Development of an AI-assisted mobile application for improving polypharmacy management, medication adherence and patient education in outpatient settings

Objectives Polypharmacy, the use of five or more medications by an individual, has become an increasingly prevalent and concerning issue in healthcare affecting 65.1% (37.8 million) of US geriatric patients. The management of polypharmacy presents complex challenges that can lead to medication mismanagement and adverse health outcomes. This study aimed to create a prototype smartphone application, ‘Polly,’ to support polypharmacy management by combining traditional medication management tools with real-time verification through artificial intelligence (AI). The app’s goals include improving adherence, increasing patient comprehension and reducing adverse drug events. Design Polly was built using the Flutter framework for cross-platform compatibility, with a backend supported by FastAPI and hosted on Microsoft Azure. Firebase Authentication provided secure user access. Key features include AI-powered medication verification using a fine-tuned YOLOv11 machine vision model, which identifies medications from user-provided images to confirm dosage and schedule accuracy. Results The application incorporates a clear daily schedule view, comprehensive medication lists and detailed input and scheduling options tailored to geriatric users. The machine vision system enhances safety by verifying medication intake while notifications and historical tracking improve adherence. Polly’s error detection system flags discrepancies, prompting users to correct mistakes before taking their medications. Conclusions Polly demonstrates the feasibility of integrating machine vision with traditional medication management to improve safety and adherence in polypharmacy. This app addresses limitations of existing tools by providing real-time verification and proactive error correction, particularly benefiting geriatric populations managing complex regimens. Future directions include clinical validation and expansion to support healthcare provider integration.

Authors

Institutions

Publication Details

Journal
BMJ Innovations
Published
2026-05-21
DOI
https://doi.org/10.1136/bmjinnov-2025-001372
Primary Topic
Pharmaceutical Practices and Patient Outcomes
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Development of an AI-assisted mobile application for improving polypharmacy management, medication adherence and patient education in outpatient settings

Joseph Mariscal, Nathaniel Hagan, Nicholas Warriner, Jory Cooper Nagel et al.
BMJ Innovations
Pharmaceutical Practices and Patient Outcomes
article

Development of an AI-assisted mobile application for improving polypharmacy management, medication adherence and patient education in outpatient settings

Joseph Mariscal, Nathaniel Hagan, Nicholas Warriner, Jory Cooper Nagel, Pavitra Attanayake, Mark Trottier
article en

Abstract

Objectives Polypharmacy, the use of five or more medications by an individual, has become an increasingly prevalent and concerning issue in healthcare affecting 65.1% (37.8 million) of US geriatric patients. The management of polypharmacy presents complex challenges that can lead to medication mismanagement and adverse health outcomes. This study aimed to create a prototype smartphone application, ‘Polly,’ to support polypharmacy management by combining traditional medication management tools with real-time verification through artificial intelligence (AI). The app’s goals include improving adherence, increasing patient comprehension and reducing adverse drug events. Design Polly was built using the Flutter framework for cross-platform compatibility, with a backend supported by FastAPI and hosted on Microsoft Azure. Firebase Authentication provided secure user access. Key features include AI-powered medication verification using a fine-tuned YOLOv11 machine vision model, which identifies medications from user-provided images to confirm dosage and schedule accuracy. Results The application incorporates a clear daily schedule view, comprehensive medication lists and detailed input and scheduling options tailored to geriatric users. The machine vision system enhances safety by verifying medication intake while notifications and historical tracking improve adherence. Polly’s error detection system flags discrepancies, prompting users to correct mistakes before taking their medications. Conclusions Polly demonstrates the feasibility of integrating machine vision with traditional medication management to improve safety and adherence in polypharmacy. This app addresses limitations of existing tools by providing real-time verification and proactive error correction, particularly benefiting geriatric populations managing complex regimens. Future directions include clinical validation and expansion to support healthcare provider integration.

BMJ Innovations
Grand Rapids Community College (US), Western Michigan University (US), Lakeland Library Cooperative (US), Stryker (United States) (US), Michigan State University (US)
Blue Cross Blue Shield of Michigan Foundation
Openalex Percentile: Top 8%
Pharmaceutical Practices and Patient Outcomes
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.