Development of a Machine Learning Model to Predict Cardiac Arrest during Transport of Trauma Patients

Abstract

Background: Trauma is a serious medical and economic burden worldwide, and patients with traumatic injuries have a poor survival rate after cardiac arrest. The authors developed a prediction model specific to prehospital trauma care and used machine learning techniques to increase its accuracy. Methods: This retrospective observational study analyzed data from patients with blunt trauma injuries due to traffic accidents and falls from January 1, 2018, to December 31, 2019. The data were collected from the National Emergency Medical Services Information System, which stores emergency medical service activity records nationwide in the United States. A random forest algorithm was used to develop a machine learning model. Results: The prediction model had an area under the curve of 0.95 and a negative predictive value of 0.99. The feature importance of the predictive model was highest for the AVPU (Alert, Verbal, Pain, Un-responsive) scale, followed by oxygen saturation (SpO2). Among patients who were progressing to cardiac arrest, the cutoff value was 89% for SpO2 in nonalert patients. Conclusions: The machine learning model was highly accurate in identifying patients who did not develop cardiac arrest.