Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database

Abstract

BACKGROUND Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease, affecting over 30% of the United States population. Early patient identification using a simple method is highly desirable. AIM To create machine learning models for predicting NAFLD in the general United States population. METHODS Using the NHANES 1988-1994. Thirty NAFLD-related factors were included. The dataset was divided into the training (70%) and testing (30%) datasets. Twenty-four machine learning algorithms were applied to the training dataset. The best-performing models and another interpretable model ( i.e. , coarse trees) were tested using the testing dataset. RESULTS There were 3235 participants ( n = 3235) that met the inclusion criteria. In the training phase, the ensemble of random undersampling (RUS) boosted trees had the highest F1 (0.53). In the testing phase, we compared selective machine learning models and NAFLD indices. Based on F1, the ensemble of RUS boosted trees remained the top performer (accuracy 71.1% and F1 0.56) followed by the fatty liver index (accuracy 68.8% and F1 0.52). A simple model (coarse trees) had an accuracy of 74.9% and an F1 of 0.33. CONCLUSION Not every machine learning model is complex. Using a simpler model such as coarse trees, we can create an interpretable model for predicting NAFLD with only two predictors: fasting C-peptide and waist circumference. Although the simpler model does not have the best performance, its simplicity is useful in clinical practice.

Machine-Learning Algorithm for Predicting Fatty Liver Disease in a Taiwanese Population

“…Our findings were consistent with the findings of Atsawarungruangkit et al [ 13 ], who demonstrated the superiority of a machine-learning model over the fatty liver index in predicting the presence of fatty liver disease, although the machine model utilized more features than the fatty liver index did and could not be calculated with a calculator. The calculation of the fatty liver index was also not simple and required the use of a spreadsheet or an internet app that would be similar to the use of a machine model.…”

“…Several ML techniques, such as logistic regression (LR), random forest (RF), artificial neural networks (ANNs), support vector machines, and extreme gradient boosting (xgBoost), show promise in improving predictions compared with conventional risk scoring systems. There are several previous studies that used ML methods to show a higher diagnostic value for the presence of fatty liver disease with clinical variables [ 9 , 10 , 11 , 12 , 13 , 14 , 15 ]. However, these studies utilized a limited number of datasets, and most of them did not examine with an additional testing dataset for validation.…”

A dynamic machine learning model for prediction of NAFLD in a health checkup population: A longitudinal study

“…As the end product of purine metabolism, high levels of serum uric acid could induce fat accumulation and then lead to the development of fatty liver [ 36 ]. Waist circumference was also a significant predictor of NAFLD, consistent finding has been revealed in previous studies [ 7 , 37 ]. Furthermore, our results also showed that direct bilirubin levels from five or more years ago can have a significant and continuous effect on the development of NAFLD, which may hint at its long-term effect on the onset of the disease.…”

“…As expected, more and more research has been conducted to solve such issues. However, previous related studies were mostly cross-sectional and mainly focused on the development of diagnostic prediction models, which failed to determine causal relationships or provide early risk probabilities sometime before the confirmed diagnosis of NAFLD [ [4] , [5] , [6] ]. Besides, most existing studies were based on conventional machine learning models with a single measurement of variables [ 5 , 7 , 8 ], ignoring the variation tendency contained in multiple measurements of data.…”

Identifying Patients with Nonalcoholic Fatty Liver Disease in Primary Care: How and for What Benefit?

“…The key risk factors mentioned in the guidelines include T2D, obesity, dyslipidemia, hypertriglyceridemia, elevated ALT and gamma-glutamyl transferase, and male sex [ 31 ]. Recent machine learning studies have verified and identified several clinical characteristics that are significant predictors of NAFLD, including male sex and increased waist circumference, age, hemoglobin A1c (HbA1c), BMI, AST, alkaline phosphatase, high-density lipoprotein (HDL)-cholesterol, triglycerides, and diastolic blood pressure [ 51 , 52 ].…”