Development of a field artificial intelligence triage tool: Confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds. Issue 6 (June 2021)

• Record Type: Journal Article
• Authors: Nederpelt, Charlie J.; Mokhtari, Ava K.; Alser, Osaid; Tsiligkaridis, Theodoros; Roberts, Jay; Cha, Miriam; Fawley, Jason A.; Parks, Jonathan J.; Mendoza, April E.; Fagenholz, Peter J.; Kaafarani, Haytham M.A.; King, David R.; Velmahos, George C.; Saillant, Noelle
• Is Part Of: Journal of trauma and acute care surgery. Volume 90:Issue 6(2021)
• Publication Date: 2021-06
• Subjects: Field triage -- machine learning -- gunshot wounds -- shock -- massive transfusion; Surgical intensive care -- Periodicals; Surgical emergencies -- Periodicals; Wounds and injuries -- Surgery -- Periodicals; 617.026
• DOI: 10.1097/TA.0000000000003155
• Languages: English
• ISSNs: 2163-0755

Abstract

Abstract : BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in the first hours after traumatic injury. METHODS: Using an American College of Surgeons Trauma Quality Improvement Program–derived database of truncal and junctional gunshot wound (GSW) patients (aged 16–60 years), we trained an information-aware Dirichlet deep neural network (field artificial intelligence triage). Using supervised training, field artificial intelligence triage was trained to predict shock and the need for major hemorrhage control procedures or early massive transfusion (MT) using GSW anatomical locations, vital signs, and patient information available in the field. In parallel, a confidence model was developed to predict the true-class probability (scale of 0–1), indicating the likelihood that the prediction made was correct, based on the values and interconnectivity of input variables. RESULTS: A total of 29, 816 patients met all the inclusion criteria. Shock, major surgery, and early MT were identified in 13.0%, 22.4%, and 6.3% of the included patients, respectively. Field artificial intelligence triage achieved mean areas under the receiver operating characteristic curve of 0.89, 0.86, and 0.82 for prediction of shock, early MT, and major surgery, respectively, for 80/20 train-test splits over 1, 000 epochs. Mean predicted true-class probability for errors/correct predictions was 0.25/0.87 for shock, 0.30/0.81 for MT, and 0.24/0.69 for major surgery. CONCLUSION: Field artificial intelligence triage accurately identifies potential shock in truncal GSW patients and predicts their need for MT and major surgery, with a high degree of certainty. The presented model is an important proof of concept. Future iterations will use an expansion of databases to refine and validate the model, further adding to its potential to improve triage in the field, both in civilian and military settings. LEVEL OF EVIDENCE: Prognostic, Level III. Abstract : Supplemental digital content is available in the text.