A Pragmatic Randomized Trial of an EHR-Integrated Generative AI Chart Summarization Tool for Ambulatory Clinicians
- 1UCLA Health Information Technology, UCLA Health, University of California, Los Angeles, Los Angeles, CA, USA; Department of Pediatrics, Division of Immunology,
Abstract
BACKGROUNDGenerative AI (genAI) chart summarization tools embedded in electronic health records (EHRs) are being rapidly deployed across U.S. health systems. Although these tools represent a promising solution to alleviate cognitive burdens, their effects have not been examined in randomized-clinical trials (RCTs).
METHODSIn this pragmatic RCT at a single academic health system, 284 outpatient clinicians across forty-two specialties were assigned 1:1 to Epics outpatient chart summarization tool or a usual-care control arm over 90 days, from February 23 to May 23, 2026. The primary outcome was physician task load (PTL) adapted for pre-charting. Prespecified exploratory outcomes included additional validated psychometrics as well as usability, safety, and time-based measures. Descriptive statistics included interaction and usage of the tool.
RESULTSOf 74,474 AI chart summaries generated, 14.2% were interacted with by a clinician; the proportion of generated summaries interacted with declined from 21.5% in month 1 to 10.5% in month 3, and the proportion of clinicians using the tool at least once per month declined from 88.7% to 66.2%. The adjusted between-arm difference in PTL at follow-up favored the intervention arm (scale 0-400; -27.4; 95% CI, -49.4 to -5.3; P=0.02). Among the Professional Fulfillment Index (PFI; scale 0-4, lower=better) psychometrics, overall burnout (-0.20; 95% CI, - 0.38 to -0.01) and work exhaustion (-0.24; 95% CI, -0.47 to -0.02) were lower in the intervention arm, with little difference in overall professional fulfillment (+0.04; 95% CI, -0.16 to 0.25). Charting time per encounter showed no significant between-arm difference during steady state (-1.2 seconds; 95% CI, -19.0 to 16.6). The net promoter score was -22, indicating that on average, clinicians did not recommend the tool. Among free-text respondents, 57.1% reported at least one concern, most commonly tool limitations or inaccurate information. No adverse patient safety events or near-misses were reported.
CONCLUSIONAn EHR-integrated AI chart summarization tool modestly reduced physician task load and was associated with lower burnout, without time savings and against declining engagement. Sustained usage and oversight of reported inaccuracies remain open challenges.
Trial RegistrationClinicalTrials.gov Identifier: NCT07438743
Related
- Multidimensional Assurance of an Electronic Health Record Embedded Generative Artificial Intelligence Summarization Tool
- Generative AI and Clinicians Show Comparable Prognostic Reasoning From Clinical Narratives in Biologic‐Treated CRSwNP
- Four weeks of isometric handgrip training results in lower awake ambulatory blood pressure compared with control: a randomized clinical trial
- Self-Reflection Resilience-Recovery Activity Promotion Training for Emergency Medical Service Clinicians: A Randomized Controlled Pilot Trial of a Novel Digital Intervention
- Community Pharmacy Involvement in Cardiovascular Patient Follow-Up: A Conceptual Framework for Integrated Ambulatory Pharmaceutical Care.
BibTeX
@misc{chin2026pragmatic,
title = {{A Pragmatic Randomized Trial of an EHR-Integrated Generative AI Chart Summarization Tool for Ambulatory Clinicians}},
author = {A. T. Chin and N. Zhu and S. Vangala and H. Woo and L. E. Wisk and T. Kingsley and J. N. Mafi and P. J. Lukac},
howpublished = {medRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.26.26361496},
url = {https://www.medrxiv.org/content/10.64898/2026.08.26.26361496v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - A Pragmatic Randomized Trial of an EHR-Integrated Generative AI Chart Summarization Tool for Ambulatory Clinicians
AU - A. T. Chin
AU - N. Zhu
AU - S. Vangala
AU - H. Woo
AU - L. E. Wisk
AU - T. Kingsley
AU - J. N. Mafi
AU - P. J. Lukac
PY - 2026
DA - 2026/08/26
PB - medRxiv
DO - 10.64898/2026.08.26.26361496
UR - https://www.medrxiv.org/content/10.64898/2026.08.26.26361496v1
AB - BACKGROUNDGenerative AI (genAI) chart summarization tools embedded in electronic health records (EHRs) are being rapidly deployed across U.S. health systems. Although these tools represent a promising solution to alleviate cognitive burdens, their effects have not been examined in randomized-clinical trials (RCTs). METHODSIn this pragmatic RCT at a single academic health system, 284 outpatient clinicians across forty-two specialties were assigned 1:1 to Epics outpatient chart summarization tool or a usual-care control arm over 90 days, from February 23 to May 23, 2026. The primary outcome was physician task load (PTL) adapted for pre-charting. Prespecified exploratory outcomes included additional validated psychometrics as well as usability, safety, and time-based measures. Descriptive statistics included interaction and usage of the tool. RESULTSOf 74,474 AI chart summaries generated, 14.2% were interacted with by a clinician; the proportion of generated summaries interacted with declined from 21.5% in month 1 to 10.5% in month 3, and the proportion of clinicians using the tool at least once per month declined from 88.7% to 66.2%. The adjusted between-arm difference in PTL at follow-up favored the intervention arm (scale 0-400; -27.4; 95% CI, -49.4 to -5.3; P=0.02). Among the Professional Fulfillment Index (PFI; scale 0-4, lower=better) psychometrics, overall burnout (-0.20; 95% CI, - 0.38 to -0.01) and work exhaustion (-0.24; 95% CI, -0.47 to -0.02) were lower in the intervention arm, with little difference in overall professional fulfillment (+0.04; 95% CI, -0.16 to 0.25). Charting time per encounter showed no significant between-arm difference during steady state (-1.2 seconds; 95% CI, -19.0 to 16.6). The net promoter score was -22, indicating that on average, clinicians did not recommend the tool. Among free-text respondents, 57.1% reported at least one concern, most commonly tool limitations or inaccurate information. No adverse patient safety events or near-misses were reported. CONCLUSIONAn EHR-integrated AI chart summarization tool modestly reduced physician task load and was associated with lower burnout, without time savings and against declining engagement. Sustained usage and oversight of reported inaccuracies remain open challenges. Trial RegistrationClinicalTrials.gov Identifier: NCT07438743
ER -