The ability to predict postinduction hypotension remains limited and challenging due to the multitude of data elements that may be considered
Novel machine-learning algorithms may offer a systematic approach to predict postinduction hypotension, but are understudied
What This Article Tells Us That Is New:
Among 13,323 patients undergoing a variety of surgical procedures, 8.9% experienced a mean arterial pressure less than 55 mmHg within 10 min of induction start
While some machine-learning algorithms perform worse than logistic regression, several techniques may be superior
Gradient boosting machine, with tuning, demonstrates a receiver operating characteristic area under the curve of 0.76, a negative predictive value of 19%, and positive predictive value of 96%
Background: Hypotension is a risk factor for adverse perioperative outcomes. Machine-learning methods allow large amounts of data for development of robust predictive analytics. The authors hypothesized that machine-learning methods can provide prediction for the risk of postinduction hypotension.
Methods: Data was extracted from the electronic health record of a single quaternary care center from November 2015 to May 2016 for patients over age 12 that underwent general anesthesia, without procedure exclusions. Multiple supervised machine-learning classification techniques were attempted, with postinduction hypotension (mean arterial pressure less than 55 mmHg within 10 min of induction by any measurement) as primary outcome, and preoperative medications, medical comorbidities, induction medications, and intraoperative vital signs as features. Discrimination was assessed using cross-validated area under the receiver operating characteristic curve. The best performing model was tuned and final performance assessed using split-set validation.
Results: Out of 13,323 cases, 1,185 (8.9%) experienced postinduction hypotension. Area under the receiver operating characteristic curve using logistic regression was 0.71 (95% CI, 0.70 to 0.72), support vector machines was 0.63 (95% CI, 0.58 to 0.60), naive Bayes was 0.69 (95% CI, 0.67 to 0.69), k-nearest neighbor was 0.64 (95% CI, 0.63 to 0.65), linear discriminant analysis was 0.72 (95% CI, 0.71 to 0.73), random forest was 0.74 (95% CI, 0.73 to 0.75), neural nets 0.71 (95% CI, 0.69 to 0.71), and gradient boosting machine 0.76 (95% CI, 0.75 to 0.77). Test set area for the gradient boosting machine was 0.74 (95% CI, 0.72 to 0.77).
Conclusions: The success of this technique in predicting postinduction hypotension demonstrates feasibility of machine-learning models for predictive analytics in the field of anesthesiology, with performance dependent on model selection and appropriate tuning.