Predicting vital sign deviations during surgery from patient monitoring data: developing and validating single-stream deep learning models

Alina Dubatovka; Christoph B Nöthiger; Donat R Spahn; Joachim M Buhmann; Tadzio R Roche; David W Tscholl

doi:10.1016/j.bja.2024.06.030

Predicting vital sign deviations during surgery from patient monitoring data: developing and validating single-stream deep learning models

Br J Anaesth. 2024 Oct;133(4):889-892. doi: 10.1016/j.bja.2024.06.030. Epub 2024 Aug 1.

Authors

Alina Dubatovka¹, Christoph B Nöthiger², Donat R Spahn², Joachim M Buhmann¹, Tadzio R Roche³, David W Tscholl²

Affiliations

¹ Department of Computer Science, ETH Zurich, Zurich, Switzerland.
² Institute of Anaesthesiology, University of Zurich, University Hospital Zurich, Zurich, Switzerland.
³ Institute of Anaesthesiology, University of Zurich, University Hospital Zurich, Zurich, Switzerland. Electronic address: [email protected].

PMID: 39089955
DOI: 10.1016/j.bja.2024.06.030

No abstract available

Keywords: algorithms; artificial intelligence; biosignals; clinical decision support systems; digital medicine; machine learning; perioperative medicine, vital signs.

Publication types

Letter
Validation Study

MeSH terms

Deep Learning*
Humans
Monitoring, Intraoperative* / methods
Reproducibility of Results
Vital Signs*