To 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.

Retrospective diagnostic performance evaluation with threshold-based analysis.

Primary care radiography services in Singapore, using data derived from two primary care clinics and a tertiary hospital.

A 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 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.

At 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.

Threshold 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.

Peripheral artery disease (PAD) affected approximately 800 000 Canadians aged 25 years or older in 2015 and it poses a substantial risk of lower extremity amputation (LEA). While clinical risk factors for amputation are well-established, the impact of social determinants of health (SDoH) on amputation risk remains unclear, particularly in a Canadian context.

This systematic review aims to: (1) synthesise evidence on the associations between multilevel SDoH domains and LEA (both major and/or minor) risk in Canadian PAD patients including intersectional effects of race and ethnicity with another SDoH domain, and (2) evaluate the statistical methodologies used in the researched literature to inform future study design and analysis approaches.

We will systematically search MEDLINE, Embase, EmCare, Global Health, Cumulative Index to Nursing and Allied Health Literature and Web of Science for studies examining SDoH and LEA in Canadian patients with PAD (including chronic limb-threatening ischaemia which is a severe form of PAD). Date limits for each database will be from inception through December 2025. SDoH will be categorised using a modified Healthy People 2030 SDoH framework under six domains: economic stability, education, food, neighbourhood and physical environment, healthcare system and community and social context. Two reviewers will independently screen titles, abstracts and full texts, with discrepancies resolved by a third reviewer. Data will be extracted on study characteristics, SDoH measures, outcomes and statistical methods. Risk of bias will be assessed using RoB 2 for randomised trials, ROBINS-I for non-randomised studies of interventions and ROBINS-E for studies investigating exposures. A narrative synthesis, and where data permit, a Bayesian hierarchical meta-analysis using both effect size and contingency table approaches will be conducted. Statistical heterogeneity will be explored through subgroup analyses and meta-regression, examining study design, SDoH measurement approaches and population characteristics.

As a systematic review and meta-analysis, ethics approval is not required. For institutional oversight, we provide the contact of Dr Sonia Anand (Associate Vice-President, Global Health, McMaster University; anands@mcmaster.ca). Results will be reported following PRISMA guidelines and disseminated through a peer-reviewed publication.

CRD420251115759.