeutics. In: Cesario A, D’Oria M, Auffray C, et al. (eds). Personalized Medicine Meets Artificial Intelligence. Springer International Publishing, 2023, pp. 63–81. ISBN 978-3-031-32613-4.

13. Bove LA. Increasing patient engagement through the use of wearable technology. J Nurse Pract 2019; 15:535–539.

14. Narkhede N. Kafka: the definitive guide: real-time data and stream processing at scale. 1st ed. O’Reilly Media, 2016. ISBN 978-1-4919-3616-0.

15. Chen Y, Sun W, Zhang N, et al. Towards efficient fine-grained access control and trustworthy data processing for remote monitoring services in IoT. IEEE Trans Inf Forensics Secur 2019; 14: 1830–1842.

16. Beinema T, Op Den Akker H, Hofs D, et al. The WOOL dialogue platform: enabling interdisciplinary userfriendly development of dialogue for conversational agents. Open Res Europe 2022; 2: 7.

17. Beinema T, Op Den Akker H, Hermens HJ, et al. What to discuss? A blueprint topic model for health coaching dialogues with conversational agents. Int J Hum Comput Interact 2023; 39: 164–182.

18. Michie S and Abraham C. Interventions to change health behaviours: evidence-based or evidenceinspired? Psychol Health 2004; 19: 29–49.

19. Michie S, Van StralenMMandWest R. The behaviour change wheel: a new method for characterising and designing behaviour change interventions. Implement Sci 2011; 6: 42.

20. Ara´ujo-Soares V, Hankonen N, Presseau J, et al. Developing behavior change interventions for selfmanagement in chronic illness: an integrative overview. Eur Psychol 2019; 24: 7–25.

21. Barker F, Atkins L and De Lusignan S. Applying the COM-B behaviour model and behaviour change wheel to develop an intervention to improve hearing-aid use in adult auditory rehabilitation. Int J Audiol 2016; 55: S90–S98.

More Publications

The post Advanced monitoring, alerting and feedback in early risk mitigation for pancreatic cancer appeared first on Healthentia.

Healthentia by Innovation Sprint, together with partners from the iHelp consortium, has contributed to groundbreaking research published in the Health Informatics Journal (SAGE, 2025). The paper, “Advanced Monitoring, Alerting and Feedback in Early Risk Mitigation for Pancreatic Cancer” , presents a novel digital system designed to support early risk mitigation in pancreatic cancer through personalized health interventions and intelligent patient monitoring. You can read the full publication here: https://doi.org/10.1177/14604582251387969

A New Paradigm in Digital Health

Pancreatic cancer remains one of the most challenging diseases to detect and treat early. The iHelp platform—powered by Healthentia and other core components developed by Innovation Sprint—offers a new way to strengthen patient engagement and proactive care. The system enables healthcare professionals to design, monitor, and adapt personalized mitigation plans based on both clinical data and behavioral insights derived from wearables and self-reports.

How It Works

At the heart of this approach lies the Monitoring, Alerting, and Feedback (MA&F) subsystem of iHelp. This subsystem connects several advanced components:

• Monitoring & Alerting: Allows healthcare professionals to create tailored mitigation plans and continuously evaluate patients’ progress using real-world and self-reported data.
• Virtual Coach (Healthentia): Engages patients through personalized dialogues, feedback, and educational content designed to encourage healthy behaviors and adherence.
• Smart Profiler: Uses intelligent decision-making algorithms to select the most appropriate content and timing for each patient interaction, applying the Behavior Change Wheel model to promote lasting lifestyle change.
• Impact Evaluator: Analyzes the effects of different types of advice on patient behavior, helping healthcare providers fine-tune future interventions.

These elements work together to form a closed feedback loop—from data collection and analysis to patient engagement and outcome evaluation.

Evidence from Pilot Studies

The system was evaluated through multiple pilot studies across Europe focusing on cancer prevention and patient quality of life. Participants received over 600 pieces of personalized content across key lifestyle domains such as physical activity, nutrition, sleep, and stress. Results indicated increased adherence to action plans, improved quality of behavioral data, and enhanced engagement between patients and healthcare providers.

 A Step Toward Predictive and Preventive Healthcare

By integrating AI-driven analytics, wearable data, and behavioral science, iHelp represents a major step toward a predictive, preventive, and participatory model of healthcare. For Innovation Sprint, this achievement underscores our commitment to advancing digital therapeutics and data-driven health management through platforms like Healthentia.

As healthcare continues its digital transformation, the collaboration behind iHelp demonstrates how multidisciplinary innovation can turn patient data into actionable insights—bridging the gap between clinical expertise and personalized patient empowerment.

The post Advancing Early Risk Mitigation in Pancreatic Cancer with Personalized Digital Health appeared first on Healthentia.

We have published a paper in the Journal of Medical Internet Research (JMIR), where we present a holistic framework for designing and executing behavior change strategies through a multiagent reasoning system. This framework, implemented in Healthentia, enables personalized digital coaching by selecting the most effective techniques based on individual assessments and real-world data. In the study, we explored its application in patients with type 2 diabetes, showing promising results in improving glucose levels, weight, and BMI. You can read the full publication here: doi:10.2196/73807.

Advancing Digital Coaching for Sustainable Lifestyle Change in Type 2 Diabetes

Risky lifestyle behaviors remain one of the most pressing challenges in global health, contributing to the rising burden of chronic diseases. Despite wide recognition of the need for healthier long-term habits, achieving meaningful and lasting behavioral change continues to be difficult. Traditional interventions often fall short in promoting sustained motivation, and cost-effective digital solutions that adapt to individual needs are still limited.

At Healthentia, we are committed to bridging this gap by leveraging science-driven innovation in digital health. Our latest research presents a holistic framework designed to transform lifestyle behavior change through personalized digital coaching, powered by an automated multiagent reasoning system.

A Science-Backed Multiagent Framework

This framework brings together established behavioral change science and the practical strength of Healthentia’s certified SaMD (Software as a medical device). At its core, the system uses multiagent reasoning to select the most effective coaching strategies for everyone based on personal assessments and daily health and lifestyle data.

By prioritizing evidence-based BCTs (Behavioral Change Techniques) with the strongest impact on change, Healthentia’s digital coaching adapts in real time to user progress and engagement patterns. This ensures that interventions are not only relevant but also sustainable, empowering patients to take ownership of their health journey.

Application in Type 2 Diabetes Management

To illustrate this approach, we applied the behavioral change coaching scheme in a study involving patients with Type 2 Diabetes during a total of 12 weeks intervention plan with a 2-week assessment and adherence control weeks. Nine participants were monitored using Healthentia SaMD for remote care and personalized coaching content delivery.

The outcomes were highly encouraging. Within the group, fasting glucose levels dropped by an average of –17.3 mg/dL, supported by a large effect size and strong statistical significance. Patients also experienced meaningful reductions in weight (–2.89 kg) and BMI (–1.05 kg/m²). Importantly, the personalized coaching delivered through Healthentia resonated with patients, with over 71% of the opened, recommended content received positively.

These results demonstrate the potential of combining behavioral science with adaptive digital coaching to create measurable improvements in health outcomes.

What This Means for the Future

While these findings are preliminary, they highlight a promising path forward. Future directions include refining the multiagent selection process, expanding the type 2 diabetes program with more comprehensive health markers, and broadening the applications of this framework to other chronic conditions.

Further to the CE-marked virtual coaching module of Healthentia, wellbeing coaching support that is supported by genAI technologies can have strong influence to the patients’ behavior. This is to be studied and presented in future work.

Healthentia’s mission is to advance decentralized care with digital tools that are not only clinically robust but also deeply human-centered. By fusing data-driven intelligence with personalized coaching, we are helping patients break free from the limitations of one-size-fits-all health advice—giving them the right support at the right time.

The post Personalized Digital Coaching for Type 2 Diabetes: An Innovative Approach to Sustainable Lifestyle Change appeared first on Healthentia.

CATEGORY: Digital Health

SOURCE: JMIR Publications Advancing Digital Health & Open Science, July 2025, doi:10.2196/73807

Multidomain Behavioral Change Digital Coaching for Chronic Disease Management in Patients With Type 2 Diabetes: Framework Development and Preliminary Evaluation

 Konstantina Kostopoulou¹, Danae Lekka¹, Aristodemos Pnevmatikakis¹, Nellie Angelova¹, Stefanos Tamouridis³, Panos Stafylas^1,2, Alexandra Bargiota³, Sofoklis Kyriazakos¹

¹Innovation Sprint Srl, Belgium

²Healthlink

³University of Thessaly, Greece

More Publications

The post Multidomain Behavioral Change Digital Coaching for Chronic Disease Management in Patients With Type 2 Diabetes: Framework Development and Preliminary Evaluation appeared first on Healthentia.

The paper highlighted how the platform addressed the fragmented nature of heart failure care by enabling continuous communication between hospital specialists and community healthcare providers.

Study Design and Implementation

The AZIMUTH study (FondAZione A. Gemelli IRCCS Artificial Intelligence Empowered Digital PlatforM to sUpport paTients with Heart Failure) addressed this healthcare challenge through innovative digital health technology. It demonstrates how smartphone-based care could transform outcomes for heart failure patients. This multicenter, prospective study enrolled 300 heart failure patients across four leading Italian medical centers in Phases 1 and 2.

The study utilized Healthentia v3, a Class I Software as Medical Device (SaMD), as the core platform for remote patient monitoring and care delivery operating through two integrated components:

Patient Mobile Application: Patients used intuitive “widgets” for daily health monitoring, including mandatory weight and blood pressure tracking, validated questionnaires (Kansas Questionnaire and medication adherence assessments), and optional monitoring of heart rate, oxygen saturation, and physical activity. The app seamlessly integrated with Bluetooth-enabled devices to minimize manual entry errors.

Clinical Dashboard: Healthcare providers accessed a platform that consolidated patient data into actionable insights, featuring real-time monitoring, intelligent alert systems based on clinical thresholds, longitudinal trend analysis, and integrated patient communication tools.

