In-hospital Mortality Prediction among Patients with Fractures of Pelvis and Acetabulum in Intensive Care Unit: Machine Learning versus Conventional System

Abstract

BackgroundFractures of pelvis and/or Acetabulum are leading risks of death worldwide. However, the capability of in-hospital mortality prediction by conventional system is so far limited. Here, we hypothesis that the use of machine learning (ML) algorithms could provide better performance of prediction than the traditional scoring system Simple Acute Physiologic Score (SAPS) II for patients with pelvic and acetabular trauma in intensive care unit (ICU).MethodsWe developed customized mortality prediction models with ML techniques based on MIMIC-III, an open access de-defined database consisting of data from more than 25,000 patients who were admitted to the Beth Israel Deaconess Medical Center (BIDMC). 307 patients were enrolled with an ICD-9 diagnosis of pelvic, acetabular or combined pelvic and acetabular fractures and who had an ICU stay more than 72 hours. ML models including decision tree, logistic regression and random forest were established by using the SAPS II features from the first 72 hours after ICU admission and the traditional first-24-hours features were used to build respective control models. We evaluated and made a comparison of each model’s performance through the area under the receiver-operating characteristic curve (AUROC). Feature importance method was used to visualize top risk factors for disease mortality.ResultsAll the ML models outperformed the traditional scoring system SAPS II (AUROC=0.73), among which the best fitted random forest model had the supreme performance (AUROC of 0.90). With the use of evolution of physiological features over time rather than 24-hours snapshots, all the ML models performed better than respective controls. Age remained the top of feature importance for all classifiers. Age, BUN (minimum value on day 2), and BUN (maximum value on day 3) were the top 3 predictor variables in the optimal random forest experiment model. In the best decision tree model, the top 3 risk factors, in decreasing order of contribution, were age, the lowest systolic blood pressure on day 1 and the same value on day 3.ConclusionThe results suggested that mortality modeling with ML techniques could aid in better performance of prediction for models in the context of pelvic and acetabular trauma and potentially support decision-making for orthopedics and ICU practitioners.