AUTHOR=Reis Zilma Silveira Nogueira , Pereira Gláucia Miranda Varella , Dias Cristiane dos Santos , Lage Eura Martins , de Oliveira Isaias José Ramos , Pagano Adriana Silvina 

TITLE=Artificial intelligence-based tools for patient support to enhance medication adherence: a focused review

JOURNAL=Frontiers in Digital Health

VOLUME=Volume 7 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2025.1523070

DOI=10.3389/fdgth.2025.1523070

ISSN=2673-253X

ABSTRACT=ObjectiveMedication adherence involves patients correctly taking medications as prescribed. This review evaluates whether artificial intelligence (AI) based tools contribute to adherence-related insights or avoid medication intake errors.MethodsWe assessed studies employing AI tools to directly benefit patient medication use, promoting adherence or avoiding self-administration error outcomes. The search strategy was conducted on six databases in August 2024. ROB2 and ROBINS1 assessed the risk of bias.ResultsThe review gathered seven eligible studies, including patients from three clinical trials and one prospective cohort. The overall risk of bias was moderate to high. Three reports drew on conceptual frameworks with simulated testing. The evidence identified was scarce considering measurable outcomes. However, based on randomized clinical trials, AI-based tools improved medication adherence ranging from 6.7% to 32.7% compared to any intervention controls and current practices, respectively. Digital intervention using video and voice interaction providing real-time monitoring pointed to AI's potential to alert to self-medication errors. Based on conceptual framework reports, we highlight the potential of cognitive behavioral approaches tailored to engage patients in their treatment.ConclusionEven though the present evidence is weak, smart systems using AI tools are promising in helping patients use prescribed medications. The review offers insights for future research.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/view/CRD42024571504, identifier: CRD42024571504.