Development of practical triage methods for critical trauma patients: machine-learning algorithm for evaluating hybrid operation theatre entry of trauma patients (THETA)

Abstract

Purpose: Hybrid operating rooms benefit patients with severe trauma but have a prerequisite of significant resources. This paper proposes a practical triage method to determine patients that should enter the hybrid operating room considering a limited availability of medical resources.

Methods: This retrospective observational study was conducted using the database from the Japan Trauma Data Bank comprising information collected between January 2004 and December 2018. A machine-learning-based triage algorithm was developed using the baseline demographics, injury mechanisms, and vital signs obtained from the database. The analysis dataset comprised information regarding 117,771 trauma patients with an abbreviated injury scale (AIS) > 3. The performance of the proposed model was compared against those of other statistical models [logistic regression and classification and regression tree (CART) models] while considering the status quo entry condition (systolic blood pressure < 90 mmHg).

Results: The proposed trauma hybrid-suite entry algorithm (THETA) outperformed other pre-existing algorithms [precision-recall area under the curve: THETA (0.59), logistic regression model (0.22), and classification and regression tree (0.20)].

Conclusion: A machine-learning-based algorithm was developed to triage patient entry into hybrid operating rooms. Although the validation in a prospective multicentre arrangement is warranted, the proposed algorithm could be a potentially useful tool in clinical practice.

Keywords: Entry condition; Hybrid operation theatre; Hybrid suite; Machine learning; RAPTOR.