Development of a prediction model for hypotension after induction of anesthesia using machine learning

Abstract

Arterial hypotension during the early phase of anesthesia can lead to adverse outcomes such as a prolonged postoperative stay or even death. Predicting hypotension during anesthesia induction is complicated by its diverse causes. We investigated the feasibility of developing a machine-learning model to predict postinduction hypotension. Naïve Bayes, logistic regression, random forest, and artificial neural network models were trained to predict postinduction hypotension, occurring between tracheal intubation and incision, using data for the period from between the start of anesthesia induction and immediately before tracheal intubation obtained from an anesthesia monitor, a drug administration infusion pump, an anesthesia machine, and from patients' demographics, together with preexisting disease information from electronic health records. Among 222 patients, 126 developed postinduction hypotension. The random-forest model showed the best performance, with an area under the receiver operating characteristic curve of 0.842 (95% confidence interval [CI]: 0.736-0.948). This was higher than that for the Naïve Bayes (0.778; 95% CI: 0.65-0.898), logistic regression (0.756; 95% CI: 0.630-0.881), and artificial-neural-network (0.760; 95% CI: 0.640-0.880) models. The most important features affecting the accuracy of machine-learning prediction were a patient's lowest systolic blood pressure, lowest mean blood pressure, and mean systolic blood pressure before tracheal intubation. We found that machine-learning models using data obtained from various anesthesia machines between the start of anesthesia induction and immediately before tracheal intubation can predict hypotension occurring during the period between tracheal intubation and incision.

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1. Distribution of hypotension after tracheal intubation.

(a) the distribution of the elapsed time from tracheal intubation to first hypotension event in terms of patients. (b) the distribution of the elapsed time from tracheal intubation in terms of hypotension episodes. (c) the cumulative distribution of the elapsed time from tracheal intubation to first hypotension event in terms of patients. (d) the cumulative distribution of the elapsed time from tracheal intubation in terms of hypotension episodes.

Fig 2. Receiver operating characteristic curve.

Naïve Bayes, logistic regression, random forest, and ANN models are expressed as black, blue, red, and purple lines, respectively. Naïve Bayes with Feature set B (AUC, 77.82%), logistic regression with Feature set B (AUC, 75.56%), random forest with Feature set C (AUC, 84.23%), and ANN with All features (AUC, 76.01%). ANN, artificial neural network.

Fig 3. Feature importance plot from the random forest model.

NIBP_SBP.min and NIBP_MBP.min were ranked as the first and second most important features based on the importance plot of the random forest model. NIBP, noninvasive blood pressure; SBP, systolic blood pressure; MBP, mean blood pressure; TV, tidal volume; CP, plasma concentration; HR, heart rate; DBP, diastolic blood pressure; RR, respiratory rate; CT, target concentration.