Artificial Intelligence Versus Human Interpretation in Diagnostic Radiology: A Systematic Review of Diagnostic Accuracy and Operational Efficiency.
- 1Medicine, Navarra University Foundation (UNINAVARRA), Neiva, COL.
- 2Medicine, Faculty of Health Sciences, Surcolombiana University, Neiva, COL.
- 3Research and Innovation Center (CIINA), Navarra University Foundation (UNINAVARRA), Neiva, COL.
Abstract
Rising imaging workload and a shortage of radiology specialists have driven interest in artificial intelligence (AI) to improve diagnostic speed and accuracy. This systematic review, without meta-analysis, describes how AI affects diagnostic accuracy and operational efficiency compared with human interpretation in diagnostic radiology. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Cochrane guidance, PubMed, ClinicalKey, ScienceDirect, and Google Scholar were searched on 11 April 2026 for studies published from January 2019 onwards. Two reviewers independently performed study selection, data extraction, and a Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2)-based risk-of-bias assessment. Twenty-one studies were included: 11 compared standalone AI with human readers, six compared AI-assisted with unassisted readers, and four reported both; 18 evaluated task-specific image-analysis AI and three evaluated generative AI models. Because no subgroup was homogeneous enough to pool, we synthesised results narratively and stratified them by comparison type, AI category, imaging modality, and study quality. Standalone image-analysis AI achieved high sensitivity for fractures and selected chest findings but performed less well on subtle findings and lower-quality images, and in one computed tomography-referenced comparison a radiologist outperformed AI. AI assistance improved reader performance more consistently, particularly among less experienced readers. Generative models did not reach specialist performance on complex tasks. Efficiency gains were concentrated in normal studies, and the only randomised trial found lower mammography screen-reading workload with similar early screening performance. No study assessed patient outcomes, and 18 of 21 studies were retrospective. This evidence supports AI only as a supervised, complementary tool; improvements in diagnostic accuracy should not be equated with clinical benefit.
Related
- CT-Referenced Diagnostic Performance and Complementary Error Patterns of Artificial Intelligence Versus a Single Emergency Physician in Chest Radiograph Interpretation: A Retrospective Paired Diagnostic Accuracy Study
- Artificial Intelligence-Based Burn Assessment Demonstrates High Diagnostic Accuracy: Systematic Review and Meta-Analysis
- From underdiagnosis to scalable screening: Applications of artificial intelligence for vertebral compression fracture detection – a systematic review and meta-analysis of diagnostic performance
- Clinical setting-dependent diagnostic accuracy of artificial intelligence and store-and-forward diabetic retinopathy screening: a systematic review and meta-analysis
- Artificial Intelligence for Automated Analysis and Interpretation of Intravascular Ultrasound in Coronary Artery Disease: A Systematic Review
BibTeX
@article{diazperdomo2026artificial,
title = {{Artificial Intelligence Versus Human Interpretation in Diagnostic Radiology: A Systematic Review of Diagnostic Accuracy and Operational Efficiency.}},
author = {Santiago Diaz-Perdomo and María J Losada-Peña and Viviana Gutiérrez-Riobamba and Luisa F Cobaleda-Ramos and Yolercy Vasquez and Jose D Charry},
journal = {Cureus},
year = {2026},
month = nov,
doi = {10.7759/cureus.118954},
url = {https://europepmc.org/article/MED/42968966},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial Intelligence Versus Human Interpretation in Diagnostic Radiology: A Systematic Review of Diagnostic Accuracy and Operational Efficiency.
AU - Santiago Diaz-Perdomo
AU - María J Losada-Peña
AU - Viviana Gutiérrez-Riobamba
AU - Luisa F Cobaleda-Ramos
AU - Yolercy Vasquez
AU - Jose D Charry
PY - 2026
DA - 2026/11/01
JO - Cureus
DO - 10.7759/cureus.118954
UR - https://europepmc.org/article/MED/42968966
AB - Rising imaging workload and a shortage of radiology specialists have driven interest in artificial intelligence (AI) to improve diagnostic speed and accuracy. This systematic review, without meta-analysis, describes how AI affects diagnostic accuracy and operational efficiency compared with human interpretation in diagnostic radiology. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) and Cochrane guidance, PubMed, ClinicalKey, ScienceDirect, and Google Scholar were searched on 11 April 2026 for studies published from January 2019 onwards. Two reviewers independently performed study selection, data extraction, and a Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2)-based risk-of-bias assessment. Twenty-one studies were included: 11 compared standalone AI with human readers, six compared AI-assisted with unassisted readers, and four reported both; 18 evaluated task-specific image-analysis AI and three evaluated generative AI models. Because no subgroup was homogeneous enough to pool, we synthesised results narratively and stratified them by comparison type, AI category, imaging modality, and study quality. Standalone image-analysis AI achieved high sensitivity for fractures and selected chest findings but performed less well on subtle findings and lower-quality images, and in one computed tomography-referenced comparison a radiologist outperformed AI. AI assistance improved reader performance more consistently, particularly among less experienced readers. Generative models did not reach specialist performance on complex tasks. Efficiency gains were concentrated in normal studies, and the only randomised trial found lower mammography screen-reading workload with similar early screening performance. No study assessed patient outcomes, and 18 of 21 studies were retrospective. This evidence supports AI only as a supervised, complementary tool; improvements in diagnostic accuracy should not be equated with clinical benefit.
SN - 2168-8184
ER -