Moderate evidence
Published recordHealthProblem Space
More
Diagnostic accuracy of a DenseNet-121 deep learning algorithm for chest radiograph triage in health assessment applicants: a prospective shadow-mode validation study in Nepal
- Truvace record
- TRV-2026-1265raw data (JSON)
- Version
- v3Revised
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 9ca49d020c9d…check it
Objectives To evaluate the diagnostic accuracy of a publicly available DenseNet-121 convolutional neural network (TorchXRayVision) for triaging chest radiographs of health assessment applicants at a tertiary hospital in Nepal. Design Prospective, single-centre, shadow-mode diagnostic accuracy validation study. Reported in accordance with the Standards for Reporting of Diagnostic Accuracy Studies (STARD) 2015 checklist and STARD-Artificial Intelligence (AI)/Developmental and Exploratory Clinical Investigations of…
The problem
At a threshold set for at least 95% sensitivity, a study of 826 chest X-rays in Nepal found only 17.89% of the AI's abnormal flags were correct, agreement with radiologists was low (kappa 0.237), and its probability scores were badly miscalibrated (ECE 0.564).
What this doesn’t fix
Single-reader reference standard, small number of positives creating wide uncertainty, and lack of independent external validation limit generalizability before operational deployment.
Sources
1 on file- BMJ Opendoi:10.1136/bmjopen-2026-124868
Cite this record
v3Truvace Impact Record TRV-2026-1265, v3: “Diagnostic accuracy of a DenseNet-121 deep learning algorithm for chest radiograph triage in health assessment applicants: a prospective shadow-mode validation study in Nepal.” Truvace, 2026-11-05. /record/TRV-2026-1265 (accessed on the day you copy it). sha256 9ca49d020c9df20b…
Change history
3 versionsEvery change made to this record since it was first published, and why.
Voice pass: plainer wording and study attribution; no facts or figures changed.
Editorial pass: sharper headline; gain/problem restated as concrete outcomes.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-1265 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace