Periodic Reporting for period 3 - iHELP (Personalised Health Monitoring and Decision Support Based on Artificial Intelligence and Holistic Health Records)
Periodo di rendicontazione: 2024-01-01 al 2024-06-30
iHELP delivered a novel personalised-healthcare framework that fosters the collection, integration and management of health-related data from various sources (medical records, lifestyle, behaviours, social media interactions) in a standardised structure called Holistic Health Records (HHRs). The data in the HHRs were analysed using advance AI techniques to draw adaptive learning models that are used to provide decision support in the form of early risk predictions as well as personalised prevention & intervention measures (alerts, behavioural nudges, consultations medications, therapies, screening etc) that are delivered through user-centric mobile and wearable applications. The standardised integration of data and recalibration of learning models enabled the development of advanced AI techniques that fostered the timely decision support to all stakeholders in the value chain, including: medical experts and also policy makers using relevant interfaces.
The specific focus of iHELP was on the development of solutions targeting to early identification and mitigation of the risks associated with Pancreatic Cancer based on the application of advance AI-based learning and decision support techniques on the historic (primary) data of Cancer patients gathered from established data banks and cohorts. This analysis enabled the (i) specification of key risks associated with Pancreatic Cancer, (ii) development of predictive models for identified risks, and (iii) development of adaptive models for targeted prevention and intervention measures. Based on the identification of key risks and availability of respective models, the project selected high-risk individuals (from hospital records and other sources) that took part in the pilot activities or digital trials. The digital trials carried out through user-centric mobile and wearable applications that applied proven usability principles to offer more engaging experience for health monitoring, risk assessment and personalised decision support. In addition to providing the personalised monitoring, alerting and decision support mechanisms, the iHELP (mobile and wearable) technology solutions facilitated the validation of its solutions, the assessment of their impact and raising health related awareness at individual level. The (secondary) data gathered through the mobile and wearable applications (concerning lifestyle, behavioural, social interactions and response to targeted prevention and intervention measures) was integrated with primary data in the standardised HHR format – within a big data platform. Recalibrated AI-based learning techniques were developed to provide near real-time risk assessment based on the integration and availability of primary and secondary data in the standardised HHR format. The availability of HHRs provided opportunities to validate iHELP outcomes (e.g. improvements in quality of life, reduced risks etc) through advance analytic functions. iHELP solutions also helped in policy making by providing decision support and social analysis on the design of new screening programs and new guidelines for bringing improvements in clinical, lifestyle and behavioural aspects of the fight against Cancer.
The specific focus of iHELP was on the development of solutions targeting to early identification and mitigation of the risks associated with Pancreatic Cancer based on the application of advance AI-based learning and decision support techniques on the historic (primary) data of Cancer patients gathered from established data banks and cohorts. This analysis enabled the (i) specification of key risks associated with Pancreatic Cancer, (ii) development of predictive models for identified risks, and (iii) development of adaptive models for targeted prevention and intervention measures. Based on the identification of key risks and availability of respective models, the project selected high-risk individuals (from hospital records and other sources) that took part in the pilot activities or digital trials. The digital trials carried out through user-centric mobile and wearable applications that applied proven usability principles to offer more engaging experience for health monitoring, risk assessment and personalised decision support. In addition to providing the personalised monitoring, alerting and decision support mechanisms, the iHELP (mobile and wearable) technology solutions facilitated the validation of its solutions, the assessment of their impact and raising health related awareness at individual level. The (secondary) data gathered through the mobile and wearable applications (concerning lifestyle, behavioural, social interactions and response to targeted prevention and intervention measures) was integrated with primary data in the standardised HHR format – within a big data platform. Recalibrated AI-based learning techniques were developed to provide near real-time risk assessment based on the integration and availability of primary and secondary data in the standardised HHR format. The availability of HHRs provided opportunities to validate iHELP outcomes (e.g. improvements in quality of life, reduced risks etc) through advance analytic functions. iHELP solutions also helped in policy making by providing decision support and social analysis on the design of new screening programs and new guidelines for bringing improvements in clinical, lifestyle and behavioural aspects of the fight against Cancer.
- Continuous analysis of the user & technical requirements to drive the implementations and integrations of the final software prototypes
- Deployment of a central iHelp platform able to host all iHelp components and sub-components by using Helm charts and Kubernetes as deployment mechanism
- Replication of iHelp platform in three pilots premises for experimenting, stress testing and evaluating behaviours of iHelp components in different environments
- Implementation and execution of improved AI models in contrary to the ones developed in the 1st reporting period, including analysis on comorbidities and methylation, resulting on improved accuracy in the clustering of potential patients
- Final implementation of multilingual Decision Support System (DSS) and Monitoring & Alerting (M&A) user interfaces for the clinicians
- Final implementation of a multilingual approach in the personalized messaging, where patient are receiving tailored messages and virtual coaching in their native language
- Final implementation of remote monitoring and data evaluation mechanism based on specific Prevention and Risk Mitigation plans
- Final implementation of the Virtual Coach and of the iHelp patient companion application for near real-time engagement between the Healthcare Professionals (HCPs) and the patients, for the delivery of personalized recommendations and the establishment of respective dialogues and messages
- Final implementation of the Analytic Workbench evaluated by all pilot cases, as it is used to store, make discoverable and execute the various AI models
- Final implementation of the Explainable Dashboard Hub (EDH) for improved interpretability and explainability of the results from the AI models
- Organisation of 1 workshop and 1 Special Session in International Conferences
- Establishment of synergies with other EU funded projects
- Collaboration with Horizon Results Booster and the HS Booster project in the context of the project’s innovation and exploitation activities
- Deployment of a central iHelp platform able to host all iHelp components and sub-components by using Helm charts and Kubernetes as deployment mechanism
- Replication of iHelp platform in three pilots premises for experimenting, stress testing and evaluating behaviours of iHelp components in different environments
- Implementation and execution of improved AI models in contrary to the ones developed in the 1st reporting period, including analysis on comorbidities and methylation, resulting on improved accuracy in the clustering of potential patients
- Final implementation of multilingual Decision Support System (DSS) and Monitoring & Alerting (M&A) user interfaces for the clinicians
- Final implementation of a multilingual approach in the personalized messaging, where patient are receiving tailored messages and virtual coaching in their native language
- Final implementation of remote monitoring and data evaluation mechanism based on specific Prevention and Risk Mitigation plans
- Final implementation of the Virtual Coach and of the iHelp patient companion application for near real-time engagement between the Healthcare Professionals (HCPs) and the patients, for the delivery of personalized recommendations and the establishment of respective dialogues and messages
- Final implementation of the Analytic Workbench evaluated by all pilot cases, as it is used to store, make discoverable and execute the various AI models
- Final implementation of the Explainable Dashboard Hub (EDH) for improved interpretability and explainability of the results from the AI models
- Organisation of 1 workshop and 1 Special Session in International Conferences
- Establishment of synergies with other EU funded projects
- Collaboration with Horizon Results Booster and the HS Booster project in the context of the project’s innovation and exploitation activities
- Utilized and combined several genomic and epigenomic risk biomarkers to estimate combined risk scores as well as to provide an integrated system for monitoring biologically risk reduction
- Research implemented on the methylation status and different epigenomic factors showcasing improved accuracy on the utilisation of AI models
- Development of a predictive model for the risk of developing pancreatic cancer using biomedical data collected over a 9-month follow-up period on patients with pancreatic cancer and individuals with associated risk factors for this cancer
- Developed a powerful tool for remote patient monitoring that aims to save valuable time during patient consultation and long-term cancer treatment and prevention procedures
- Implemented advanced AI-based tools for assessing the impact and adherence of patients on the personalized recommendations received by their HCPs.
- Facilitated the wider adoption and market innovation of integrated health and care solutions of the project through a systematic Health Technology Assessment (HTA) that considered techno-economic and socio-economic factors.
- Fostered effective lifestyle and behavioral changes through the introduction of community-based prevention and intervention strategies.
- Achieved significant engagement and satisfaction among participants through its user-friendly and advanced solutions.
- Significantly increased participants knowledge of general health topics and cancer risk factors, contributing to informed decision-making and preventive actions.
- Established a continuous usability, technological and socioeconomical assessment and validation approach by also engaging the HCPs. Education and training of the HCPs was provided in the utilization of emerging technologies.
- Introduced an AI Assessment Grid (AIAG) which can be a valuable tool and guide towards the assessment of AI-based solutions that are offered in the modern healthcare domain.
- Research implemented on the methylation status and different epigenomic factors showcasing improved accuracy on the utilisation of AI models
- Development of a predictive model for the risk of developing pancreatic cancer using biomedical data collected over a 9-month follow-up period on patients with pancreatic cancer and individuals with associated risk factors for this cancer
- Developed a powerful tool for remote patient monitoring that aims to save valuable time during patient consultation and long-term cancer treatment and prevention procedures
- Implemented advanced AI-based tools for assessing the impact and adherence of patients on the personalized recommendations received by their HCPs.
- Facilitated the wider adoption and market innovation of integrated health and care solutions of the project through a systematic Health Technology Assessment (HTA) that considered techno-economic and socio-economic factors.
- Fostered effective lifestyle and behavioral changes through the introduction of community-based prevention and intervention strategies.
- Achieved significant engagement and satisfaction among participants through its user-friendly and advanced solutions.
- Significantly increased participants knowledge of general health topics and cancer risk factors, contributing to informed decision-making and preventive actions.
- Established a continuous usability, technological and socioeconomical assessment and validation approach by also engaging the HCPs. Education and training of the HCPs was provided in the utilization of emerging technologies.
- Introduced an AI Assessment Grid (AIAG) which can be a valuable tool and guide towards the assessment of AI-based solutions that are offered in the modern healthcare domain.