Periodic Reporting for period 2 - WARIFA (Watching the risk factors: Artificial intelligence and the prevention of chronic conditions)
Berichtszeitraum: 2022-07-01 bis 2023-12-31
The United Nations has specifically addressed the need for preventing noncommunicable diseases in their "2030 agenda for sustainable development". WHO defines noncommunicable diseases as Chronic Conditions (CCs) caused by a combination of genetic, physiological, environmental and behavioural factors which can affect all age groups and countries. The leading causes of death for the citizens of the EU of CCs include cardiovascular diseases, cancers, chronic respiratory diseases, and diabetes. The management of CCs represents an increasing burden on health care systems worldwide.
The WARIFA project will develop a prototype of a combined early risk assessment tool that will provide individual citizens with personalised recommendations for the four main CCs.The WARIFA app will be available to individual citizens via a user-friendly app on their smartphone.
AI-based combined early risk assessment can empower citizens to adopt healthier habits and a better lifestyle by providing personalised recommendations on how to change their risk behaviour. The benefits of early risk assessment, prevention and intervention will be evident both at individual and at health care system level.
At individual level, citizens will be supported in improving by at least 20% each risk factor by increasing the level of physical activity; reducing sun exposure; or the number of hypoglycaemic events. At the health care level, WARIFA will contribute to the early diagnosis of CCs by promoting early identification of risks.
The WARIFA project will develop a prototype of a combined early risk assessment tool that will provide individual citizens with personalised recommendations for the four main CCs.The WARIFA app will be available to individual citizens via a user-friendly app on their smartphone.
AI-based combined early risk assessment can empower citizens to adopt healthier habits and a better lifestyle by providing personalised recommendations on how to change their risk behaviour. The benefits of early risk assessment, prevention and intervention will be evident both at individual and at health care system level.
At individual level, citizens will be supported in improving by at least 20% each risk factor by increasing the level of physical activity; reducing sun exposure; or the number of hypoglycaemic events. At the health care level, WARIFA will contribute to the early diagnosis of CCs by promoting early identification of risks.
WARIFA started on the 1st of January 2021 and has a duration of 48 months. The WARIFA consortium consist of 12 partners from six European countries.
The consortium gathered twice in 2023 for Consortium Wide Meetings from the 06th to the 08th of March in Las Palmas de Gran Canaria, Spain and from the 06th to the 08th of November, in Frankfurt, Germany.
The following main results were achieved by December 2023:
1. Periodic activity and ethics management report - update
2. Periodic risk and ethic management report - update
3. Review report on stakeholders’ roles, needs and preferences
4. Web page included in the WARIFA website containing a prototype of map display of the community risk profiles for the pilot communities studied in Romania, Spain and Norway
5. Final version of blueprint of the AI preventive system including input and output variables, end-user interface design and usability-related requirements
6. Demonstration of the data acquisition functionalities as part of the WARIFA app
7. Report on the specifications of the WARIFA app interface
8. Description of the designed graphical user interfaces and data acquisition functionalities
9. Pilot prototype on heterogenous data for monitor risk factors and to provide preventive behavior over time
10. Method for generating the optimum model to be transmitted to WP6 based on information from WP4
11. Construction of probabilistic network
12. Establishing the inference method
13. Co-creation report
14. Stakeholders analysis
15. Dissemination activities report
16. Business & Commercialisation Plan
17. Plan for the dissemination and exploitation of results - update
The following milestones were reached by December 2023:
Front end (20 Dec 2022)
WARIFA prototype (30 Dec 2023)
The consortium gathered twice in 2023 for Consortium Wide Meetings from the 06th to the 08th of March in Las Palmas de Gran Canaria, Spain and from the 06th to the 08th of November, in Frankfurt, Germany.
The following main results were achieved by December 2023:
1. Periodic activity and ethics management report - update
2. Periodic risk and ethic management report - update
3. Review report on stakeholders’ roles, needs and preferences
4. Web page included in the WARIFA website containing a prototype of map display of the community risk profiles for the pilot communities studied in Romania, Spain and Norway
5. Final version of blueprint of the AI preventive system including input and output variables, end-user interface design and usability-related requirements
6. Demonstration of the data acquisition functionalities as part of the WARIFA app
7. Report on the specifications of the WARIFA app interface
8. Description of the designed graphical user interfaces and data acquisition functionalities
9. Pilot prototype on heterogenous data for monitor risk factors and to provide preventive behavior over time
10. Method for generating the optimum model to be transmitted to WP6 based on information from WP4
11. Construction of probabilistic network
12. Establishing the inference method
13. Co-creation report
14. Stakeholders analysis
15. Dissemination activities report
16. Business & Commercialisation Plan
17. Plan for the dissemination and exploitation of results - update
The following milestones were reached by December 2023:
Front end (20 Dec 2022)
WARIFA prototype (30 Dec 2023)
The WARIFA project aims to facilitate personalised early risk prediction, prevention and intervention based on AI and Big Data technologies. We want to explore how AI-based mobile applications may be used as a tool for individual lifestyle changes. This includes the use of mobile applications to analyse and estimate individual risk, correlate it with the community risk profile, provide evidence-based and personalized advice together with prompts for preventive lifestyle changes. The aim is to empower citizens to self-monitor the implementation of risk-reducing lifestyle changes.
Health apps are already being used in the prevention and management of CCs. However, the issue of long-term commitment continues to be a major challenge. By improving the understanding of what simple changes in the users` behaviour can do for their health, the motivation to make lifestyle-related changes can improve substantially. The willingness to engage in their own health, may be further increased by providing users with one single app that can manage multiple CCs. In addition to better self-management for citizens and patients, the Warifa app may also help healthcare personnel. Although the Warifa app is primarily designed for citizens and patients, information on the advice given by the app, may also inform decisions to be taken by the user`s doctor. As environmental conditions, such as air and water quality, is recorded by the app and directly can influence disease outcomes, health personnel may find the information from the Warifa app useful.
WARIFA developed a prototype of an AI-based system that aims to help prevent chronic conditions for all citizens. To achieve this objective, it was necessary to combine ubiquitous data and personal user-generated data, and interdisciplinary efforts from clinical, technical, and sociological backgrounds.
By combining ubiquitous data from the user`s environment with user-generated data, AI algorithms can process the most relevant data in the appropriate context and then provide the tools for personalized advice resulting in more specific preventive interventions.
The main results from the work conducted are available in the following scientific papers:
Who are the “Hard-to-Reach” groups in chronic-health and health technology research? A scoping review. In the Proceedings of the 18th Scandinavian Conference on Health Informatics (SHI 2022), https://ecp.ep.liu.se/index.php/shi/article/view/460
Evaluation of Synthetic Categorical Data Generation Techniques for Predicting Cardiovascular Diseases and Post-Hoc Interpretability of the Risk Factors, Applied Science, https://www.mdpi.com/2076-3417/13/7/4119
WARIFA Consortium, Quality, Usability, and Effectiveness of mHealth Apps and the Role of Artificial Intelligence: Current Scenario and Challenges, Journal of Medical Internet Research, https://www.jmir.org/2023/1/e44030
Combining Synthetic Patient Data Generation with Machine Learning Methods for Diabetes Prediction,
Machine Learning to Determine Physical Activity using Glucose Level Monitoring in People with type 1 Diabetes Mellitus,
Data-driven cardiovascular risk prediction and prognosis factor identification in diabetic patients, https://ieeexplore.ieee.org/document/9926871
The developed technical prototype will be tested in a pilot trial. The aim of the testing is to get a proof of concept that a single app can provide lifestyle recommendations relevant for multiple CCs while taking into account the context of the user. By providing alternative options, the user can decide which option fits best in a specific situation and does not feel to be ruled by the AI system.
In the short term the Warifa app is expected to influence individual risk factors, e.g. reducing the number of sunburns or increase physical activity. In the long term, the use of preventive apps may improve the outcomes of CCs such as reducing the number of skin cancer cases or limiting the complications of diabetes.
Health apps are already being used in the prevention and management of CCs. However, the issue of long-term commitment continues to be a major challenge. By improving the understanding of what simple changes in the users` behaviour can do for their health, the motivation to make lifestyle-related changes can improve substantially. The willingness to engage in their own health, may be further increased by providing users with one single app that can manage multiple CCs. In addition to better self-management for citizens and patients, the Warifa app may also help healthcare personnel. Although the Warifa app is primarily designed for citizens and patients, information on the advice given by the app, may also inform decisions to be taken by the user`s doctor. As environmental conditions, such as air and water quality, is recorded by the app and directly can influence disease outcomes, health personnel may find the information from the Warifa app useful.
WARIFA developed a prototype of an AI-based system that aims to help prevent chronic conditions for all citizens. To achieve this objective, it was necessary to combine ubiquitous data and personal user-generated data, and interdisciplinary efforts from clinical, technical, and sociological backgrounds.
By combining ubiquitous data from the user`s environment with user-generated data, AI algorithms can process the most relevant data in the appropriate context and then provide the tools for personalized advice resulting in more specific preventive interventions.
The main results from the work conducted are available in the following scientific papers:
Who are the “Hard-to-Reach” groups in chronic-health and health technology research? A scoping review. In the Proceedings of the 18th Scandinavian Conference on Health Informatics (SHI 2022), https://ecp.ep.liu.se/index.php/shi/article/view/460
Evaluation of Synthetic Categorical Data Generation Techniques for Predicting Cardiovascular Diseases and Post-Hoc Interpretability of the Risk Factors, Applied Science, https://www.mdpi.com/2076-3417/13/7/4119
WARIFA Consortium, Quality, Usability, and Effectiveness of mHealth Apps and the Role of Artificial Intelligence: Current Scenario and Challenges, Journal of Medical Internet Research, https://www.jmir.org/2023/1/e44030
Combining Synthetic Patient Data Generation with Machine Learning Methods for Diabetes Prediction,
Machine Learning to Determine Physical Activity using Glucose Level Monitoring in People with type 1 Diabetes Mellitus,
Data-driven cardiovascular risk prediction and prognosis factor identification in diabetic patients, https://ieeexplore.ieee.org/document/9926871
The developed technical prototype will be tested in a pilot trial. The aim of the testing is to get a proof of concept that a single app can provide lifestyle recommendations relevant for multiple CCs while taking into account the context of the user. By providing alternative options, the user can decide which option fits best in a specific situation and does not feel to be ruled by the AI system.
In the short term the Warifa app is expected to influence individual risk factors, e.g. reducing the number of sunburns or increase physical activity. In the long term, the use of preventive apps may improve the outcomes of CCs such as reducing the number of skin cancer cases or limiting the complications of diabetes.