Why the study?
Arterial hypotension is associated with postoperative complications like myocardial infarction or acute kidney injury, but little research exists for real-time prediction specifying when events occur.
Does a machine learning model based on systematic feature engineering of invasive blood pressure predict intraoperative hypotension 5 minutes in advance?
Comparison
Random forest model based on invasive blood pressure feature engineering vs normal samples
Design
Prediction model development study
Authors
Loading...
May enable earlier postoperative intervention; hypothesis-generating for real-time hypotension forecasting until validated prospectively.
Does a machine learning model based on systematic feature engineering of invasive blood pressure predict intraoperative hypotension 5 minutes in advance?
A random forest machine learning model using systematic feature engineering on invasive blood pressure can predict intraoperative hypotension 5 minutes in advance with high accuracy and precision.
Lee et al. (2022) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: