Key result
Systematic review protocol evaluates machine-learning models for predicting peri-anesthetic hypoxemia.
Why the study?
Machine-learning models for predicting peri-anesthetic hypoxemia have been developed but require systematic evaluation and critical appraisal.
Can machine-learning models accurately predict peri-anesthetic hypoxemia?
Can machine-learning models accurately predict peri-anesthetic hypoxemia?
This study aims to systematically review and meta-analyze the performance of machine-learning models for predicting hypoxemia following general anesthesia.
ML models for peri-anesthetic hypoxemia show moderate performance with high bias risk and scant external validation; leaves open routine adoption pending prospective trials.
Systematic review and multilevel meta-analysis of machine-learning models for predicting peri-anesthetic hypoxemia, with separate synthesis of internal and external validation and PROBAST+AI assessment. This is a retrospective registration created after completion of the search, screening, extraction, appraisal, and synthesis stages.
No takes yet. Share an insight, caveat, or question.
Saem et al. (2026) studied this question. Machine-learning models for predicting peri-anesthetic hypoxemia were evaluated in a systematic review, though specific performance results are not reported in this registration abstract.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: