Assessment of Classification Models and Relevant Features on Nonalcoholic Steatohepatitis Using Random Forest

Abstract

Nonalcoholic fatty liver disease (NAFLD) is the hepatic manifestation of metabolic syndrome and is the most common cause of chronic liver disease in developed countries. Certain conditions, including mild inflammation biomarkers, dyslipidemia, and insulin resistance, can trigger a progression to nonalcoholic steatohepatitis (NASH), a condition characterized by inflammation and liver cell damage. We demonstrate the usefulness of machine learning with a case study to analyze the most important features in random forest (RF) models for predicting patients at risk of developing NASH. We collected data from patients who attended the Cardiovascular Risk Unit of Mostoles University Hospital (Madrid, Spain) from 2005 to 2021. We reviewed electronic health records to assess the presence of NASH, which was used as the outcome. We chose RF as the algorithm to develop six models using different pre-processing strategies. The performance metrics was evaluated to choose an optimized model. Finally, several interpretability techniques, such as feature importance, contribution of each feature to predictions, and partial dependence plots, were used to understand and explain the model to help obtain a better understanding of machine learning-based predictions. In total, 1525 patients met the inclusion criteria. The mean age was 57.3 years, and 507 patients had NASH (prevalence of 33.2%). Filter methods (the chi-square and Mann–Whitney–Wilcoxon tests) did not produce additional insight in terms of interactions, contributions, or relationships among variables and their outcomes. The random forest model correctly classified patients with NASH to an accuracy of 0.87 in the best model and to 0.79 in the worst one. Four features were the most relevant: insulin resistance, ferritin, serum levels of insulin, and triglycerides. The contribution of each feature was assessed via partial dependence plots. Random forest-based modeling demonstrated that machine learning can be used to improve interpretability, produce understanding of the modeled behavior, and demonstrate how far certain features can contribute to predictions.

Identification and Predictive Value of Risk Factors for Mortality Due to Listeria monocytogenes Infection: Use of Machine Learning with a Nationwide Administrative Data Set

“…We consider RF an excellent, reliable, stable, and robust nonlinear classifier compared to conventional approaches. RF can address nonlinearity, as has been demonstrated previously [34,53]. In our study, RF not only performed fairly well but also selected some interesting features as most relevant to Listeria-related mortality.…”

“…We used the RF implementation in the R package randomForest [31]. Several biomedical publications, such as ones on steatohepatitis, have shown that RF is an excellent, reliable, stable, and robust nonlinear classifier compared to other machine-learning classifiers [32][33][34]. RF works by building many decision trees in which features predict a categorical outcome (e.g., mortality).…”

Artificial intelligence in nonalcoholic fatty liver disease

“…Serum ferritin and insulin were selected with high sensitivity and specificity using the LASSO approach with a sensitivity of 70%, specificity of 79%, and area under the curve of 0.79 [16]. Another study by Garcia-Carretero et al used random forest (RF) models for predicting patients at risk of developing NASH in 1525 patients [15]. The electronic health records were used to assess the presence of NASH.…”

“…Four features that were the most relevant included insulin resistance, ferritin, serum levels of insulin, and triglycerides. Random forest-based modeling demonstrated that machine learning could be used to improve interpretability, produce an understanding of the modeled behavior, and demonstrate how far certain features can contribute to predictions [15].…”

DataSheet2.CDX

“…Insulin resistance (IR) is defined as an impaired biological response to insulin stimulation of target tissues mainly including the liver, muscle, and adipose tissue. Insulin resistance syndrome, also known as metabolic syndrome, is associated with a broad spectrum of diseases such as obesity, hyperglycemia, hypertension, dyslipidemia, non-alcoholic fatty liver disease, cardiovascular disease, polycystic ovarian syndrome, and type 2 diabetes mellitus (Allahbadia and Merchant, 2008;Willard et al, 2016;Cortés-Rojo et al, 2020;García-Carretero et al, 2021). Insulin resistance is mainly related to excess body fat and also genetic causes, which affects as many as one in three Americans and becomes a tremendous burden for the healthcare system of the United States (Balasubramanyam, 2006;McCarthy, 2014;Sharma et al, 2019;Rajesh and Sarkar, 2021).…”