A digital therapy pathway is a healthcare method that employs technology to provide support and therapy services to patients remotely.  These technologies can include wearables and a mobile app for collecting data, an online platform for visualization purposes, video conferencing and chatting for direct communication between clinicians and patients, and a virtual companion service that can support the patient by giving personalized advice [2].

Typically, the process of digital therapy includes many steps [3]. These can include:

1. A first assessment of each patient to determine the best therapy approach
2. Set of clear goals that are specific, measurable, and achievable defined by healthcare professionals
3. Progress monitoring with the use of questionnaires and other digital tools allows healthcare professionals to keep track of the effectiveness of the treatment and adjust it as required

For the last step, a digital evaluation method of the data collected can be implemented where the predefined goals are transformed into critical rules for the health progression. This performance assessment can automatically alert the patient through the mobile app when a measurable attribute is out of range or provide guidance, feedback, and support as patients work towards achieving their goals. This will be achieved with the use of a virtual companion service, that will trigger a dialogue on a regular basis in order to give advice in a personalized manner to ensure progress towards the goals.

To conclude, digital therapy pathways can be an effective way to deliver therapy services to patients who need continuous monitoring and have difficulty accessing traditional in-person therapy, such as those who have mobility issues and also it can thrive in areas where demand for traditional treatment outgrows its capacity [3].

Up to this point, digital therapy is mostly used to supply psychotherapy [4] and Healthentia can be used to provide such services as it incorporates all the aforementioned tools, aspiring to effectively support also other diseases than mental health conditions. Healthentia can provide feedback and in combination with a virtual coaching service, orchestrated by a predefined digital clinical pathway, it can create a personalized approach to improve someone’s health. However, it is important to always take into account patients’ mental health needs, as in some cases in-person therapy may be required.

References

[1] “Global Digital Therapeutics Market Report 2022: Analysis & Forecasts 2020-2026 – Market to Reach $12.1 Billion by 2026” (accessed May 15, 2023).

[2] C. Moore, “What Is Digital Therapy and How Does It Really Work?”, Quenza, Aug. 13, 2021. (accessed May 15, 2023).

[3] “Digital Therapeutics: How Software Can Treat Diseases” AltexSoft. (accessed May 15, 2023).

[4] A. Nwosu, S. Boardman, M. M. Husain, and P. M. Doraiswamy, “Digital therapeutics for mental health: Is attrition the Achilles heel?”, Frontiers in Psychiatry, vol. 13, 2022, Accessed: May 15, 2023. [Online].

The post Digital Therapy Pathway & Patient Monitoring appeared first on Healthentia.

What is WOOL?

Let’s start by diving into the question: what is WOOL? WOOL is an open-source (MIT Licensed) software platform for authoring and executing scripted dialogues between virtual agents and users. The platform includes a visual editor tool that allows domain experts to author these dialogue scripts without necessarily having experience in writing code or script in general. The platform also includes parsers – software modules that can read, interpret and execute these dialogue scripts to power web- or mobile applications. At this moment, there is a parser written in Java and one written in JavaScript. By including the dialogue scripts and embedding the parser in your web- or mobile application, you can easily include a virtual agent that can have natural language dialogues with the users of your system. How you design your user interface, and the specifics on how users interact with the virtual agent is up to you as a designer and developer of the application. However, the principles of WOOL dialogues are based on offering users a fixed number of choices of “reply options” – an interaction paradigm that is often found in video games. In fact, WOOL is based on the open-source Yarn Platform, which was developed for creating narrative-driven video games.

The image below shows the workflow of writing a dialogue script in the WOOL Editor (left), to using the Parser tools and finally arriving at a mobile phone app user interface (right).

WOOL in Healthentia

As the Healthentia platform is extending its scope to supporting Digital Therapeutics (DTx), a large emphasis is given to supporting the end-users (e.g., patients) in managing their health. This support is offered in various ways: better feedback and information about their own behaviour, improved communication between healthcare professionals and the user, and the inclusion of a digital virtual coach. This digital virtual coach will be a companion to patients using the Healthentia application and will guide them throughout their digital therapeutic intervention. The coach can assist the patient with technical questions, provide information on their condition or disease, and also provide tailored advice on how the patient can improve in certain lifestyle factors.

This digital virtual coach is powered by a large number of systems that work together to ensure the advice provided by the coach is correct, and optimally tailored to the patient. Data is processed and interpreted, the state of the patient is modelled in a detailed clinical pathway, and all this information is taken into account when deciding on the topics of conversation between the coach and the patient. Keep an eye on this blog for further details on these processing steps. For now, it is enough to mention that the content of the digital virtual coach is provided by WOOL dialogues.

Why not Chatbot Platform X?

You might wonder why we choose to use WOOL instead of one of the many chatbot platforms that are out there. Well, this has to do mainly with quality and control. Chatbot frameworks like Google DialogFlow, Amazon Lex, or Microsoft Azure Bot Service offer powerful tools for natural language understanding, modelling conversation flows and connecting to your underlying Knowledge Base to make sure the user’s intent is matched with the right answer. Chatbots that are built using this type of platforms are quickly gaining popularity and perform better and better in their intended roles: answering user questions.

Testimonials of companies using these platforms generally follow the same pattern: “At AwesomeTech we managed to resolve 40% of our customer queries using DialogFlow!”, “At BlueSkiesAirlines we managed to streamline our booking flow using Azure Bot Service!”. Imagine having a call center with hundreds of employees that have to answer the same type of customer questions over and over again… you may be inclined to automate this process. And that’s where most Chatbot Platforms are made for.

Does Healthentia have customers that ask the same questions every day? Questions that have a simple answer, and can be resolved in a few steps? Well, not really. We do not want to build a customer-service agent (patient-service agent?), we do want to build a personal companion for patients that can build up a personal relationship with the patient over longer periods of time, and offer engaging, tailored conversations that help keep the patient on track in his or her digital therapeutic intervention. We strongly believe we need to pick the right tool for the right job, and chatbot services are not it.

WOOL in EU Projects

The WOOL Platform itself was born out of a European Horizon 2020 research project, called Council of Coaches. The Council of Coaches project aimed to develop a platform in which multiple embodied conversational coaches could aid users in various health domains towards a healthy lifestyle. The underlying platform – WOOL, was released as an open source outcome of this project (as well as the 3D Embodied Conversational Agent Platform called “Agents United”). So, WOOL was developed specifically with the eHealth use case in mind and is a platform that is still very much under development.

WOOL is currently being used and expanded upon in various European research projects. The first one is the H2020 iHelp project in which Innovation Sprint will support various pilots that will be ran targeting pancreatic (and other forms of) cancer. Second is the H2020 RE-SAMPLE project, focusing on COPD patients that also suffer from comorbidities in which both Innovation Sprint and RRD work to create a virtual companion for the patients. RRD is also using the WOOL Platform in the H2020 SmartWork and AAL Leaves projects. All in all, support and uptake of the WOOL Platform is ensured for the foreseen future.

So, what’s next?

In the coming months, Innovation Sprint will be releasing various updates to its Healthentia platform that will slowly introduce the DTx features into the platform, including the digital virtual coach, powered by WOOL. Keep an eye on our website and blog for future updates!

Follow the WOOL Platform on Twitter @WOOLPlatform or check out the website at www.woolplatform.eu and finally, you can follow Innovation Sprint on Twitter to get notified of future blog updates: @InnovSprint

The post The WOOL Platform in Healthentia 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.