학술논문
A Pilot Study Using Machine Learning Algorithms and Wearable Technology for the Early Detection of Postoperative Complications After Cardiothoracic Surgery
Document Type
Academic Journal
Author
Beqari, Jorind; Powell, Joseph; Hurd, Jacob; Potter, Alexandra L.; McCarthy, Meghan; Srinivasan, Deepti; Wang, Danny; Cranor, James; Zhang, Lizi; Webster, Kyle; Kim, Joshua; Rosenstein, Allison; Zheng, Zeyuan; Lin, Tung Ho; Li, Jing; Fang, Zhengyu; Zhang, Yuhang; Anderson, Alex; Madsen, James; Anderson, Jacob; Clark, Anne; Yang, Margaret E.; Nurko, Andrea; El-Jawahri, Areej R.; Sundt, Thoralf M.; Melnitchouk, Serguei; Jassar, Arminder S.; D’Alessandro, David; Panda, Nikhil; Schumacher-Beal, Lana Y.; Wright, Cameron D.; Auchincloss, Hugh G.; Sachdeva, Uma M.; Lanuti, Michael; Colson, Yolonda L.; Langer, Nathaniel; Osho, Asishana; Yang, Chi-Fu Jeffrey; Li, Xiao
Source
Annals of Surgery. Mar 14, 2024
Subject
Language
English
ISSN
0003-4932
Abstract
OBJECTIVE:: To evaluate whether a machine learning algorithm (i.e. the “NightSignal” algorithm) can be used for the detection of postoperative complications prior to symptom onset after cardiothoracic surgery. SUMMARY BACKGROUND DATA:: Methods that enable the early detection of postoperative complications after cardiothoracic surgery are needed. METHODS:: This was a prospective observational cohort study conducted from July 2021 to February 2023 at a single academic tertiary care hospital. Patients aged 18 years or older scheduled to undergo cardiothoracic surgery were recruited. Study participants wore a Fitbit watch continuously for at least 1 week preoperatively and up to 90-days postoperatively. The ability of the NightSignal algorithm—which was previously developed for the early detection of Covid-19—to detect postoperative complications was evaluated. The primary outcomes were algorithm sensitivity and specificity for postoperative event detection. RESULTS:: A total of 56 patients undergoing cardiothoracic surgery met inclusion criteria, of which 24 (42.9%) underwent thoracic operations and 32 (57.1%) underwent cardiac operations. The median age was 62 (IQR: 51-68) years and 30 (53.6%) patients were female. The NightSignal algorithm detected 17 of the 21 postoperative events a median of 2 (IQR: 1-3) days prior to symptom onset, representing a sensitivity of 81%. The specificity, negative predictive value, and positive predictive value of the algorithm for the detection of postoperative events were 75%, 97%, and 28%, respectively. CONCLUSIONS:: Machine learning analysis of biometric data collected from wearable devices has the potential to detect postoperative complications—prior to symptom onset—after cardiothoracic surgery.