Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1284
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-10-05T06:55:58.096687Z
status: published
lens: trace
sector: health
headline: Generative AI versus physicians in diagnostic radiology: a systematic review and meta-analysis
dek: Purpose Generative artificial intelligence (AI) models are increasingly evaluated for diagnostic tasks in radiology, yet accuracy, study designs, endpoints, and comparators vary widely. The purpose was to synthesize diagnostic accuracy of generative AI for radiology and compare performance with physicians. Materials and methods A systematic review and meta-analysis was prospectively registered in PROSPERO (CRD420251040000) and conducted in accordance with PRISMA-DTA guidance. Searches of Medline, Scopus, Web of…
gain_title: Generative AI achieved higher diagnostic accuracy when given text-only input compared to image-only input in radiology tasks.
problem_title: Generative AI showed significantly lower diagnostic accuracy than expert physicians on radiology tasks, with a 13.0 percentage point gap.
trace_subject: diagnostic accuracy of generative AI for radiology tasks
gain_reading: Generative AI achieved higher diagnostic accuracy when given text-only input compared to image-only input in radiology tasks.
gain_evidence: Text-only input was associated with higher accuracy than image-only input
problem_reading: Generative AI showed significantly lower diagnostic accuracy than expert physicians on radiology tasks, with a 13.0 percentage point gap.
problem_evidence: Generative AI overall showed significantly lower accuracy than expert physicians | Generative AI remained less accurate than expert physicians on diagnostic tasks in radiology
quick_read: A systematic review and meta-analysis of 48 studies published through March 2025 synthesized diagnostic accuracy of generative AI in radiology and compared it to physician performance using multilevel random-effects meta-regression.

The finding matters because lower AI accuracy relative to experts raises safety concerns for clinical deployment, while the higher accuracy with text-only inputs suggests assistive, text-oriented use cases need further study but may be confounded by task difficulty and information content.
limitation: Observed differences in accuracy by input modality may be confounded by task difficulty and information content, and evaluations lacked standardization.
tag: Dual reading
key_points: Systematic review and meta-analysis of 48 studies from June 2018-March 2025 comparing generative AI to physicians on radiology diagnostic tasks. | Pooled generative AI accuracy was 42.9% for free-text tasks and 58.1% for choice tasks. | Multilevel random-effects meta-regression with study-clustered robust inference found text-only input outperformed image-only and text-and-image inputs. | Authors concluded standardized, transparently reported, adequately powered evaluations are warranted before clinical deployment.
rundown: The review was prospectively registered in PROSPERO and followed PRISMA-DTA guidance, searching Medline, Scopus, Web of Science, Cochrane Central, and medRxiv, with two reviewers screening and assessing bias with PROBAST+AI.

Analysis reported a difference of +13.0 percentage points for physicians minus AI (P = .038), and found image-only input was -25.9 percentage points lower than text-only (P = .001) and text-and-image was -10.6 points lower than text-only (P = .046).
sources:
- peer_reviewed | Japanese Journal of Radiology | https://doi.org/10.1007/s11604-026-02090-7 | 2026-10-03
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

c33d7889faa59ffb65501affc0c5f389f9733b9995e0fdfb3db4c8206e989a4a

previous

0000000000000000000000000000000000000000000000000000000000000000