Predicting mortality among patients with liver cirrhosis in electronic health records with machine learning

Abstract

Objective Liver cirrhosis is a leading cause of death and effects millions of people in the United States. Early mortality prediction among patients with cirrhosis might give healthcare providers more opportunity to effectively treat the condition. We hypothesized that laboratory test results and other related diagnoses would be associated with mortality in this population. Our another assumption was that a deep learning model could outperform the current Model for End Stage Liver disease (MELD) score in predicting mortality. Materials and methods We utilized electronic health record data from 34,575 patients with a diagnosis of cirrhosis from a large medical center to study associations with mortality. Three time-windows of mortality (365 days, 180 days and 90 days) and two cases with different number of variables (all 41 available variables and 4 variables in MELD-NA) were studied. Missing values were imputed using multiple imputation for continuous variables and mode for categorical variables. Deep learning and machine learning algorithms, i.e., deep neural networks (DNN), random forest (RF) and logistic regression (LR) were employed to study the associations between baseline features such as laboratory measurements and diagnoses for each time window by 5-fold cross validation method. Metrics such as area under the receiver operating curve (AUC), overall accuracy, sensitivity, and specificity were used to evaluate models. Results Performance of models comprising all variables outperformed those with 4 MELD-NA variables for all prediction cases and the DNN model outperformed the LR and RF models. For example, the DNN model achieved an AUC of 0.88, 0.86, and 0.85 for 90, 180, and 365-day mortality respectively as compared to the MELD score, which resulted in corresponding AUCs of 0.81, 0.79, and 0.76 for the same instances. The DNN and LR models had a significantly better f1 score compared to MELD at all time points examined. Conclusion Other variables such as alkaline phosphatase, alanine aminotransferase, and hemoglobin were also top informative features besides the 4 MELD-Na variables. Machine learning and deep learning models outperformed the current standard of risk prediction among patients with cirrhosis. Advanced informatics techniques showed promise for risk prediction in patients with cirrhosis.

The computer will see you now: Prediction of long‐term survival in patients with cirrhosis

“…Recent studies have used machine learning to predict mortality. [ 2–4 ] However, the results are not consistently supportive, even in the short term. For example, a study examining the multicenter North American Consortium for the Study of End‐Stage Liver Disease cohort did not identify any significant difference between AI‐based models and MELD‐Na in a prediction of 90‐day mortality.…”

“Beyond MELD” – Emerging strategies and technologies for improving mortality prediction, organ allocation and outcomes in liver transplantation

“…[89][90][91] Deep neural networks, characterised by multiple layers between the input and output layers, 91 have been utilised for longitudinal analyses of EHR data to predict outcomes of cirrhosis. 92 In liver transplant, ML methodologies have been used to explore waitlist mortality and organ allocation. 87,88,[92][93][94][95][96] One of the first ML models in transplant hepatology developed in 2003 was an ANN model to predict 1-year mortality in a cohort of 92 patients.…”

“…92 In liver transplant, ML methodologies have been used to explore waitlist mortality and organ allocation. 87,88,[92][93][94][95][96] One of the first ML models in transplant hepatology developed in 2003 was an ANN model to predict 1-year mortality in a cohort of 92 patients. While limited in scale, this ANN model outperformed logistic regression and the Child-Pugh score.…”

Therapeutic advances in alcohol-associated hepatitis

“…An example is the MELD score, which was generated by logistic regressionin recent studies, the predictive capabilities of the MELD score have been refined using additional non-biased variables. [67][68][69] Similar predictive analytics have recently been used to help clinicians distinguish differential diagnoses such as cholangitis from AH. 70 Although these advances are exciting and will continue to improve over the coming years as we generate even larger data sets and better analytic capabilities, most of these have not been definitively able to improve upon traditional clinician diagnosis.…”