TRV-2026-1265Version 3 · Revised

Saved · see the current record

Why this version exists

Voice pass: plainer wording and study attribution; no facts or figures changed.

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-1265
version: 3
kind: revised
reason: Voice pass: plainer wording and study attribution; no facts or figures changed.
timestamp: 2026-11-05T11:20:05.849568Z
status: published
lens: p_space
sector: health
headline: 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
dek: 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…
gain_title: (none)
problem_title: 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).
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: 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).
problem_evidence: positive predictive value 17.89% (95% Wilson CI 13.4% to 23.5%) and Cohen's κ 0.237 | Systematic score compression-preserved discrimination despite calibration shift-is a quantifiable marker of low- and middle-income country distributional shift.
quick_read: From 5 to 20 June 2026, researchers prospectively tested a publicly available DenseNet-121 model from TorchXRayVision in shadow mode on 826 consecutive chest radiographs from health assessment applicants at Patan Hospital in Lalitpur, Nepal, comparing AI scores to blinded single-reader radiologist classifications.

The model preserved discrimination with high sensitivity and NPV, suggesting rule-out triage potential, but exhibited systematic calibration failure and low PPV in this population, so threshold stability, the strength of the reference standard and readiness for operational deployment remain uncertain without local recalibration and independent external validation.
limitation: Single-reader reference standard, small number of positives creating wide uncertainty, and lack of independent external validation limit generalizability before operational deployment.
tag: Evidence-backed problem
key_points: Prospective single-centre shadow-mode study from 5 June 2026 to 20 June 2026 inclusive with 826 consecutive applicants; 41 (4.97%) classified abnormal by reference standard. | Index test was TorchXRayVision densenet121-res224-all with maximum aggregated pathology probability compared against post hoc threshold 0.6258 selected for >=95% sensitivity. | Reference standard was single-reader-per-case review by two board-certified radiodiagnosticians and one resident, blinded to AI output. | 10-fold cross-validation showed bias-corrected specificity 75.80% with optimism +1.40 pp; independent external validation was not performed.
rundown: The study enrolled 826 consecutive foreign employment predeparture and student migration applicants at Patan Academy of Health Sciences/Patan Hospital, with two exclusions for DICOM technical failure, and used a maximum aggregated pathology probability score.

At threshold 0.6258, specificity was 77.2% (95% CI 74.1% to 80.0%) with PPV 17.89% and Cohen's kappa 0.237, while Brier score 0.3621 exceeded null Brier 0.0472 and ECE was 0.564, showing score compression from 0.52-0.72.

Authors concluded high sensitivity supports potential as radiographic abnormality rule-out triage tool but noted this does not constitute microbiological exclusion of active pulmonary tuberculosis and called for prospective local calibration and external validation.
sources:
- peer_reviewed | BMJ Open | https://doi.org/10.1136/bmjopen-2026-124868 | 2026-10-01
prev: bd709f89fbe39f715a58597d79f844b61f0b7d7e6e24bc69b86ccd3921630865
SHA-256 hash
9ca49d020c9df20b5e4cd9a26c060abf1da0caae3c6f3d6bc2d718d5199e0363
Previous version’s hash
bd709f89fbe39f715a58597d79f844b61f0b7d7e6e24bc69b86ccd3921630865
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.