JMIR Publications

ABSTRACT

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.