Ai-enhanced clinical decision support reduces medication errors and adverse drug events in a multicenter…

Randomized trialInternational journal of medical informatics· Jul 2026

Ai-enhanced clinical decision support reduces medication errors and adverse drug events in a multicenter teaching hospital network: A prospective randomized controlled trial.

Nurbek Shakarbaev

Clinical Decision SupportRandomized trialQ1IF 6.2

AI-enhanced clinical decision support nearly halved hospital medication error rates

Ai-enhanced clinical decision support reduces medication errors and adverse drug events in a multicenter teaching hospital network: A prospective randomized controlled trial.

Nurbek Shakarbaev

International journal of medical informatics · Jul 2026 · Q1 in Health Informatics

Background

Medication errors remain a leading source of preventable harm in hospitalized patients, contributing to adverse drug events (adverse drug events), prolonged hospital stay, and avoidable healthcare costs.

Purpose

To evaluate the effect of an AI-enhanced, electronic health records-integrated clinical decision support systems on medication error rates and adverse drug events incidence in hospitalized adults, with additional assessment of alert performance, clinician adoption, and cost-effectiveness.

Methods

We conducted a prospective, parallel-arm, randomized controlled trial (randomized controlled trial) across four tertiary-care teaching hospitals in Tashkent, Uzbekistan (January 2022 - August 2023).

n = 1,000 patient

Results

medication error rates nearly halved with AI decision support

More results

Overall alert acceptance was 73.6%, with allergy/contraindication alerts achieving 95.5%.

Clinician adoption rose from 42.1% to 88.7% daily active users over 12 months.

Estimated return on investment was 489% over 12 months.

“

Conclusion · 1 of 3

AI-enhanced clinical decision support systems integration was associated with substantially improved medication safety and selected hospital outcomes in a multicenter low- and middle-income countries tertiary-care setting.

Conclusion · 2 of 3

The MedGuard-UZ AI project materials are publicly available at https://github.com/Shakarbayev/MedGuard-UZ.

Conclusion · 3 of 3

For peer-review reproducibility, the repository state corresponding to this revision has been archived under the tagged release v1.0.0-ijmedi-rct (tag commit: f796c3d).

Ai-enhanced clinical decision support reduces medication errors and adverse drug events in a multicenter teaching hospital network: A prospective randomized controlled trial.

Ai-enhanced clinical decision support reduces medication errors and adverse drug events in a multicenter teaching hospital network: A prospective randomized controlled trial.

Related papers