Electrocardiographic deep learning for predicting post-procedural mortality: a model development and validation study.

Autor:	Ouyang D; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA. Electronic address: david.ouyang@cshs.org., Theurer J; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Stein NR; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Hughes JW; Department of Computer Science, Stanford University, Palo Alto, CA, USA., Elias P; Milstein Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA; Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA., He B; Department of Computer Science, Stanford University, Palo Alto, CA, USA., Yuan N; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Duffy G; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Sandhu RK; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Ebinger J; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Botting P; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Jujjavarapu M; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Claggett B; Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA., Tooley JE; Division of Cardiology, Stanford University, Palo Alto, CA, USA., Poterucha T; Milstein Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA., Chen JH; Division of Bioinformatics Research, Stanford University, Palo Alto, CA, USA., Nurok M; Division of Anesthesia, Department of Surgery, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Perez M; Division of Cardiology, Stanford University, Palo Alto, CA, USA., Perotte A; Milstein Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA., Zou JY; Department of Computer Science, Stanford University, Palo Alto, CA, USA; Department of Medicine, and Department of Biomedical Data Science, Stanford University, Palo Alto, CA, USA., Cook NR; Division of Preventive Medicine, Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA., Chugh SS; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Cheng S; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Albert CM; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Jazyk:	angličtina
Zdroj:	The Lancet. Digital health [Lancet Digit Health] 2024 Jan; Vol. 6 (1), pp. e70-e78. Date of Electronic Publication: 2023 Dec 07.
DOI:	10.1016/S2589-7500(23)00220-0
Abstrakt:	Background: Preoperative risk assessments used in clinical practice are insufficient in their ability to identify risk for postoperative mortality. Deep-learning analysis of electrocardiography can identify hidden risk markers that can help to prognosticate postoperative mortality. We aimed to develop a prognostic model that accurately predicts postoperative mortality in patients undergoing medical procedures and who had received preoperative electrocardiographic diagnostic testing. Methods: In a derivation cohort of preoperative patients with available electrocardiograms (ECGs) from Cedars-Sinai Medical Center (Los Angeles, CA, USA) between Jan 1, 2015 and Dec 31, 2019, a deep-learning algorithm was developed to leverage waveform signals to discriminate postoperative mortality. We randomly split patients (8:1:1) into subsets for training, internal validation, and final algorithm test analyses. Model performance was assessed using area under the receiver operating characteristic curve (AUC) values in the hold-out test dataset and in two external hospital cohorts and compared with the established Revised Cardiac Risk Index (RCRI) score. The primary outcome was post-procedural mortality across three health-care systems. Findings: 45 969 patients had a complete ECG waveform image available for at least one 12-lead ECG performed within the 30 days before the procedure date (59 975 inpatient procedures and 112 794 ECGs): 36 839 patients in the training dataset, 4549 in the internal validation dataset, and 4581 in the internal test dataset. In the held-out internal test cohort, the algorithm discriminates mortality with an AUC value of 0·83 (95% CI 0·79-0·87), surpassing the discrimination of the RCRI score with an AUC of 0·67 (0·61-0·72). The algorithm similarly discriminated risk for mortality in two independent US health-care systems, with AUCs of 0·79 (0·75-0·83) and 0·75 (0·74-0·76), respectively. Patients determined to be high risk by the deep-learning model had an unadjusted odds ratio (OR) of 8·83 (5·57-13·20) for postoperative mortality compared with an unadjusted OR of 2·08 (0·77-3·50) for postoperative mortality for RCRI scores of more than 2. The deep-learning algorithm performed similarly for patients undergoing cardiac surgery (AUC 0·85 [0·77-0·92]), non-cardiac surgery (AUC 0·83 [0·79-0·88]), and catheterisation or endoscopy suite procedures (AUC 0·76 [0·72-0·81]). Interpretation: A deep-learning algorithm interpreting preoperative ECGs can improve discrimination of postoperative mortality. The deep-learning algorithm worked equally well for risk stratification of cardiac surgeries, non-cardiac surgeries, and catheterisation laboratory procedures, and was validated in three independent health-care systems. This algorithm can provide additional information to clinicians making the decision to perform medical procedures and stratify the risk of future complications. Funding: National Heart, Lung, and Blood Institute. Competing Interests: Declaration of interests DO reports support from the National Institute of Health (NIH; NHLBI R00HL157421) and Alexion, and consulting or honoraria for lectures from EchoIQ, Ultromics, Pfizer, InVision, the Korean Society of Echo, and the Japanese Society of Echo. JWH reports funding from the National Science Foundation (DGE-1656518). PE reports research support from the NIH (T32HL007854-21) and serves on the American College of Cardiology Innovation Council. BC reports consulting from Alnylam, Cardurion, Corvia, CVRX, Cytokinetics, Intellia, and Rocket. TP reports stock in Abbot and Baxter, and research support from the American Heart Association, Eido, Pfizer, Edwards, and the New York Academy of Medicine. JHC reports research funding from NIH/National Institute of Aging (AI17812101), NIH/National Institute on Drug Abuse (UG1DA015815-CTN-0136), AIMI-HAI Partnership, Doris Duke Charitable Foundation (20211260), Google (SPO136094), American Heart Association, and Clinical and Translational Sciences Awards Program by the National Center for Advancing Translational Sciences (R56LM013365); is a co-founder of Reaction Explorer; and receives consulting fees from Sutton Pierce and Younker Hyde MacFarlane. MP reports research support from the NIH (HL136390), patents for ECG-based cardiac arrhythmia detection (WO2014205310A3), and consulting fees from Apple, Biotronik, Boston Scientific, QALY, Johnson and Johnson, and Bristol Myers Squibb. CMA reports support from NIH (HL165840), consulting fees from Medtronic, Novartis, Illumina, and Medtronic, and participation in advisory boards for Boston Scientific, Medtronic, and Element Science; and is a trustee on the board for the Heart Rhythm Society. All other authors declare no competing interests. (Copyright © 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND license. Published by Elsevier Ltd.. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu