CATEGORY: Ontologies and Machine Learning Techniques

SOURCE: MDPI Open Access Journals, Sensors, March 2024, 24(6), 1739; https://doi.org/10.3390/s24061739

Advanced Data Processing of Pancreatic Cancer Data Integrating Ontologies and Machine Learning Techniques to Create Holistic Health Records

George Manias¹, Ainhoa Azqueta-Alzúaz², Athanasios Dalianis³, Jacob Griffiths⁴, Maritini Kalogerini³, Konstantina Kostopoulou⁵, Eleftheria Kouremenou¹, Pavlos Kranas⁶, Sofoklis Kyriazakos⁵, Danae Lekka⁵, Fabio Melillo⁷, Marta Patiño-Martinez², Oscar Garcia Perales⁴, Aristodemos Pnevmatikakis⁵, Salvador Garcia Torrens⁸, Usman Wajid⁴ and Dimosthenis Kyriazis¹

More Publications

The post Advanced Data Processing of Pancreatic Cancer Data Integrating Ontologies and Machine Learning Techniques to Create Holistic Health Records appeared first on Healthentia.

Topics: eHealth, patient reported outcomes, e-clinical platform, smart eHealth

SOURCE: Front. Digit. Health, 06 September 2021;  BOOK DOI Link, Chapter DOI Link

Discovering Composite Lifestyle Biomarkers With Artificial Intelligence From Clinical Studies to Enable Smart eHealth and Digital Therapeutic Services

Sofoklis Kyriazakos ^1,2* ; Aristodemos Pnevmatikakis ¹ ; Alfredo Cesario ^1,3 ; Konstantina Kostopoulou ¹ ; Luca Boldrini ⁴; Vincenzo Valentini ^4,5 ; Giovanni Scambia ⁴ 

The post Discovering Composite Lifestyle Biomarkers With Artificial Intelligence From Clinical Studies to Enable Smart eHealth and Digital Therapeutic Services appeared first on Healthentia.

Lifesciences and Healthcare are considered to be slow-moving industries in terms of their digital transformation; however, this has been changing rapidly in the aftermath of the Covid-19 outbreak. In Innovation Sprint we believe that the surrounding environment of these industries pinning to strict regulatory requirements, should not influence the level of technology adoption. Given our tech-DNA, we opt for edge technologies and practices. These cover the best of the breed of architectural approaches, hosting environments, mobile apps, IoT devices, security infrastructures, continuous integration processes, AI and ML mechanics, and all other pieces of the puzzle for a state-of-the-art solution.

Let’s make a dive into the technologies we use in Healthentia and let’s see how we achieve high performance and compliance. Below, you can find an overall description of the system architecture, as well as a presentation of the infrastructure that maintains and facilitates Healthentia System performance.

System Architecture

Healthentia SaaS is a three-tiered application. The datastore tier contains one hosted Azure SQL database for structures study data and an Azure Blob storage for media and any other files. The application tier contains our services, the Web API, and the Web Platform. Finally, the client tier contains the Web Platform client (out portal app targeting the healthcare professionals) and the Mobile client (our Android and iOS app targeting the patients or study participants).
Additionally, a rest API developed in Python Django framework is responsible for Machine Learning Operations and communicates with Healthentia Platform, using Healthentia Web API exposed endpoints.

Hosting environment

Our Infrastructure is hosted on Microsoft Azure, in Western Europe and is based on a Kubernetes cluster on Azure Kubernetes service, which has the following benefits:

• Accelerates containerised application development
• Increases operational efficiency
• Builds on an enterprise-grade, more secure foundation
• Runs any workload in the cloud, at the edge, or as a hybrid

Kubernetes provides a way to schedule and deploy containers, scale them to the desired state and manage their lifecycles. In this way, Healthentia is a container-based application, thus portable, scalable and extensible. More information on Kubernetes: https://azure.microsoft.com/en-in/services/kubernetes-service/

Mobile apps

Our mobile app is built using React Native, a framework for building native apps for Android and iOS using React. It offers a unique user experience in the Bring Your Own Device approach we follow. The user interface is an outcome of co-development with patients, which is a process that is renewed for several therapeutic areas.

IoT devices

Healthentia supports a large number of IoT devices, through API or SDK integration. Prominent among them are all Fitbit and Garmin devices. Furthermore, it supports iOS Health Kit integration, which extends the spectrum of devices that can be used. Further to the above, Healthentia can capture activity information directly from the smartphones’ sensors, utilizing their hardware sensors (like the accelerometer and barometer) as well as their software ones (like the step sensor). This direct access to raw sensor data facilitates composite activity measurements, like the frailty test and the 6-minute walk test.

