Solam Lee1, Hyung-Chul Lee2, Yu Seong Chu3, Seung Woo Song4, Gyo Jin Ahn5, Hunju Lee6, Sejung Yang7, Sang Baek Koh8. 1. Department of Preventive Medicine, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea; Department of Dermatology, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea. 2. Department of Anaesthesiology and Pain Medicine, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea. 3. Department of Biomedical Engineering, Yonsei University, Wonju, Republic of Korea. 4. Department of Anaesthesiology, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea. 5. Department of Emergency Medicine, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea. 6. Department of Preventive Medicine, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea. 7. Department of Biomedical Engineering, Yonsei University, Wonju, Republic of Korea. Electronic address: syang@yonsei.ac.kr. 8. Department of Preventive Medicine, Yonsei University Wonju College of Medicine, Wonju, Republic of Korea. Electronic address: kohhj@yonsei.ac.kr.
Abstract
BACKGROUND: Intraoperative 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. METHODS: In 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). RESULTS: In 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]). CONCLUSIONS: Deep 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.
BACKGROUND:Intraoperative 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. METHODS: In 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). RESULTS: In 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]). CONCLUSIONS: Deep 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.