@article{ref1,
title="The derivation of an ICD-10-based trauma-related mortality model utilizing machine learning",
journal="Journal of trauma and acute care surgery",
year="2021",
author="Tran, Zachary and Zhang, Wenhao and Verma, Arjun and Cook, Alan and Kim, Dennis and Burruss, Sigrid and Ramezani, Ramin and Benharash, Peyman",
volume="ePub",
number="ePub",
pages="ePub-ePub",
abstract="BACKGROUND: Existing mortality prediction models have attempted to quantify injury burden following trauma-related admissions with the most notable being the Injury Severity Score (ISS). Although easy to calculate, it requires additional administrative coding. International Classification of Diseases (ICD)-based models such as the Trauma Mortality Prediction Model (TMPM-ICD10) circumvent these limitations, but they utilize linear modeling which may not adequately capture the intricate relationships of injuries on mortality. Using ICD-10 coding and machine learning algorithms, the present study utilized the National Trauma Data Bank (NTDB) to develop mortality prediction models whose performance was compared to logistic regression, ISS and TMPM-ICD10. <br><br>METHODS: The 2015-2017 NTDB was used to identify adults following trauma-related admissions. Of 8,021 ICD-10 codes, injuries were categorized into 1,495 unique variables. The primary outcome was in-hospital mortality. eXtreme Gradient Boosting (XGBoost), a machine learning technique that uses iterations of decision trees, was used to develop mortality models. Model discrimination was compared to logistic regression, ISS and TMPM-ICD10 using receiver operating characteristic (ROC) and probabilistic accuracy with calibration curves. <br><br>RESULTS: Of 1,611,063 patients, 54,870 (3.41%) experienced in-hospital mortality. Compared to those who survived, those who died more frequently suffered from penetrating trauma and had a greater number of injuries. The XGBoost model exhibited superior ROC (0.863 (95% CI: 0.862-0.864) compared to logistic regression (0.845 (95% CI: 0.844-0.846)), ISS (0.828 (95% CI: 0.827-0.829)) and TMPM-ICD10 (0.861 (95% CI: 0.860-0.862)) (all p<0.001). Importantly, the ML model also had significantly improved calibration compared to other methodologies (XGBoost: coefficient of determination (R2) = 0.993, logistic regression: R2 = 0.981, ISS: R2 = 0.649, TMPM-ICD10: R2 = 0.830). <br><br>CONCLUSIONS: Machine learning models using XGBoost demonstrated superior performance and calibration compared to logistic regression, ISS and TMPM-ICD10. Such approaches in quantifying injury severity may improve its utility in mortality prognostication, quality improvement and trauma research. LEVEL OF EVIDENCE: Level III.<p /> <p>Language: en</p>",
language="en",
issn="2163-0755",
doi="10.1097/TA.0000000000003416",
url="http://dx.doi.org/10.1097/TA.0000000000003416"
}