Vendor-Agnostic Multisite Automated Dual-Energy X-Ray Absorptiometry Reporting Using Artificial Intelligence-Based Optical Character Recognition: Impact on Workflow Efficiency and Accuracy.
Authors
Affiliations (7)
Affiliations (7)
- Associate Professor of Radiology and Clinical Director of Imaging Informatics, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania. Electronic address: [email protected].
- Assistant Professor of Radiology and Vice Chair for Innovation, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania.
- Professor of Radiology, Vice Chair for Performance Improvement, and Site Chair, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania; Member, ACR.
- Professor of Radiology, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania.
- Associate Professor of Radiology, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania.
- Lead Diagnostic Radiology Advanced Practice Clinician, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania.
- Professor of Radiology and Vice Chair of Imaging Informatics, Department of Radiology, Jefferson Health-Thomas Jefferson University Hospital, Philadelphia, Pennsylvania; Member of the Board of Chancellors of the ACR.
Abstract
To evaluate the operational impact and accuracy of a vendor-agnostic, artificial intelligence (AI)-based optical character recognition (OCR) system for drafting dual-energy x-ray absorptiometry (DXA) reports across academic and community practice settings, we implemented a DXA reporting pipeline across four outpatient imaging sites within a single health system (two academic, two community). The system used AI OCR to extract measurements from DXA DICOM images and rule-based logic to generate complete draft reports within the radiology reporting system. Operational impact was assessed using a pre/post design, measuring report creation time (RCT; report start to first signature) and report turnaround time (TAT; study completion to final signature). Report accuracy was assessed by comparing AI drafts and original reports against source images (n = 400). Median RCT decreased from 3.48 to 0.87 min and median TAT from 2.40 to 0.96 hours at the academic sites. At the community sites, median RCT decreased from 1.42 to 0.63 min and median TAT from 133.82 to 42.10 hours. Mean differences for all four comparisons were significant by Welch's t test (all P < .0001). AI drafts had comparable to slightly higher numerical accuracy than original reports (academic: 99.9% versus 99.4%, P = .022; community: 100% versus 99.6%, P = .031), increased completeness at community sites (100% versus 45%, P < .001), and preserved diagnostic accuracy (≥99.5% across cohorts). Implementation of a vendor-agnostic, AI OCR DXA reporting system was associated with substantial reductions in RCT and report TAT, including an approximately 4-day median TAT reduction at community sites, while maintaining numerical and diagnostic accuracy and improving report completeness.