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.
A deep learning algorithm screened chest radiographs with 99.7% accuracy in ruling out abnormalities, potentially reducing unnecessary follow-up testing.
This diagnostic validation study examined 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. The DenseNet-121 algorithm demonstrated high point-estimate sensitivity and excellent discrimination for chest radiograph triage in a Nepali health-assessment population, supporting its potential as a radiographic abnormality rule-out triage tool (NPV 99 point 67%); this does not constitute microbiological exclusion.
What the study was
- Study design
- Diagnostic validation study
- Population
- Human participants or patients described in the PubMed abstract
- Sample size
- 41
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- BMJ open
Why it surfaced
Diagnostic validation study; conservative rapid-triage score based on novelty, clinical relevance, design quality, and population or unmet need.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.