Table 1.
Baseline characteristics of the datasets.
Fig 1.
Flowchart of patient inclusion.
SNUH, Seoul National University Hospital; CNUH, Chungnam National University Hospital.
Fig 2.
Process of biosignal annotation for hypoxemia prediction.
Each 1-minute segment was labeled as hypoxemic if a hypoxemic event occurred within 1 minute after the segment ended and as non-hypoxemic otherwise. Yellow bar, prediction window with non-hypoxemic event; orange bar, prediction window including SpO2 < 95% during hypoxemic event; green bar, observational window. SpO2, peripheral oxygen saturation.
Table 2.
Comparative performance of machine learning models for hypoxemia prediction in pediatric patients. The performance of the four machine learning models (XGBoost, LSTM, Transformer, and InceptionTime) in predicting hypoxemia in pediatric patients under general anesthesia was evaluated across both internal and external validation datasets.
Fig 3.
Comparison of the performance curves of four models (XGBoost, InceptionTime, Transformer, and LSTM) in predicting intraoperative hypoxemia in pediatric patients under general anesthesia.
Abbreviations: AUROC for internal (a) and external validations (b). LSTM, long short-term memory; AUROC, area under the receiver operating characteristic curve.
Fig 4.
SHAP values for feature importance in the model’s predictions of intraoperative hypoxemia.
SHAP values for internal (a) and external validations (b). The plot shows that demographic features have a highly context-dependent influence. In contrast, key physiological variables such as SpO2, FiO2, and EtCO2 exhibit a more significant and direct impact on the model’s predictions compared to mechanical ventilation parameters like PIP, TV, and MV, aligning with clinical intuition. Abbreviation: SHAP, Shapley Additive exPlanations; SpO2, peripheral oxygen saturation; FiO2, fraction of inspired oxygen; EtCO2, end-tidal carbon dioxide; PIP, peak inspiratory pressure; TV, tidal volume and MV, minute ventilation.