Effect of an Electronic Health Record-Integrated Clinical Dashboard for Radiologists on STAT Priority Chest Radiograph Reporting and Downstream Care: A Stepped-Wedge Cluster Randomized Trial
- 1Kaiser Permanente Northern California Division of Research, Pleasanton, CA
Abstract
BackgroundChest radiographs (CXRs) are the most common imaging exam performed, but CXR reports can be nonspecific due to incomplete history, relying on vague terms like "opacities" to convey diagnostic uncertainty. We prospectively evaluated whether introducing a clinical dashboard with relevant patient information affects CXR report specificity and efficiency, report concordance with discharge diagnoses, and follow-up chest CT utilization.
MethodsIn this stepped-wedge cluster randomized trial (NCT06785246), a clinical dashboard for radiologists was rolled out with user education sessions across 15 service areas of an integrated health system from June 2024 to June 2025. Emergency department (ED) and inpatient CXRs were included. A large language model (GPT-4o) was validated using a Delphi panel of three experts to classify report specificity and CXR report diagnosis. A subsequent model release (GPT-5.4) graded each CXR report impression as negative, specific abnormal, or nonspecific abnormal. It also judged whether an abnormal impression matched an ED discharge diagnosis. The primary outcome was the proportion of specific reports (negative or specific abnormal). Secondary outcomes were report-discharge diagnosis concordance, follow-up chest CT, antibiotic and diuretic orders, and CXR reporting time. Mixed-effects models adjusted for time, patient age, and radiograph view, with random effects for radiologists, facilities, and service area.
ResultsThe trial included 404,860 ED and inpatient encounter STAT priority CXRs read by 387 radiologists (256,303 control; 148,557 intervention). The adjusted proportion of specific reports was 82.2% in control periods and 82.1% in intervention periods (difference, -0.10 percentage points; 95% CI, -0.53 to 0.34; P=.66). Among abnormal reports, concordance with a discharge diagnosis rose from 40.9% to 42.2% (difference, 1.24 points; 95% CI, 0.20 to 2.28; P=.02). Follow-up chest CT fell from 11.4% to 10.9% (difference, -0.55 points; 95% CI, -0.92 to -0.17; P=.004). Antibiotic orders (24.0% vs 23.9%) and diuretic orders (14.7% vs 14.8%) within 7 days did not change, nor did reporting time (difference, -0.8 seconds; 95% CI, -2.7 to 1.0).
ConclusionsGiving radiologists EHR context through a dashboard did not change the specificity of STAT priority CXR reports or prescribing patterns. It was associated with small improvements in diagnostic concordance and follow-up CT use, without slowing reporting. Validated large language models make it feasible to measure report quality across a health system.
Trial registrationClinicalTrials.gov NCT06785246.
Related
- An Integrated Electronic Patient-Reported Outcome-Guided COPD Management Strategy Incorporating Adjunctive Acupuncture: Study Protocol for a Randomized Controlled Trial.
- Quality evaluation of commercial ‘Boju’ (Chrysanthemum morifolium Ramat.) using integrated electronic nose, electronic tongue, and GC-IMS analysis
- Disagreement between AI and Radiologists: Quantifying Direction and Fragility
- Pheno+: An Electronic Health Record-Integrated, Clinician-in-the-Loop Application for Efficient Phenotyping in Clinical Genomics
- Usability and workflow implications of an electronic health record-integrated tool for automated phenotyping: Formative evaluation of Pheno+
BibTeX
@misc{balkman2026effect,
title = {{Effect of an Electronic Health Record-Integrated Clinical Dashboard for Radiologists on STAT Priority Chest Radiograph Reporting and Downstream Care: A Stepped-Wedge Cluster Randomized Trial}},
author = {J. D. Balkman and S. R. Chimmula and A. M. Lam and J. R. Nugent and T. Gadgil and A. L. Avins and D. R. Sax and V. A. Arasu},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.23.26363355},
url = {https://www.medrxiv.org/content/10.64898/2026.09.23.26363355v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Effect of an Electronic Health Record-Integrated Clinical Dashboard for Radiologists on STAT Priority Chest Radiograph Reporting and Downstream Care: A Stepped-Wedge Cluster Randomized Trial
AU - J. D. Balkman
AU - S. R. Chimmula
AU - A. M. Lam
AU - J. R. Nugent
AU - T. Gadgil
AU - A. L. Avins
AU - D. R. Sax
AU - V. A. Arasu
PY - 2026
DA - 2026/09/23
PB - medRxiv
DO - 10.64898/2026.09.23.26363355
UR - https://www.medrxiv.org/content/10.64898/2026.09.23.26363355v1
AB - BackgroundChest radiographs (CXRs) are the most common imaging exam performed, but CXR reports can be nonspecific due to incomplete history, relying on vague terms like "opacities" to convey diagnostic uncertainty. We prospectively evaluated whether introducing a clinical dashboard with relevant patient information affects CXR report specificity and efficiency, report concordance with discharge diagnoses, and follow-up chest CT utilization. MethodsIn this stepped-wedge cluster randomized trial (NCT06785246), a clinical dashboard for radiologists was rolled out with user education sessions across 15 service areas of an integrated health system from June 2024 to June 2025. Emergency department (ED) and inpatient CXRs were included. A large language model (GPT-4o) was validated using a Delphi panel of three experts to classify report specificity and CXR report diagnosis. A subsequent model release (GPT-5.4) graded each CXR report impression as negative, specific abnormal, or nonspecific abnormal. It also judged whether an abnormal impression matched an ED discharge diagnosis. The primary outcome was the proportion of specific reports (negative or specific abnormal). Secondary outcomes were report-discharge diagnosis concordance, follow-up chest CT, antibiotic and diuretic orders, and CXR reporting time. Mixed-effects models adjusted for time, patient age, and radiograph view, with random effects for radiologists, facilities, and service area. ResultsThe trial included 404,860 ED and inpatient encounter STAT priority CXRs read by 387 radiologists (256,303 control; 148,557 intervention). The adjusted proportion of specific reports was 82.2% in control periods and 82.1% in intervention periods (difference, -0.10 percentage points; 95% CI, -0.53 to 0.34; P=.66). Among abnormal reports, concordance with a discharge diagnosis rose from 40.9% to 42.2% (difference, 1.24 points; 95% CI, 0.20 to 2.28; P=.02). Follow-up chest CT fell from 11.4% to 10.9% (difference, -0.55 points; 95% CI, -0.92 to -0.17; P=.004). Antibiotic orders (24.0% vs 23.9%) and diuretic orders (14.7% vs 14.8%) within 7 days did not change, nor did reporting time (difference, -0.8 seconds; 95% CI, -2.7 to 1.0). ConclusionsGiving radiologists EHR context through a dashboard did not change the specificity of STAT priority CXR reports or prescribing patterns. It was associated with small improvements in diagnostic concordance and follow-up CT use, without slowing reporting. Validated large language models make it feasible to measure report quality across a health system. Trial registrationClinicalTrials.gov NCT06785246.
ER -