The study carefully addressed the real-world implementation by establishing clear inclusion criteria that balanced technological requirements with practical applicability. Patients required basic digital literacy or caregiver support, smartphone compatibility, and received comprehensive training during enrollment. The platform was designed for intuitive use across age groups, ensuring broad accessibility.

Proven Results

The study successfully demonstrated the effectiveness of digital health solutions in heart failure management:

Patient Engagement: Achieved the primary objective with over 70% of patients successfully engaging with the digital platform throughout the study period.

Clinical Improvements: Patients showed significantly improved medication adherence and treatment engagement compared to traditional care approaches.

Healthcare Provider Value: Clinicians reported enhanced ability to monitor patients remotely, identify early warning signs, and coordinate care more effectively.

Feasibility Confirmed: The app-based model proved both technically feasible and clinically valuable across diverse patient demographics.

Impact and Validation

AZIMUTH validated that smartphone-based care could transform outcomes for heart failure patients – a population traditionally challenged by frequent hospitalizations and complex medication regimens. The study proved that digital health solutions, when properly implemented through certified medical device platforms like Healthentia, could enhance both patient outcomes and healthcare efficiency.

The successful completion of AZIMUTH Phase 1 established a new evidence base for digital health adoption in chronic disease management. Azimuth demonstrated that collaborative innovation between healthcare institutions, pharmaceutical companies, and technology providers can deliver measurable clinical value. A second paper with results from Phase II is expected soon and new partners have joined efforts in a new study named Azimusa utilizing the Azimuth care model and expanding further the scope to more medical centers in the north with more patients.

The post AZIMUTH Study: Digital Transformation in Heart Failure Care appeared first on Healthentia.

What Is B-COMPASS?

At its core, B-COMPASS helps all stakeholders in Healthcare from clinicians, caregivers, software providers, and healthcare policymakers to identify the drivers behind patient behavior. It relies on a concise set of fewer than ten questions to generate a patient profile based on five key dimensions: health consciousness, treatment needs, personal concerns, acceptance, and perceived control.

This simplicity makes it powerful. It enables the creation of tailored communication and support strategies to address the unique challenges each patient faces, ultimately aiming to improve adherence and treatment outcomes.

How Innovation Sprint Is Contributing

As a proud partner in the BEAMER project, Innovation Sprint brings deep experience in real-world data collection, behavioral modeling, and chronic disease management through our flagship Software as a Medical Device (SaMD), Healthentia.

With years of insights from managing patient journeys, particularly around non-adherence patterns, Innovation Sprint contributes to shaping and validating the B-COMPASS model with real-world scenarios. Our involvement ensures the model reflects actual patient needs and clinical realities, making it both usable and impactful in digital health platforms.

Through Healthentia, we have seen firsthand how variable patient engagement can be, and how crucial it is to adapt digital interventions to individual needs. Integrating tools like B-COMPASS enhances our ability to design adaptive programs that not only monitor but also positively influence patient behavior over time.

Why B-COMPASS Matters for SaMDs like Healthentia

Tools like B-COMPASS don’t just provide insight, they enable action. For SaMDs, this means gaining the ability to segment patients more meaningfully and respond with personalized interventions, educational content, and coaching.

The result? Increased treatment adherence, improved patient satisfaction, and reduced healthcare burden—goals at the heart of both BEAMER and Innovation Sprint’s mission.

Looking Forward

As B-COMPASS matures within the BEAMER framework, its integration into digital health ecosystems like Healthentia will further personalize chronic disease management. We believe this marks a pivotal step toward scalable, human-centered digital healthcare.

To learn more about B-COMPASS and the BEAMER project, visit https://beamerproject.eu/BEAMER-model/.

The post Enhancing Patient Adherence with B-COMPASS: A New Horizon for Digital Health Solutions appeared first on Healthentia.

CATEGORY: Digital Health

SOURCE: European Heart Journal – Digital Health, April 2025, https://doi.org/10.1093/ehjdh/ztaf040

Study design and rationale of the AZIMUTH trial: a smartphone, app-based, E-health-integrated model of care for heart failure patients

Domenico D’Amario¹, Attilio Restivo^2,3, Renzo Laborante^2,3, Donato Antonio Paglianiti^2,3, Alfredo Cesario^2,3,4,5, Stefano Patarnello², Sofoklis Kyriazakos⁶, Alice Luraschi², Konstantina Kostopoulou⁶, Antonio Iaconelli^2,3, Enrico Incaminato¹, Gaetano Rizzo¹, Marco Gorini⁷, Stefania Marcoli⁷, Vincenzo Bartoli⁷, Thomas Griffiths⁸, Peter Fenici^3,7,9, Simona Giubilato¹⁰, Maurizio Volterrani¹¹, Giuseppe Patti¹, Vincenzo Valentini^2,3, Giovanni Scambia^2,3, Filippo Crea^3,12

More Publications

The post Study design and rationale of the AZIMUTH trial: a smartphone, app-based, E-health-integrated model of care for heart failure patients appeared first on Healthentia.