Security & Privacy

The high information security performance of the Healthentia is aspired to stand as one of its competitive advantages. Our Information Security Policy aims to:

• Εnsure the confidentiality, availability and integrity of the information it processes
• Protect the data subjects’ rights within the scope of its business operations
• Comply with the applicable legislative and regulatory requirements

Security is ensured at 3 levels: 1) infrastructure, 2) processes, 3) continuous security posture assessment and update.

CI-CD Infrastructure

Azure Build Pipelines are responsible to build our code from source control and create artefacts to be used from the release pipelines and the deployments. Build Pipelines exist in Azure DevOps to be triggered automatically by committing the branch they are linked to, or manually from Azure DevOps.
The release pipelines are responsible for publishing apps to the production and test environments. These pipelines deploy the newest application images (Web and API) from the docker repository to the Kubernetes cluster.

AI mechanics

The AI module of Healthentia offers three services: biomarker discovery, patient phenotyping and in-silico trials. The biomarker discovery and patient phenotyping services are carried out off-line and their results are available on-line: The discovered biomarkers are used in risk assessment, virtual coaching and DTx. The estimated phenotypes are used in the in-silico trials to modify the behaviors of the simulated patients based on data models.

For more information, you can contact us at info@innovationsprint.eu.

The post How Technology meets Clinical Research? appeared first on Healthentia.

A biomarker is a naturally occurring characteristic by which a pathological or physiological process can be identified. A digital biomarker comprises of objective, quantifiable physiological and behavioral data, measured utilising digital portable, wearable, implantable or digestible devices, to be used to predict and manage health-related outcomes.

Innovation Sprint has built a composite contextual biomarker-based οn multiple aspects of Real-World Data (RWD), collected from people unobtrusively, while following-up their normal living routine. It is composite in the sense that it is not based on a single measurement, but rather on multiple diverse measurements (objective RWD) and peoples’ reports (subjective RWD). It is contextual in the sense that not only the person is measured, but also the person’s lifestyle context: social and environmental aspects complement the more traditional physiological and psychological ones.

Our RWD

At Innovation Sprint we are strong advocates of the empirical knowledge that lifestyle is a strong determinant of health. Hence our biomarker is based on RWD spanning four important aspects of a person’s lifestyle:

 Physiological RWD quantifies physical behaviour (active vs sedentary lifestyle as measured by steps walked, floors climbed, activity types, minutes in different intensity levels or heart rate zones, resting heart rate, sleep characteristics) and includes body info (height, weight, gender, race), nutrition (water, other liquids, food) and symptoms (body temperature, cough, diarrhea, headache, nausea, pain, etc.).

 Psychological RWD quantifies at a simple level mood, and in more complex situations mental state collected via elaborate, domain-specific questionnaires. Measurements can also play a role, either directly e.g. facial expression recognition, or indirectly, e.g. weather where people are living).

 Social RWD quantifies social activity of people. This can be measured indirectly from the usage of the phone (diversity, duration, frequency of calls) and social media (diversity, number, frequency of interactions). More direct information can be reported using questionnaires on activities with friends, family or co-workers.

 Environmental RWD indicates the quality of life. Usually, reported by the users. Measurements of living or working environment quality are made with commercial devices (e.g. air quality meters).

AI for discovering our biomarker

Biomarker discovery at Innovation Sprint is done in three stages

Definition stage, where the domain experts select the clinically significant outcomes that need to be predicted by the biomarker(s).

Manual RWD selection stage, where domain knowledge is applied to refine our generic RWD selection into those lifestyle aspects that are relevant to the disease/condition in question.

Iterative design stage: Machine Learning/AI algorithms are used to train a proprietary classifier using the elected RWD to predict the selected clinically significant outcomes. The classifier is applied on new data  yielding predictions and insights leading to digital therapeutics.

Validating our approach

We employed RWD collected over 7 years to train a biomarker that predicts significant weight changes. Such a biomarker is important for patients with several diseases (e.g. NAFLD), as well as for the general population interested in well-being. We achieved over 80% or correct prediction of the outcome, while we also analysed the different RWD aspects that led each individual to positive or negative outcomes, in order to offer personalized coaching services.

As we speak, we are utilising the same approach in other therapeutic areas, e.g. cervical cancer, to predict low toxicity events. Starting from 2021 we will validate this hypothesis in much larger cohorts, targeting –among others- COPD patients with Cardiovascular Disease comorbidities.

We will keep you update on our observations and findings!

Aristodemos Pnevmatikakis
R&D Director, Innovation Sprint

The post ‘Discovering biomarkers’ appeared first on Healthentia.