Key result
The STEP-OP hybrid deep learning model predicted 5-minute intraoperative hypotension with a greater area under the precision-recall curve (0.716; 95% CI 0.708-0.723) than logistic regression.
Why the study?
Intraoperative hypotension adversely impacts postoperative outcomes, but predicting and treating it in advance using individual clinical parameters is difficult.
Does the STEP-OP hybrid deep learning model improve the prediction of 5-minute intraoperative hypotension compared to individual neural networks or logistic regression in patients undergoing noncardiac surgery?
Observational (n=18,813)
No
Does the STEP-OP hybrid deep learning model improve the prediction of 5-minute intraoperative hypotension compared to individual neural networks or logistic regression in patients undergoing noncardiac surgery?
Effect estimate: AUPRC 0.716 (95% CI 0.708-0.723)
Absolute Event Rate: 0.716% vs 0.673%
The STEP-OP hybrid deep learning model predicts intraoperative hypotension more accurately than individual CNN, RNN, or logistic regression models.
May support ML-based intraoperative hypotension prediction; leaves open clinical utility pending prospective validation.
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. CLINICALTRIAL ClinicalTrials.gov NCT02914444; https://clinicaltrials.gov/ct2/show/NCT02914444.
No takes yet. Share an insight, caveat, or question.
Choe et al. (2021) conducted an observational in Intraoperative hypotension (n=18,813). STEP-OP model vs. Logistic regression, CNN, and RNN models was evaluated on Area under the precision-recall curve (AUPRC) for predicting 5-minute intraoperative hypotension (AUPRC 0.716, 95% CI 0.708-0.723). The STEP-OP hybrid deep learning model predicted 5-minute intraoperative hypotension with a greater area under the precision-recall curve (0.716; 95% CI 0.708-0.723) than logistic regression.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: