Multidimensional machine learning models predicting outcomes after trauma

Dimitrios Moris; Ricardo Henao; Hannah Hensman; Linda Stempora; Scott Chasse; Seth Schobel; Christopher J Dente; Allan D Kirk; Eric Elster

doi:10.1016/j.surg.2022.08.007

Multidimensional machine learning models predicting outcomes after trauma

Surgery. 2022 Dec;172(6):1851-1859. doi: 10.1016/j.surg.2022.08.007. Epub 2022 Sep 16.

Authors

Dimitrios Moris¹, Ricardo Henao², Hannah Hensman³, Linda Stempora⁴, Scott Chasse⁴, Seth Schobel⁵, Christopher J Dente⁶, Allan D Kirk⁴, Eric Elster⁷

Affiliations

¹ Medical Center, Duke University Durham, NC. Electronic address: dimitrios.moris@duke.edu.
² School of Medicine, Duke University Durham, NC.
³ DecisionQ, Arlington, VA; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.
⁴ Medical Center, Duke University Durham, NC; Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD.
⁵ Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD; Henry M. Jackson Foundation for the Advancement of Military Medicine, Inc, Bethesda, MD.
⁶ Department of Surgery, Emory University, Atlanta, GA.
⁷ Surgical Critical Care Initiative, Department of Surgery, Uniformed Services University of the Health Sciences; Bethesda, MD; Walter Reed National Military Medical Center, Bethesda, MD.

PMID: 36116976
DOI: 10.1016/j.surg.2022.08.007

Abstract

Background: An emerging body of literature supports the role of individualized prognostic tools to guide the management of patients after trauma. The aim of this study was to develop advanced modeling tools from multidimensional data sources, including immunological analytes and clinical and administrative data, to predict outcomes in trauma patients.

Methods: This was a prospective study of trauma patients at Level 1 centers from 2015 to 2019. Clinical, flow cytometry, and serum cytokine data were collected within 48 hours of admission. Sparse logistic regression models were developed, jointly selecting predictors and estimating the risk of ventilator-associated pneumonia, acute kidney injury, complicated disposition (death, rehabilitation, or nursing facility), and return to the operating room. Model parameters (regularization controlling model sparsity) and performance estimation were obtained via nested leave-one-out cross-validation.

Results: A total of 179 patients were included. The incidences of ventilator-associated pneumonia, acute kidney injury, complicated disposition, and return to the operating room were 17.7%, 28.8%, 22.5%, and 12.3%, respectively. Regarding extensive resource use, 30.7% of patients had prolonged intensive care unit stay, 73.2% had prolonged length of stay, and 23.5% had need for prolonged ventilatory support. The models were developed and cross-validated for ventilator-associated pneumonia, acute kidney injury, complicated dispositions, and return to the operating room, yielding predictive areas under the curve from 0.70 to 0.91. Each model derived its optimal predictive value by combining clinical, administrative, and immunological analyte data.

Conclusion: Clinical, immunological, and administrative data can be combined to predict post-traumatic outcomes and resource use. Multidimensional machine learning modeling can identify trauma patients with complicated clinical trajectories and high resource needs.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Acute Kidney Injury* / diagnosis
Acute Kidney Injury* / etiology
Humans
Logistic Models
Machine Learning
Pneumonia, Ventilator-Associated* / diagnosis
Pneumonia, Ventilator-Associated* / epidemiology
Pneumonia, Ventilator-Associated* / etiology
Prospective Studies
Retrospective Studies