Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs

Abstract Plain pelvic radiographs (PXR) remain crucial for initial trauma assessment, yet interpretation challenges persist. While artificial intelligence (AI) shows promise, its practical impact across specialties remains unexplored. We conducted a retrospective image-based, multi-reader multi-case...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu-San Tee, Jen-Fu Huang, Yu-Ting Huang, Chi-Po Hsu, Huan-Wu Chen, Chi-Hsun Hsieh, Chih-Yuan Fu, Chi-Tung Cheng, Chien-Hung Liao
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01923-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234432454557696
author Yu-San Tee
Jen-Fu Huang
Yu-Ting Huang
Chi-Po Hsu
Huan-Wu Chen
Chi-Hsun Hsieh
Chih-Yuan Fu
Chi-Tung Cheng
Chien-Hung Liao
author_facet Yu-San Tee
Jen-Fu Huang
Yu-Ting Huang
Chi-Po Hsu
Huan-Wu Chen
Chi-Hsun Hsieh
Chih-Yuan Fu
Chi-Tung Cheng
Chien-Hung Liao
author_sort Yu-San Tee
collection DOAJ
description Abstract Plain pelvic radiographs (PXR) remain crucial for initial trauma assessment, yet interpretation challenges persist. While artificial intelligence (AI) shows promise, its practical impact across specialties remains unexplored. We conducted a retrospective image-based, multi-reader multi-case (MRMC) study using a standardized, prospectively planned evaluation protocol. A total of 26 physicians (8 radiologists, 10 emergency physicians, 8 trauma surgeons) interpreted 150 PXRs in three sequential sessions: without AI, with AI-alert, and with AI-visual guidance. AI assistance improved overall diagnostic accuracy from 0.870 to 0.940 (p < 0.001) and reduced interpretation time from 22.70 to 9.58 s (p < 0.001). Non-radiologists showed substantial improvements, with emergency physicians demonstrating increases in specificity (26.2%, p = 0.006) and positive predictive value (41.5%, p = 0.006). Trauma surgeons with AI-visual guidance achieved comparable accuracy to unaided radiologists (0.940 vs. 0.920, p = 0.556). Tailored AI assistance effectively bridges the performance gap between radiologists and non-radiologists while reducing reading time. These findings suggest AI integration could enhance clinical workflow efficiency across specialties in trauma care settings.
format Article
id doaj-art-f4ad4f4b4a0e49f5a098cc21b04f6fb8
institution Kabale University
issn 2398-6352
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-f4ad4f4b4a0e49f5a098cc21b04f6fb82025-08-20T04:03:11ZengNature Portfolionpj Digital Medicine2398-63522025-08-018111010.1038/s41746-025-01923-5Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographsYu-San Tee0Jen-Fu Huang1Yu-Ting Huang2Chi-Po Hsu3Huan-Wu Chen4Chi-Hsun Hsieh5Chih-Yuan Fu6Chi-Tung Cheng7Chien-Hung Liao8Department of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Diagnostic Radiology, Chang Gung Memorial Hospital at Keelung, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDivision of Emergency and Critical Care Radiology, Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityDepartment of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung UniversityAbstract Plain pelvic radiographs (PXR) remain crucial for initial trauma assessment, yet interpretation challenges persist. While artificial intelligence (AI) shows promise, its practical impact across specialties remains unexplored. We conducted a retrospective image-based, multi-reader multi-case (MRMC) study using a standardized, prospectively planned evaluation protocol. A total of 26 physicians (8 radiologists, 10 emergency physicians, 8 trauma surgeons) interpreted 150 PXRs in three sequential sessions: without AI, with AI-alert, and with AI-visual guidance. AI assistance improved overall diagnostic accuracy from 0.870 to 0.940 (p < 0.001) and reduced interpretation time from 22.70 to 9.58 s (p < 0.001). Non-radiologists showed substantial improvements, with emergency physicians demonstrating increases in specificity (26.2%, p = 0.006) and positive predictive value (41.5%, p = 0.006). Trauma surgeons with AI-visual guidance achieved comparable accuracy to unaided radiologists (0.940 vs. 0.920, p = 0.556). Tailored AI assistance effectively bridges the performance gap between radiologists and non-radiologists while reducing reading time. These findings suggest AI integration could enhance clinical workflow efficiency across specialties in trauma care settings.https://doi.org/10.1038/s41746-025-01923-5
spellingShingle Yu-San Tee
Jen-Fu Huang
Yu-Ting Huang
Chi-Po Hsu
Huan-Wu Chen
Chi-Hsun Hsieh
Chih-Yuan Fu
Chi-Tung Cheng
Chien-Hung Liao
Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
npj Digital Medicine
title Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
title_full Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
title_fullStr Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
title_full_unstemmed Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
title_short Comparative analysis of AI support levels in clinical interpretation of traumatic pelvic radiographs
title_sort comparative analysis of ai support levels in clinical interpretation of traumatic pelvic radiographs
url https://doi.org/10.1038/s41746-025-01923-5
work_keys_str_mv AT yusantee comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT jenfuhuang comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT yutinghuang comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT chipohsu comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT huanwuchen comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT chihsunhsieh comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT chihyuanfu comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT chitungcheng comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs
AT chienhungliao comparativeanalysisofaisupportlevelsinclinicalinterpretationoftraumaticpelvicradiographs