Deep-Learning-Based Survival Prediction of Patients in Coronary Care Units

Abstract

Background: A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability. We collected information on patients with various diseases in coronary care units (CCUs) from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The purpose of this study was to use this information to construct a neural-network model based on deep learning to predict the survival probabilities of patients with conditions that are common in CCUs.

Method: We collected information on patients in the United States with five common diseases in CCUs from 2001 to 2012. We randomly divided the patients into a training cohort and a testing cohort at a ratio of 7 : 3 and applied a survival prediction method based on deep learning to predict their survival probability. We compared our model with the Cox proportional-hazards regression (CPH) model and used the concordance indexes (C-indexes), receiver operating characteristic (ROC) curve, and calibration plots to evaluate the predictive performance of the model.

Results: The 3,388 CCU patients included in the study were randomly divided into 2,371 in the training cohort and 1,017 in the testing cohort. The stepwise regression results showed that the important factors affecting patient survival were the type of disease, age, race, anion gap, glucose, neutrophils, white blood cells, potassium, creatine kinase, and blood urea nitrogen (P < 0.05). We used the training cohort to construct a deep-learning model, for which the C-index was 0.833, or about 5% higher than that for the CPH model (0.786). The C-index of the deep-learning model for the test cohort was 0.822, which was also higher than that for the CPH model (0.782). The areas under the ROC curve for the 28-day, 90-day, and 1-year survival probabilities were 0.875, 0.865, and 0.874, respectively, in the deep-learning model, respectively, and 0.830, 0.843, and 0.806 in the CPH model. These values indicate that the survival analysis model based on deep learning is better than the traditional CPH model in predicting the survival of CCU patients.

Conclusion: A survival prediction model based on deep learning has higher accuracy than the CPH model in predicting the survival of CCU patients, and it also has a better discrimination ability.

Figure 1

Work flow overview.

Figure 2

Neural network model structure diagram.

Figure 3

Kaplan-Meier curve of training and testing sets. There was no statistically significant difference between the survival of training and testing sets in the log-rank test (P = 0.73).

Figure 4

The loss and C-index change process diagram of training and testing.

Figure 5

Calibration plot. Calibration plot of the (a) CPH model and (b) deep learning model for 28-day, 90-day, and 1-year prediction in testing cohort population.

Figure 6

ROC plot. Comparison of ROC between the CPH model and the deep learning model in (a) 28 days, (b) 90 days, and (c) 1 year in testing cohort population.