Background Tools to assist clinicians in predicting pneumonia could lead to a significant decline in morbidity. Therefore, we sought to develop a model in combat trauma patients for identifying those at highest risk of pneumonia. Methods This was a retrospective study of 73 primarily blast‐injured casualties with combat extremity wounds. Binary classification models for pneumonia prediction were developed with measurements of injury severity from the Abbreviated Injury Scale (AIS), transfusion blood products received before arrival at Walter Reed National Military Medical Center (WRNMMC), and serum protein levels. Predictive models were generated with leave‐one‐out‐cross‐validation using the variable selection method of backward elimination (BE) and the machine learning algorithms of random forests (RF) and logistic regression (LR). BE was attempted with two predictor sets: (1) all variables and (2) serum proteins alone. Results Incidence of pneumonia was 12% (n = 9). Different variable sets were produced by BE when considering all variables and just serum proteins alone. BE selected the variables ISS, AIS chest, and cryoprecipitate within the first 24 h following injury for the first predictor set 1 and FGF‐basic, IL‐2R, and IL‐6 for predictor set 2. Using both variable sets, a RF was generated with AUCs of 0.95 and 0.87—both higher than LR algorithms. Conclusion Advanced modeling allowed for the identification of clinical and biomarker data predictive of pneumonia in a cohort of predominantly blast‐injured combat trauma patients. The generalizability of the models developed here will require an external validation dataset.
BACKGROUND Identifying clinical and biomarker profiles of trauma patients may facilitate the creation of models that predict postoperative complications. We sought to determine the utility of modeling for predicting severe sepsis (SS) and organ space infections (OSI) following laparotomy for abdominal trauma. METHODS Clinical and molecular biomarker data were collected prospectively from patients undergoing exploratory laparotomy for abdominal trauma at a Level I trauma center between 2014 and 2017. Machine learning algorithms were used to develop models predicting SS and OSI. Random forest (RF) was performed, and features were selected using backward elimination. The SS model was trained on 117 records and validated using the leave-one-out method on the remaining 15 records. The OSI model was trained on 113 records and validated on the remaining 19. Models were assessed using areas under the curve. RESULTS One hundred thirty-two patients were included (median age, 30 years [23–42 years], 68.9% penetrating injury, median Injury Severity Score of 18 [10–27]). Of these, 10.6% (14 of 132) developed SS and 13.6% (18 of 132) developed OSI. The final RF model resulted in five variables for SS (Penetrating Abdominal Trauma Index, serum epidermal growth factor, monocyte chemoattractant protein-1, interleukin-6, and eotaxin) and four variables for OSI (Penetrating Abdominal Trauma Index, serum epidermal growth factor, monocyte chemoattractant protein-1, and interleukin-8). The RF models predicted SS and OSI with areas under the curve of 0.798 and 0.774, respectively. CONCLUSION Random forests with RFE can help identify clinical and biomarker profiles predictive of SS and OSI after trauma laparotomy. Once validated, these models could be used as clinical decision support tools for earlier detection and treatment of infectious complications following injury. LEVEL OF EVIDENCE Prognostic, level III.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.