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

Abstract

Background: Intraoperative hypotension has an adverse impact on postoperative outcomes. However, it is difficult to predict and treat intraoperative hypotension in advance according to individual clinical parameters.

Objective: The aim of this study was to develop a prediction model to forecast 5-minute intraoperative hypotension based on the weighted average ensemble of individual neural networks, utilizing the biosignals recorded during noncardiac surgery.

Methods: In this retrospective observational study, arterial waveforms were recorded during noncardiac operations performed between August 2016 and December 2019, at Seoul National University Hospital, Seoul, South Korea. We analyzed the arterial waveforms from the big data in the VitalDB repository of electronic health records. We defined 2s hypotension as the moving average of arterial pressure under 65 mmHg for 2 seconds, and intraoperative hypotensive events were defined when the 2s hypotension lasted for at least 60 seconds. We developed an artificial intelligence-enabled process, named short-term event prediction in the operating room (STEP-OP), for predicting short-term intraoperative hypotension.

Results: The study was performed on 18,813 subjects undergoing noncardiac surgeries. Deep-learning algorithms (convolutional neural network [CNN] and recurrent neural network [RNN]) using raw waveforms as input showed greater area under the precision-recall curve (AUPRC) scores (0.698, 95% CI 0.690-0.705 and 0.706, 95% CI 0.698-0.715, respectively) than that of the logistic regression algorithm (0.673, 95% CI 0.665-0.682). STEP-OP performed better and had greater AUPRC values than those of the RNN and CNN algorithms (0.716, 95% CI 0.708-0.723).

Conclusions: We developed STEP-OP as a weighted average of deep-learning models. STEP-OP predicts intraoperative hypotension more accurately than the CNN, RNN, and logistic regression models.

Trial registration: ClinicalTrials.gov NCT02914444; https://ichgcp.net/clinical-trials-registry/NCT02914444.

Keywords: arterial pressure; artificial intelligence; biosignals; deep learning; hypotension; machine learning.

Conflict of interest statement

Conflicts of Interest: None declared.

©Sooho Choe, Eunjeong Park, Wooseok Shin, Bonah Koo, Dongjin Shin, Chulwoo Jung, Hyungchul Lee, Jeongmin Kim. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 30.09.2021.

Figures

Figure 1

Process flow and criteria of short-term event prediction in the operating room (STEP-OP) for constructing the prediction model of intraoperative hypotension using VitalDB. CNN: convolutional neural network; RNN: recurrent neural network; NaN: missing values.

Figure 2

CONSORT diagram with flow of data construction.

Figure 3

Short-term event prediction in the operating room (STEP-OP) model construction. K×F denotes the kernel size and number of filters. ReLU activation was used after each convolution layer, and the sigmoid was used for the final activation. Normalization, pooling, and dropout layers are omitted in the figure. LSTM: long short-term memory; FC: fully connected layer.

Figure 4

(A) Optimal weight value α on 10% of the training set. (B) Precision-recall curve of developed models. AUPRC: area under the precision-recall curve; CNN: convolutional neural network; RNN: recurrent neural network; STEP-OP: short-term event prediction in the operating room.

Figure 5

Example of a patient record depicting the arterial pressure and STEP-OP prediction values over time. Arterial pressure denotes the 2-second moving average of the arterial pressure. STEP-OP: short-term event prediction in the operating room.