Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension

Abstract

Hypotensive events in the initial stage of anesthesia can cause serious complications in the patients after surgery, which could be fatal. In this study, we intended to predict hypotension after tracheal intubation using machine learning and deep learning techniques after intubation one minute in advance. Meta learning models, such as random forest, extreme gradient boosting (Xgboost), and deep learning models, especially the convolutional neural network (CNN) model and the deep neural network (DNN), were trained to predict hypotension occurring between tracheal intubation and incision, using data from four minutes to one minute before tracheal intubation. Vital records and electronic health records (EHR) for 282 of 319 patients who underwent laparoscopic cholecystectomy from October 2018 to July 2019 were collected. Among the 282 patients, 151 developed post-induction hypotension. Our experiments had two scenarios: using raw vital records and feature engineering on vital records. The experiments on raw data showed that CNN had the best accuracy of 72.63%, followed by random forest (70.32%) and Xgboost (64.6%). The experiments on feature engineering showed that random forest combined with feature selection had the best accuracy of 74.89%, while CNN had a lower accuracy of 68.95% than that of the experiment on raw data. Our study is an extension of previous studies to detect hypotension before intubation with a one-minute advance. To improve accuracy, we built a model using state-of-art algorithms. We found that CNN had a good performance, but that random forest had a better performance when combined with feature selection. In addition, we found that the examination period (data period) is also important.

Machine learning for predicting acute hypotension: A systematic review

“…Regarding the training data time length, Lee et al ( 20 ) studied the intra-operative AHE scenario and found 3 min of data performed better than 2 and 1 min. It is not difficult to imagine that a shorter prediction window and a longer training data time would provide better prediction accuracy, but a prediction window that is too short would be clinically less valuable to healthcare providers in terms of providing them with sufficient time to check the patient's situation and decide if an intervention is needed.…”

“…Note that the most used number of features is between 2 and 9, as shown in Figure 4 (right panel). Lee et al ( 20 ) compared the use of vital records with the use of vital records plus electronic health records (EHR), and found that for the convolutional neural network model, EHR improves the accuracy by 0.39%; however, for other algorithms, such as RF, Xgboost, and deep neural network, the differences were negligible. Therefore, with these completely different findings, it is difficult to conclude which methodology is the best for extracting the features, what features are universally effective no matter what algorithms are applied, or how feature reduction impacts prediction performance.…”

Short-Term Event Prediction in the Operating Room (STEP-OP) of Five-Minute Intraoperative Hypotension Using Hybrid Deep Learning: Retrospective Observational Study and Model Development

“…It is based on a logistic regression and uses engineered features derived from the 20-second arterial waveform as input [ 4 ]. Other researchers have attempted to predict postinduction hypotension using either machine- or deep-learning technologies [ 5 , 25 ]. However, conventional machine-learning technologies require manually engineered features extracted from raw data because they lack the ability to process raw data [ 11 ].…”

A retrospective analysis based on multiple machine learning models to predict lymph node metastasis in early gastric cancer

“…After a comprehensive review of different ML prediction algorithms reported in the literature, compared the scalable, flexible, accurate, and relatively fast, five types of supervised ML classifiers were selected to provide for the establishment the prediction model in EGC (33)(34)(35)(36)(37). These models were the logistic regression classifier (LRC), linear support vector classifier (Linear SVC), Gaussian process classification (GPC), and two gradient boosting methods extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM).…”