Retrospective Study
Copyright ©The Author(s) 2021. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Hepatol. Oct 27, 2021; 13(10): 1417-1427
Published online Oct 27, 2021. doi: 10.4254/wjh.v13.i10.1417
Machine learning models for predicting non-alcoholic fatty liver disease in the general United States population: NHANES database
Amporn Atsawarungruangkit, Passisd Laoveeravat, Kittichai Promrat
Amporn Atsawarungruangkit, Kittichai Promrat, Division of Gastroenterology, Warren Alpert Medical School, Brown University, Providence, RI 02903, United States
Passisd Laoveeravat, Division of Digestive Diseases and Nutrition, University of Kentucky College of Medicine, Lexington, KY 40536, United States
Kittichai Promrat, Division of Gastroenterology and Hepatology, Providence VA Medical Center, Providence, RI 02908, United States
Author contributions: Atsawarungruangkit A and Laoveeravat P contributed equally to this work including study design, data analysis, result interpretation, and manuscript writing; Promrat K critically revised the manuscript and provided supervision.
Institutional review board statement: The National Health and Nutrition Examination Survey protocol was approved by the National Center for Health Statistics Research Ethics Review Board (Hyattsville, MD, United States).
Informed consent statement: In NHANES III, the consent form was signed by participants in the survey.
Conflict-of-interest statement: No conflict of interest exists.
Data sharing statement: The dataset used in this manuscript is NHANES III, which is publicly available dataset.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Amporn Atsawarungruangkit, MD, Academic Fellow, Instructor, Research Fellow, Division of Gastroenterology, Warren Alpert Medical School, Brown University, 593 Eddy Street, POB 240, Providence, RI 02903, United States. amporn_atsawarungruangkit@brown.edu
Received: March 7, 2021
Peer-review started: March 7, 2021
First decision: May 2, 2021
Revised: May 11, 2021
Accepted: September 19, 2021
Article in press: September 19, 2021
Published online: October 27, 2021
Processing time: 229 Days and 11.1 Hours
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.

Keywords: Artificial intelligence; Machine learning; Non-alcoholic fatty liver disease; Fatty liver; United States population; NHANES

Core Tip: A simple method with a good accuracy for identifying patients with non-alcoholic fatty liver disease is highly desirable. Among 24 machine learning models, the ensemble of random undersampling boosted trees was the top performer (accuracy 71.1% and F1 0.56). A simple model (coarse trees) with only two predictors (fasting C-peptide and waist circumference) had an accuracy of 74.9% and an F1 of 0.33. Not every machine learning model is complex. Using a simple model such as coarse trees, physicians can easily integrate machine learning model into their practice without any software implementation.