Date of Completion

2021

Document Type

Honors College Thesis

Department

Computer Science

Thesis Type

Honors College

First Advisor

Nick Cheney

Second Advisor

Mitchell Tsai

Keywords

Machine Learning, Reintubation, Anesthesiology

Abstract

Accurate estimations of surgical risks is important for improving the shared decision making and informed consent processes. Reintubation is a severe postoperative complication that can lead to various other detrimental outcomes. Reintubation can also be broken up into early reintubation (within 72 hours of surgery) and late reintubation (within 30 days of surgery). Using clinical data provided by ACS NSQIP, scoring systems were developed for the prediction of combined, early, and late reintubation. The risk factors included in each scoring system were narrowed down from a set of 37 pre and perioperative factors. The scoring systems demonstrated good performance in terms of both accuracy and discrimination, and these results were only marginally worse than prediction using the full set of risk variables. While more work needs to be done to identify clinically relevant differences between the early and late reintubation outcomes, the scoring systems provided here can be used by surgeons and patients to improve the quality of care overall.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Share

COinS