AI-Enhanced Point-of-Care Diagnostics for Infectious Diseases in Resource-Limited Settings: A Scoping Review

Abstract

Preprint v2 (May 2026). Version 2 of this preprint adds four post-hoc explanatory cross-tabulations to the original version (v1: https://doi.org/10.5281/zenodo.19446485, posted 7 April 2026). The four new analyses operate on the same 237-study extraction set used in v1; the included-studies set is unchanged at 237. v2 converts the synthesis from a descriptive map of the field to a diagnostic analysis of why this literature produces studies prolifically but rarely converts them into prospective field-validated tools. Four findings emerge: The conventional "HIC develops, LMIC tests" framing is not supported in this corpus — high-income-country-affiliated studies skew toward later-stage validation, and low-income-country-affiliated studies report the highest prospective-field share (44%). The top 50 studies by citation count contain no lightweight architectures, and heavy architectures (ResNet, EfficientNet, Vision Transformer family) reach 0% prospective field validation across the full corpus, while the three lightweight-architecture studies reach 33%. Cost reporting is flat at 37–38% across all validation maturity stages — it does not mature with the validation pipeline. Disease coverage figures are partly an artefact of reporting completeness, with HIV over-represented and tuberculosis under-represented in the complete-case subset by 12 percentage points each. This scoping review systematically maps 237 studies on AI-enhanced point-of-care diagnostics for infectious diseases in resource-limited settings, published between 2015 and early 2026, following JBI methodology and PRISMA-ScR guidelines with a registered protocol (OSF: https://doi.org/10.17605/OSF.IO/KV8MP). The manuscript includes 16 figures (9 original + 7 new in v2), 54 references, and is accompanied by 5 supplementary materials (search strategies, PRISMA-ScR checklist, PRISMA flow diagram, grey-literature search log, complete data charting table for 237 studies, excluded studies list, and v2 analysis result tables) deposited at OSF. v2 analysis scripts, citation cache, result tables, and figures are also deposited in the OSF data and code repository (https://doi.org/10.17605/OSF.IO/KV8MP).

Ähnliche Arbeiten