ArticleBMJ open2026
How threshold customisation affects the performance of a multiclass X-ray AI model for primary care triage: a retrospective study.
Article in BMJ open, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 2 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
2 citing papers in PubMed.
- Diagnostic accuracy & clinical importance of AI confidence for extremity fracture detection: 2,508-patient retrospective cohort.Emergency radiology · 2026Article
- Primary Care Doctors' Perspectives and Experiences With a Chest X-Ray AI Triage Program: Qualitative Study.Journal of medical Internet research · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
9 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
objectivesTo describe the structured process of threshold optimisation for a commercially available multiclass chest X-ray (CXR) deep learning model, to evaluate its diagnostic performance across different operating thresholds, and to estimate its potential operational impact within an artificial intelligence (AI)-enabled triage workflow in a primary care setting.
designRetrospective diagnostic performance evaluation with threshold-based analysis.
settingPrimary care radiography services in Singapore, using data derived from two primary care clinics and a tertiary hospital.
participantsA total of 816 adult frontal chest radiographs were included (multiethnic Asian, 464 males, 352 females; mean age 60.8 years). Images were selected to represent the spectrum of findings often encountered in primary care. Exclusion criteria included paediatric studies, lateral or oblique radiographs, and findings not supported by the AI model (eg, bony abnormalities and medical devices). PRIMARY AND SECONDARY OUTCOME MEASURES: Primary outcome measures were sensitivity, specificity, and negative and positive predictive value (NPV and PPV). Secondary outcomes included estimated potential operational improvement, which is calculated by dividing the number of true negatives by the total number of CXRs.
resultsAt the default threshold of 0.15, the AI model achieved a sensitivity of 87.3% (95% CI 83.9% to 90.4%) and an NPV of 87.0% (95% CI 83.6% to 90.2%). Lowering the threshold to 0.10 increased sensitivity to 93.2% (95% CI 90.7% to 95.5%) and NPV to 91.3% (95% CI 88.2% to 94.3%), with specificity of 71.7% (95% CI 67.3% to 76.1%). These trade-offs were considered acceptable for a safety-focused co-triage workflow prioritising minimisation of false negatives.
conclusionsThreshold optimisation is critical for adapting AI models to context-specific clinical workflows. Our study shows that adjusting the operating threshold enabled prioritisation of sensitivity and NPV, supporting safe AI-assisted triage in primary care. This is a deeply collaborative process that must involve radiology and clinical teams: selecting appropriate thresholds aligned with clinical objectives for safe and effective implementation. Future work will assess real-world operational impact and user acceptance following prospective deployment.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.