Lack of adherence to treatment is a widespread issue worldwide, which leads to higher healthcare utilisation rates and even premature death. While the level of adherence may differ based on the specific condition and treatment, studies estimate that approximately 50% of medications are not taken according to the prescribed instructions. In addition, adherence rates tend to decrease even further when the treatment requires a behavioural change. Literature reviews about factors that affect people's adherence show that it is challenging to predict whom can be considered to have adherent and non-adherent behaviours. In addition, the studies highlight that it is challenging to support a person to be adherent. Based on this knowledge the BEAMER project was established (Behavioural and Adherence Model for improving quality, health outcomes and cost-Effectiveness of healthcaRe). The overall goal of the project is to improve the quality of life of individuals, enhance healthcare accessibility and sustainability, thereby transforming the way healthcare stakeholders engage with patients to understand their condition and adherence levels throughout their healthcare journey. To address the overall goal, the BEAMER project has developed a disease agnostic model named "B-COMPASS: BEAMER-COmputational Model for Patient Adherence and Support Solutions". The aim of the B-COMPASS is to identify patients' needs and preferences which enables the creation of patient-specific supports, with the intention of improving their adherence to treatment within the heterogeneity of the different disease-areas and healthcare contexts. Based on the validated BEAMER questionnaire, the B-COMPASS predicts relative adherence and offers an elicitation process of patient needs and preferences to enable targeted supports to improve patient adherence. This results in an allocation of patients to different groups based on their needs and preferences. Overall, the B-COMPASS provides patient insights that will enable more effective design of patient support, most likely resulting in better patient experience, improved adherence and lower healthcare and societal costs. So far, several activities from a technical and user perspective have already been conducted in the project to refine the B-COMPASS. This has been done by applying an iterative mixed method approach were both stakeholders (regulator, pharma, academic/research and small and medium-sized enterprises) and end users (patients, health providers and health systems) have been involved. Despite the finetuning of the B-COMPASS, the effectiveness of the B-COMPASS hinges on empirical investigations into the structural elements that impact patient behaviour and the identification of predictive factors that can assist healthcare providers' (HCP) and Research Leads in designing more effective treatment plans (the term HCPs/Research Lead include both the individuals and the institutions where care is delivered). Therefore, validation studies will be conducted to assess the B-COMPASS's performance in six therapeutic areas (cardiovascular, endocrinology, immunology, neurology, oncology and rare diseases) with patients recruited in at least Italy (FISM), Portugal (APDP and MEDIDA) Norway (AHUS), Spain (FHUNJ and FIIBAP), The Netherlands (WDO), and Germany (UDUS). The collected data will be used to evaluate the B-COMPASS's capacity to attend to a variety of needs and challenges for adherence.
See this in plain English?
AI-rewrites the medical criteria so a patient or caregiver can understand them. Always confirm with the trial site.
Accuracy of the B-COMPASS to predict adherence
Timeframe: At first data collection
Validity of B-COMPASS groupings
Timeframe: At second data collection which is 2 weeks - 6 months after first data collection (first and second data collection). It varies between pilot sites and disease area.
Accuracy of identification of patients' support needs
Timeframe: At second data collection which is 2 weeks - 6 months after first data collection (first and second data collection). It varies between pilot sites and disease area.
Reliability of B-COMPASS prediction over time
Timeframe: At first data collection and then aging at second data collection which is 2 weeks - 6 months after first data collection (first and second data collection). It varies between pilot sites and disease area.