Using the Field Artificial Intelligence Triage (FAIT) tool to predict hospital critical care resource utilization in patients with truncal gunshot wounds.

BACKGROUND: Tiered trauma triage systems have resulted in a significant mortality reduction, but models have remained unchanged. The aim of this study was to develop and test an artificial intelligence algorithm to predict critical care resource utilization. METHODS: We queried the ACS-TQIP 2017-18 database for truncal gunshot wounds(GSW). An information-aware deep neural network (DNN-IAD) model was trained to predict ICU admission and need for mechanical ventilation (MV). Input variables included demographics, comorbidities, vital signs, and external injuries. The model's performance was assessed using the area under receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). RESULTS: For the ICU admission analysis, we included 39,916 patients. For the MV need analysis, 39,591 patients were included. Median (IQR) age was 27 (22,36). AUROC and AUPRC for predicting ICU need were 84.8 ± 0.5 and 75.4 ± 0.5, and the AUROC and AUPRC for MV need were 86.8 ± 0.5 and 72.5 ± 0.6. CONCLUSIONS: Our model predicts hospital utilization outcomes in patients with truncal GSW with high accuracy, allowing early resource mobilization and rapid triage decisions in hospitals with capacity issues and austere environments.

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.

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.

Information Aware max-norm Dirichlet networks for predictive uncertainty estimation.

Precise estimation of uncertainty in predictions for AI systems is a critical factor in ensuring trust and safety. Deep neural networks trained with a conventional method are prone to over-confident predictions. In contrast to Bayesian neural networks that learn approximate distributions on weights to infer prediction confidence, we propose a novel method, Information Aware Dirichlet networks, that learn an explicit Dirichlet prior distribution on predictive distributions by minimizing a bound on the expected max norm of the prediction error and penalizing information associated with incorrect outcomes. Properties of the new cost function are derived to indicate how improved uncertainty estimation is achieved. Experiments using real datasets show that our technique outperforms, by a large margin, state-of-the-art neural networks for estimating within-distribution and out-of-distribution uncertainty, and detecting adversarial examples.

Low-dose chronic prenatal alcohol exposure abolishes the pro-cognitive effects of angiotensin IV.

Prenatal ethanol exposure (PAE) in humans results in a spectrum of disorders including deficits in learning and memory. Animal models to date have typically used high ethanol doses but have not identified the biochemical changes underlying the cognitive deficit. This study used treatment of mouse breeding harems with 5% ethanol via drinking water throughout pregnancy and lactation and explored the behavioural consequences in the progeny at 3-6 months of age using the open field test, novel object recognition test and elevated plus maze to measure anxiety and memory consolidation. The effects of angiotensin IV on behaviour of the progeny were also determined. The results indicated that PAE increased anxiety-like behaviour as determined in the open field test in male but not female progeny. In control animals, angiotensin IV enhanced memory consolidation in males, but this effect was abolished by PAE. The abolition of the pro-cognitive effect of angiotensin IV was not a consequence of increased anxiety, and there was some evidence of a long-lasting anxiolytic effect of angiotensin IV in the male PAE progeny. These results suggest that PAE may act via alteration of the actions of the brain renin-angiotensin system to impair memory consolidation, but these effects may be partially sex-dependent.