Related Experiment Video
Updated: Mar 21, 2026
Digital Home-Monitoring of Patients after Kidney Transplantation: The MACCS Platform
Published on: April 12, 2021
An Observational Study to Evaluate the Usability and Intent to Adopt an Artificial Intelligence-Powered Medication
Ju Long1, Michael Juntao Yuan, Robina Poonawala
1McCoy College of Business Administration, Department of Computer Information Systems and Quantitative Methods, Texas State University, San Marcos, TX, United States. jl38@txstate.edu.
Background:
Medication reconciliation (the process of creating an accurate list of all medications a patient is taking) is a widely practiced procedure to reduce medication errors. It is mandated by the Joint Commission and reimbursed by Medicare. Yet, in practice, medication reconciliation is often not effective owing to knowledge gaps in the team. A promising approach to improve medication reconciliation is to incorporate artificial intelligence (AI) decision support tools into the process to engage patients and bridge the knowledge gap.
Objective:
The aim of this study was to improve the accuracy and efficiency of medication reconciliation by engaging the patient, the nurse, and the physician as a team via an iPad tool. With assistance from the AI agent, the patient will review his or her own medication list from the electronic medical record (EMR) and annotate changes, before reviewing together with the physician and making decisions on the shared iPad screen.
Methods:
In this study, we developed iPad-based software tools, with AI decision support, to engage patients to "self-service" medication reconciliation and then share the annotated reconciled list with the physician. To evaluate the software tool's user interface and workflow, a small number of patients (10) in a primary care clinic were recruited, and they were observed through the whole process during a pilot study. The patients are surveyed for the tool's usability afterward.
Results:
All patients were able to complete the medication reconciliation process correctly. Every patient found at least one error or other issues with their EMR medication lists. All of them reported that the tool was easy to use, and 8 of 10 patients reported that they will use the tool in the future. However, few patients interacted with the learning modules in the tool. The physician and nurses reported the tool to be easy-to-use, easy to integrate into existing workflow, and potentially time-saving.
Conclusions:
We have developed a promising tool for a new approach to medication reconciliation. It has the potential to create more accurate medication lists faster, while better informing the patients about their medications and reducing burden on clinicians.
