Random forest modeling can predict infectious complications following trauma laparotomy

Abstract

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. 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. 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. 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. Prognostic, level III.