STEP-OP: Short-term Event Prediction in the Operating Room using Hybrid Deep Learning to Forecast Five-Minute Intraoperative Hypotension (Preprint)
BACKGROUND Intraoperative hypotension has an adverse impact on postoperative outcomes, However, it is difficult to predict and treat intraoperative hypotension with individual clinical parameter in advance. OBJECTIVE To develop a prediction model to forecast five-minute intraoperative hypotension based on the weighted average ensemble of individual neural networks, which utilize the biosignals recorded during non-cardiac surgery. METHODS In this retrospective observational study, arterial wave form was recorded during non-cardiac operation held between August 2016 and December 2019, at Seoul National University Hospital, Seoul, South Korea. We analyzed the arterial waveforms from the big data in VitalDB repository of electronic health records. We defined 2 s hypotension as the moving average of arterial pressure under 65 mm Hg for 2 s, and intraoperative hypotensive events as the case in which 2 s hypotension lasts for at least 60 s. We developed an artificial intelligence-enabled process called 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 non-cardiac surgeries. Deep-learning algorithms (convolutional neural network [CNN] and recurrent neural network [RNN]) using raw waveforms as input showed a greater area under the precision-recall curve (AUPRC) scores than the logistic regression algorithm (0.698 [95% confidence interval {CI}, 0.690–0.705], 0.706 [95% CI, 0.698–0.715]), compared with 0.673 (95% CI, 0.665–0.682), respectively. STEP-OP performed better and had greater AUPRC values than RNN and CNN algorithms (0.716 [95% CI, 0.708–0.723]). CONCLUSIONS We developed STEP-OP, the weighted average of deep-learning models. It predicted intraoperative hypotension more accurately than the CNN, RNN, and logistic regression models. CLINICALTRIAL The study was approved by the institutional review board of Seoul National University Hospital (H-2008-175-1152). (Trial Registration: ClinicalTrials.gov NCT02914444). Arterial Pressure; artificial intelligence; biosignals; deep learning; hypotension; machine learning