EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications

Peiyi Li, Shuanliang Gao, Yaqiang Wang, RuiHao Zhou, Guo Chen, Weimin Li, Xuechao Hao, Tao Zhu

British Journal of Anaesthesia · 2024-06 · 132 (6) · 1315-1326

DOI: 10.1016/j.bja.2024.02.025 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift British Journal of Anaesthesia, 2024-06. Verfasst von Peiyi Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China; Laboratory of Anesthesia and Critical Care Medicine, …. Hauptthemen laut MEDLINE: Postoperative Complications, Machine Learning. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Sichuan University, Natural Science Foundation of Sichuan Province, CAMS Innovation Fund for Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Timely detection of modifiable risk factors for postoperative pulmonary complications (PPCs) could inform ventilation strategies that attenuate lung injury. We sought to develop, validate, and internally test machine learning models that use intraoperative respiratory features to predict PPCs. METHODS: We analysed perioperative data from a cohort comprising patients aged 65 yr and older at an academic medical centre from 2019 to 2023. Two linear and four nonlinear learning models were developed and compared with the current gold-standard risk assessment tool ARISCAT (Assess Respiratory Risk in Surgical Patients in Catalonia Tool). The Shapley additive explanation of artificial intelligence was utilised to interpret feature importance and interactions. RESULTS: Perioperative data were obtained from 10 284 patients who underwent 10 484 operations (mean age [range] 71 [65-98] yr; 42% female). An optimised XGBoost model that used preoperative variables and intraoperative respiratory variables had area under the receiver operating characteristic curves (AUROCs) of 0.878 (0.866-0.891) and 0.881 (0.879-0.883) in the validation and prospective cohorts, respectively. These models outperformed ARISCAT (AUROC: 0.496-0.533). The intraoperative dynamic features of respiratory dynamic system compliance, mechanical power, and driving pressure were identified as key modifiable contributors to PPCs. A simplified model based on XGBoost including 20 variables generated an AUROC of 0.864 (0.852-0.875) in an internal testing cohort. This has been developed into a web-based tool for further external validation (https://aorm.wchscu.cn/). CONCLUSIONS: These findings suggest that real-time identification of surgical patients' risk of postoperative pulmonary complications could help personalise intraoperative ventilatory strategies and reduce postoperative pulmonary complications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Postoperative ComplicationsMachine LearningHumansAgedFemaleMaleAged, 80 and overLung DiseasesRisk AssessmentProspective StudiesCohort StudiesRisk FactorsMonitoring, Intraoperative

Stichwörter der Autor:innen

dynamic respiratory featuresintraoperative ventilation strategymachine learning modelpostoperative pulmonary complicationsreal-time risk prediction

Autor:innen und Institutionen

  • Department of Anesthesiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China; Laboratory of Anesthesia and Critical Care Medicine, National-Local Joint Engineering Research Centre of Translational Medi…
  • College of Software Engineering, Chengdu University of Information Technology, Chengdu, Sichuan, China.
  • College of Software Engineering, Chengdu University of Information Technology, Chengdu, Sichuan, China; Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service, Chengdu, Sichuan, China.
  • Department of Anesthesiology, West China Hospital, Sichuan University, Chengdu, Sichuan, China; The Research Units of West China (2018RU012)-Chinese Academy of Medical Sciences, West China Hospital, Sichuan University,…
  • Department of Respiratory and Critical Care Medicine, West China Hospital, Sichuan University, Chengdu, Sichuan, China; Institute of Respiratory Health, Frontiers Science Center for Disease-related Molecular Network, We…

Förderung

  • Sichuan University
  • Natural Science Foundation of Sichuan Province
  • CAMS Innovation Fund for Medical Sciences
  • Sichuan Province Science and Technology Support Program
  • Chinese Academy of Meteorological Sciences
  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation

Zitieren

APA

Li, P., Gao, S., Wang, Y., Zhou, R., Chen, G., Li, W., Hao, X., & Zhu, T. (2024). Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications. British Journal of Anaesthesia, 132(6), 1315-1326. https://doi.org/10.1016/j.bja.2024.02.025

Vancouver

Li P, Gao S, Wang Y, Zhou R, Chen G, Li W, et al. Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications. British Journal of Anaesthesia. 2024;132(6):1315-1326. doi:10.1016/j.bja.2024.02.025

BibTeX
@article{Li2024,
  author = {Li, Peiyi and Gao, Shuanliang and Wang, Yaqiang and Zhou, RuiHao and Chen, Guo and Li, Weimin and Hao, Xuechao and Zhu, Tao},
  title = {Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications},
  journal = {British Journal of Anaesthesia},
  year = {2024},
  volume = {132},
  number = {6},
  pages = {1315--1326},
  doi = {10.1016/j.bja.2024.02.025}
}
Kostenlos starten →