Systematic review protocol outlines evaluation standards for AI prediction models in chronic disease remote monitoring, highlighting rigorous evidence synthesis and bias assessment.
Methodology specification for a Cochrane-style systematic review of AI/ML prediction-model studies in IoT-based remote patient monitoring of chronic disease (chronic kidney disease, heart failure, diabetes, multi-morbidity). Anchored to the Cochrane Handbook for Systematic Reviews of Prognosis Research and Prediction Models (Riley/van der Windt/Croft/Moons, OUP 2019) and Cochrane Methodological Expectations Conduct Standards C1-C75. Uses PROBAST+AI (Moons et al. 2025 BMJ) as primary risk-of-bias tool; CHARMS for extraction with 100% dual independent process; REML + Hartung-Knapp-Sidik-Jonkman on logit-transformed c-statistic for meta-analysis with 95% prediction interval; Foroutan 2024/2021/2020 concept papers for GRADE; SWiM 9-item for narrative synthesis where pooling is infeasible; PRISMA 2020 + TRIPOD-SRMA + PRISMA-S + PRISMA-Equity 2012 + PRISMA-Abstracts 2020 reporting layered; PROGRESS-Plus equity extraction + SAGER sex/gender disaggregation; AMSTAR-2 + ROBIS pre-submission self-audit; OSF, PROSPERO, and Zenodo cross-reference plan; AI tool disclosure per RAISE 1 (2025) and ICMJE 2023. This deposit is the protocol companion to the data-only reproducibility package (DOI 10.5281/zenodo.20057329). Dating: this record was deposited on 2026-08-28. The methodology specification it contains is dated 2026-05-12 (v1.1). The publication date shown on this record was originally set to the specification's own date rather than the deposit date, and was corrected to the deposit date on 2026-08-29. This is a retrospective deposit and makes no claim to have been publicly available before 2026-08-28.
No takes yet. Share an insight, caveat, or question.
Abdelaal et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: