Science fiction or clinical reality: a review of the applications of artificial intelligence along the continuum of trauma care

Abstract

Artificial intelligence (AI) and machine learning describe a broad range of algorithm types that can be trained based on datasets to make predictions. The increasing sophistication of AI has created new opportunities to apply these algorithms within within trauma care. Our paper overviews the current uses of AI along the continuum of trauma care, including injury prediction, triage, emergency department volume, assessment, and outcomes. Starting at the point of injury, algorithms are being used to predict severity of motor vehicle crashes, which can help inform emergency responses. Once on the scene, AI can be used to help emergency services triage patients remotely in order to inform transfer location and urgency. For the receiving hospital, these tools can be used to predict trauma volumes in the emergency department to help allocate appropriate staffing. After patient arrival to hospital, these algorithms not only can help to predict injury severity, which can inform decision-making, but also predict patient outcomes to help trauma teams anticipate patient trajectory. Overall, these tools have the capability to transform trauma care. AI is still nascent within the trauma surgery sphere, but this body of the literature shows that this technology has vast potential. AI-based predictive tools in trauma need to be explored further through prospective trials and clinical validation of algorithms.

Current knowledge and availability of machine learning across the spectrum of trauma science

“…Recent works on Machine Learning based decision-support in trauma stratify into data source, predictors (so-called features ), Machine Learning approaches, predicted outcomes (outputs), the timing of the outcome, and availability of the features [6 ▪▪ ,7 ▪▪ ].…”

“…stepwise, Poisson, Cox, General Linear Models), including logistic regression (least absolute shrinkage, Ridge, Elastic Net regression) over neural, artificial or deep networks to tree or kernel-based methods, Gradient Boosting, Support Vector Machines, or Bayes Networks. Network-based approaches implemented feed-forward and deep neural network, multilayer perceptions, etc., tree-based approaches included random-forest or decision trees [6 ▪▪ ,7 ▪▪ ,8]. Among this spectrum, aggregation such as Random Forest and Gradient Boosting are considered more reliable [8].…”

“…Over the last 15 years, technological advances and increased computational capacity at lower cost, facilitated exploitation of complex mathematical theories. These advances triggered the exploration of algorithm-based strategies for enhanced real-time decision-support and prediction algorithms [6 ▪▪ ,7 ▪▪ ]. These algorithms correspond to what is colloquially termed Artificial Intelligence and correspond to a computational process able to perform a task that is usually the result of a human cognitive process.…”

Concentration training of MR shooting game plus AI tech on college students

“…The Internet and AI technology are two essential products in the information age. Since birth, they have created and realized many possibilities in various fields [9][10][11][12][13][14][15][16][17][18] . As an excellent tool to improve the concentration of college students, MR shooting games will produce tremendous superimposed efficiency under the blessing of Internet + AI technology and better serve college students 19 .…”

Automated volumetric evaluation of intracranial compartments and cerebrospinal fluid distribution on emergency trauma head CT scans to quantify mass effect

“…The growing demand for CT to detect IC hemorrhages and assess mass effect can be addressed through the use of artificial intelligence (AI) and machine learning ( Chang et al, 2016 ; Heit et al, 2017 ; Raju et al, 2020 ; Brossard et al, 2021 ; Colasurdo et al, 2022 ). They are utilized in emergency care for various purposes, including triage, injury prediction, and outcome evaluation ( Hunter et al, 2023 ). The ongoing efforts aim to automate lesion identification and segmentation, and assess CSF reserve ( Monteiro et al, 2020 ; Colasurdo et al, 2022 ; Schmitt et al, 2022 ; Hunter et al, 2023 ; Yamada et al, 2023 ).…”