Development of a Prediction Model for Intraoperative Blood Pressure Variability

Objective: The aim of this study was to use machine learning to predict and interpret intraoperative high blood pressure variability（IHBPV）.Design: Retrospective cohort study. Setting: Beijing Tsinghua Chang Gung Hospital . Data resources: 47520 operations performed under general anesthesia in the central operating room from March 2016 to April 2022.Interventions: None. Measurements: We collected data on preoperative baseline information and intraoperative variables. The model was constructed with python and run using the following models: XGBoost, random forest, LGBoost, and logistic regression.

Inclusion Criteria:patients who received general anesthesia, intravenous anesthesia, or intravenous-inhalation anesthesia, and ASA1-5 grade.Exclusion Criteria:surgeries with missing key information and surgeries that were not monitored for blood pressure throughout the operation