An Observational Study to Evaluate the Usability and Intent to Adopt an Artificial Intelligence–Powered Medication Reconciliation Tool
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.077 | 0.074 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".