Feras Hatib1, Zhongping Jian, Sai Buddi, Christine Lee, Jos Settels, Karen Sibert, Joseph Rinehart, Maxime Cannesson. 1. From Edwards Lifesciences Critical Care, Irvine, California (F.H., Z.J., S.B., C.L., J.S.) the Department of Anesthesiology and Perioperative Care, School of Medicine (C.L., J.R., M.C.) Department of Computer Sciences (C.L.) Department of Biomedical Engineering (C.L., M.C.), University of California, Irving, California the Department of Anesthesiology and Perioperative Medicine, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, California (K.S., M.C.).
Abstract
WHAT WE ALREADY KNOW ABOUT THIS TOPIC: WHAT THIS ARTICLE TELLS US THAT IS NEW: BACKGROUND: : With appropriate algorithms, computers can learn to detect patterns and associations in large data sets. The authors' goal was to apply machine learning to arterial pressure waveforms and create an algorithm to predict hypotension. The algorithm detects early alteration in waveforms that can herald the weakening of cardiovascular compensatory mechanisms affecting preload, afterload, and contractility. METHODS: The algorithm was developed with two different data sources: (1) a retrospective cohort, used for training, consisting of 1,334 patients' records with 545,959 min of arterial waveform recording and 25,461 episodes of hypotension; and (2) a prospective, local hospital cohort used for external validation, consisting of 204 patients' records with 33,236 min of arterial waveform recording and 1,923 episodes of hypotension. The algorithm relates a large set of features calculated from the high-fidelity arterial pressure waveform to the prediction of an upcoming hypotensive event (mean arterial pressure < 65 mmHg). Receiver-operating characteristic curve analysis evaluated the algorithm's success in predicting hypotension, defined as mean arterial pressure less than 65 mmHg. RESULTS: Using 3,022 individual features per cardiac cycle, the algorithm predicted arterial hypotension with a sensitivity and specificity of 88% (85 to 90%) and 87% (85 to 90%) 15 min before a hypotensive event (area under the curve, 0.95 [0.94 to 0.95]); 89% (87 to 91%) and 90% (87 to 92%) 10 min before (area under the curve, 0.95 [0.95 to 0.96]); 92% (90 to 94%) and 92% (90 to 94%) 5 min before (area under the curve, 0.97 [0.97 to 0.98]). CONCLUSIONS: The results demonstrate that a machine-learning algorithm can be trained, with large data sets of high-fidelity arterial waveforms, to predict hypotension in surgical patients' records.
WHAT WE ALREADY KNOW ABOUT THIS TOPIC: WHAT THIS ARTICLE TELLS US THAT IS NEW: BACKGROUND: : With appropriate algorithms, computers can learn to detect patterns and associations in large data sets. The authors' goal was to apply machine learning to arterial pressure waveforms and create an algorithm to predict hypotension. The algorithm detects early alteration in waveforms that can herald the weakening of cardiovascular compensatory mechanisms affecting preload, afterload, and contractility. METHODS: The algorithm was developed with two different data sources: (1) a retrospective cohort, used for training, consisting of 1,334 patients' records with 545,959 min of arterial waveform recording and 25,461 episodes of hypotension; and (2) a prospective, local hospital cohort used for external validation, consisting of 204 patients' records with 33,236 min of arterial waveform recording and 1,923 episodes of hypotension. The algorithm relates a large set of features calculated from the high-fidelity arterial pressure waveform to the prediction of an upcoming hypotensive event (mean arterial pressure < 65 mmHg). Receiver-operating characteristic curve analysis evaluated the algorithm's success in predicting hypotension, defined as mean arterial pressure less than 65 mmHg. RESULTS: Using 3,022 individual features per cardiac cycle, the algorithm predicted arterial hypotension with a sensitivity and specificity of 88% (85 to 90%) and 87% (85 to 90%) 15 min before a hypotensive event (area under the curve, 0.95 [0.94 to 0.95]); 89% (87 to 91%) and 90% (87 to 92%) 10 min before (area under the curve, 0.95 [0.95 to 0.96]); 92% (90 to 94%) and 92% (90 to 94%) 5 min before (area under the curve, 0.97 [0.97 to 0.98]). CONCLUSIONS: The results demonstrate that a machine-learning algorithm can be trained, with large data sets of high-fidelity arterial waveforms, to predict hypotension in surgical patients' records.
Authors: Michael L Burns; Michael R Mathis; John Vandervest; Xinyu Tan; Bo Lu; Douglas A Colquhoun; Nirav Shah; Sachin Kheterpal; Leif Saager Journal: Anesthesiology Date: 2020-04 Impact factor: 7.892
Authors: Sean Coeckelenbergh; Cedrick Zaouter; Brenton Alexander; Maxime Cannesson; Joseph Rinehart; Jacques Duranteau; Philippe Van der Linden; Alexandre Joosten Journal: J Anesth Date: 2019-09-25 Impact factor: 2.078
Authors: Marije Wijnberge; Bart F Geerts; Liselotte Hol; Nikki Lemmers; Marijn P Mulder; Patrick Berge; Jimmy Schenk; Lotte E Terwindt; Markus W Hollmann; Alexander P Vlaar; Denise P Veelo Journal: JAMA Date: 2020-03-17 Impact factor: 56.272