Development and Validation of Models for Preoperative Prediction of Risk and Postoperative Detection of Non-Infectious Complications Using Interpretable Machine Learning and Electronic Health Record Data
We developed parsimonious models for estimating risk of and detection of postoperative non-infectious complications. Our models showed good to excellent performance suggesting that these models could be used to augment manual surveillance.
Authors
- Yaxu Zhuang (ORCID: https://orcid.org/0000-0001-6754-1424)
- Kathryn L. Colborn (ORCID: https://orcid.org/0000-0001-8399-6330)
- Christina M. Stuart (ORCID: https://orcid.org/0000-0002-9851-8486)
- Robert A. Meguid (ORCID: https://orcid.org/0000-0003-2646-4252)
- Michael R. Bronsert (ORCID: https://orcid.org/0000-0003-1879-6193)
- Adam R. Dyas (ORCID: https://orcid.org/0000-0002-2136-8010)
- Yizhou Fei
- William G. Henderson
Institutions
- Colorado School of Public Health (US)
- Outcomes Research Consortium (US)
- University of Colorado Anschutz Medical Campus (US)
Publication Details
- Journal
- Annals of Surgery
- Published
- 2025-03-26
- DOI
- https://doi.org/10.1097/sla.0000000000006709
- Citations
- 3
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 7.44