Deep learning models for the prediction of intraoperative hypotension.

Abstract

BACKGROUND\nIntraoperative hypotension is associated with a risk of postoperative organ dysfunction. In this study, we aimed to present deep learning algorithms for real-time predictions 5, 10, and 15 min before a hypotensive event.\n\n\nMETHODS\nIn this retrospective observational study, deep learning algorithms were developed and validated using biosignal waveforms acquired from patient monitoring of noncardiac surgery. The classification model was a binary classifier of a hypotensive event (MAP <65 mm Hg) or a non-hypotensive event by analysing biosignal waveforms. The regression model was developed to directly estimate the MAP. The primary outcome was area under the receiver operating characteristic (AUROC) curve and the mean absolute error (MAE).\n\n\nRESULTS\nIn total, 3301 patients were included. For invasive models, the multichannel model with an arterial pressure waveform, electrocardiography, photoplethysmography, and capnography showed greater AUROC than the arterial-pressure-only models (AUROC15-min, 0.897 [95% confidence interval {CI}: 0.894-0.900] vs 0.891 [95% CI: 0.888-0.894]) and lesser MAE (MAE15-min, 7.76 mm Hg [95% CI: 7.64-7.87 mm Hg] vs 8.12 mm Hg [95% CI: 8.02-8.21 mm Hg]). For the noninvasive models, the multichannel model showed greater AUROCs than that of the photoplethysmography-only models (AUROC15-min, 0.762 [95% CI: 0.756-0.767] vs 0.694 [95% CI: 0.686-0.702]) and lesser MAEs (MAE15-min, 11.68 mm Hg [95% CI: 11.57-11.80 mm Hg] vs 12.67 [95% CI: 12.56-12.79 mm Hg]).\n\n\nCONCLUSIONS\nDeep learning models can predict hypotensive events based on biosignals acquired using invasive and noninvasive patient monitoring. In addition, the model shows better performance when using combined rather than single signals.