Background Medication adherence plays a critical role in controlling the evolution of chronic disease, as low medication adherence may lead to worse health outcomes, higher mortality, and morbidity. Assessment of their patients' medication adherence by clinicians is essential for avoiding inappropriate therapeutic intensification, associated health care expenditures, and the inappropriate inclusion of patients in time- and resource-consuming educational interventions. In both research and clinical practices the most extensively used measures of medication adherence are patient-reported outcome measures (PROMs), because of their ability to capture subjective dimensions of nonadherence. Machine learning (ML), a subfield of artificial intelligence, uses computer algorithms that automatically improve through experience. In this context, ML tools could efficiently model the complexity of and interactions between multiple patient behaviors that lead to medication adherence. Objective This study aimed to create and validate a PROM on medication adherence interpreted using an ML approach. Methods This cross-sectional, single-center, observational study was carried out a French teaching hospital between 2021 and 2022. Eligible patients must have had at least 1 long-term treatment, medication adherence evaluation other than a questionnaire, the ability to read or understand French, an age older than 18 years, and provided their nonopposition. Included adults responded to an initial version of the PROM composed of 11 items, each item being presented using a 4-point Likert scale. The initial set of items was obtained using a Delphi consensus process. Patients were classified as poorly, moderately, or highly adherent based on the results of a medication adherence assessment standard used in the daily practice of each outpatient unit. An ML-derived decision tree was built by combining the medication adherence status and PROM responses. Sensitivity, specificity, positive and negative predictive values (NPVs), and global accuracy of the final 5-item PROM were evaluated. Results We created an initial 11-item PROM with a 4-point Likert scale using the Delphi process. After item reduction, a decision tree derived from 218 patients including data obtained from the final 5-item PROM allowed patient classification into poorly, moderately, or highly adherent based on item responses. The psychometric properties were 78% (95% CI 40%-96%) sensitivity, 71% (95% CI 53%-85%) specificity, 41% (95% CI 19%-67%) positive predictive values, 93% (95% CI 74%-99%) NPV, and 70% (95% CI 55%-83%) accuracy. Conclusions We developed a medication adherence tool based on ML with an excellent NPV. This could allow prioritization processes to avoid referring highly adherent patients to time- and resource-consuming interventions. The decision tree can be easily implemented in computerized prescriber order-entry systems and digital tools in smartphones. External validation of this tool in a study including a larger number of patients with diseases associated with low medication adherence is required to confirm its use in analyzing and assessing the complexity of medication adherence.

BACKGROUND An easy-to-use method to evaluate medication adherence in the medication management of chronic diseases is essential to improving the proper use of drugs and optimal disease control. Artificial intelligence can provide tools to efficiently model the complexity of and interactions between multiple patient behaviours that lead to medication adherence. OBJECTIVE To create and validate a patient-reported outcome measure (PROM) on medication adherence interpreted using a machine-learning approach. METHODS Design: Observational cross-sectional single-centre study in a French teaching hospital between 2021 and 2022. Participants: Eligible patients must have had at least one long-term treatment, been able to read or understand French, been older than 18 years, provided their non-opposition, and have had medication adherence evaluation other than a questionnaire (therapeutic drug monitoring, drug urinary screening, medication possession ration, or physician feedback). Exposure: Included adults responded to a PROM initially composed of 11 items using a four-point Likert scale. Main outcomes and Measures: The initial set of items was obtained using a Delphi consensus process. Patients were classified as poorly, moderately, or highly adherent based on the results of a medication-adherence assessment standard used in the daily practice of each outpatient unit. A machine learning-derived decision tree was built by combining the medication-adherence status and PROM responses. Sensitivity, specificity, positive and negative predictive values (PPV and NPV), and global accuracy were evaluated. RESULTS We created an initial 11-item PROM with a four-point Likert scale using the Delphi process. After item reduction, a decision tree derived from 218 patients including data obtained from the final five-item PROM allowed patient classification into poorly, moderately, or highly adherent based on item responses. The psychometric proprieties were 78% (40%; 96%) sensitivity, 71% (53%; 85%) specificity, 41% (19%; 67%) PPV, 93% (74%; 99%) NPV and 70% (55%; 83%) accuracy. CONCLUSIONS We developed a medication-adherence tool based on machine-learning interpretation that shows good psychometric properties. The decision tree, which can be easily implemented in both computerized prescriber order-entry systems and digital tools, requires external validation with a larger number of patients to confirm its utility in analysing and assessing the complexity of medication adherence.