Decision support by machine learning systems for acute management of severely injured patients: A systematic review

David Baur; Tobias Gehlen; Julian Scherer; David Alexander Back; Serafeim Tsitsilonis; Koroush Kabir; Georg Osterhoff

doi:10.3389/fsurg.2022.924810

Decision support by machine learning systems for acute management of severely injured patients: A systematic review

Front Surg. 2022 Oct 10:9:924810. doi: 10.3389/fsurg.2022.924810. eCollection 2022.

Authors

David Baur¹, Tobias Gehlen², Julian Scherer³, David Alexander Back^{2

4}, Serafeim Tsitsilonis², Koroush Kabir⁵, Georg Osterhoff⁶

Affiliations

¹ Department for Orthopedics and Traumatology, University Hospital Leipzig, Leipzig, Germany.
² Center for Musculoskeletal Surgery, Charité University Medicine Berlin, Berlin, Germany.
³ Clinic for Traumatology, University Hospital Zurich, Zurich, Switzerland.
⁴ Clinic for Traumatology and Orthopedics, Bundeswehr Hospital Berlin, Berlin, Germany.
⁵ Department of Orthopaedics and Trauma Surgery, University Hospital Bonn, Bonn, Germany.
⁶ Department for Orthopedics, Traumatology and Plastic Surgery, University Hospital Leipzig, Leipzig, Germany.

Abstract

Introduction: Treating severely injured patients requires numerous critical decisions within short intervals in a highly complex situation. The coordination of a trauma team in this setting has been shown to be associated with multiple procedural errors, even of experienced care teams. Machine learning (ML) is an approach that estimates outcomes based on past experiences and data patterns using a computer-generated algorithm. This systematic review aimed to summarize the existing literature on the value of ML for the initial management of severely injured patients.

Methods: We conducted a systematic review of the literature with the goal of finding all articles describing the use of ML systems in the context of acute management of severely injured patients. MESH search of Pubmed/Medline and Web of Science was conducted. Studies including fewer than 10 patients were excluded. Studies were divided into the following main prediction groups: (1) injury pattern, (2) hemorrhage/need for transfusion, (3) emergency intervention, (4) ICU/length of hospital stay, and (5) mortality.

Results: Thirty-six articles met the inclusion criteria; among these were two prospective and thirty-four retrospective case series. Publication dates ranged from 2000 to 2020 and included 32 different first authors. A total of 18,586,929 patients were included in the prediction models. Mortality was the most represented main prediction group (n = 19). ML models used were artificial neural network ( n = 15), singular vector machine (n = 3), Bayesian network (n = 7), random forest (n = 6), natural language processing (n = 2), stacked ensemble classifier [SuperLearner (SL), n = 3], k-nearest neighbor (n = 1), belief system (n = 1), and sequential minimal optimization (n = 2) models. Thirty articles assessed results as positive, five showed moderate results, and one article described negative results to their implementation of the respective prediction model.

Conclusions: While the majority of articles show a generally positive result with high accuracy and precision, there are several requirements that need to be met to make the implementation of such models in daily clinical work possible. Furthermore, experience in dealing with on-site implementation and more clinical trials are necessary before the implementation of ML techniques in clinical care can become a reality.

Keywords: artificial intelligence; decision support; deep learning; machine learning; neural networks; polytrauma; prediction; trauma.

Publication types

Review