Use of Machine Learning to Predict Onset of NAFLD in an All-Comers Cohort-Development and Validation in 2 Large Asian Cohorts

Overview

Journal Gastro Hep Adv

Specialty Gastroenterology

Date 2024 Sep 23

PMID 39309369

Authors

Daniel Yan Zheng Lim

Goh Eun Chung

Pei Hua Cher

Ramasamy Chockalingam Jr

Won Kim

Chee Kiat Tan

Affiliations

Soon will be listed here.

Abstract

Background And Aims: Nonalcoholic fatty liver disease (NAFLD) is one of the most common liver diseases. There are no universally accepted models that accurately predict time to onset of NAFLD. Machine learning (ML) models may allow prediction of such time-to-event (ie, survival) outcomes. This study aims to develop and independently validate ML-derived models to allow personalized prediction of time to onset of NAFLD in individuals who have no NAFLD at baseline.

Methods: The development dataset comprised 25,599 individuals from a South Korean NAFLD registry. A random 70:30 split divided it into training and internal validation sets. ML survival models (random survival forest, extra survival trees) were fitted, with time to NAFLD diagnosis in months as the target variable and routine anthropometric and laboratory parameters as predictors. The independent validation dataset comprised 16,173 individuals from a Chinese open dataset. Models were evaluated using the concordance index (c-index) and Brier score on both the internal and independent validation sets.

Results: The datasets (development vs independent validation) had 1,331,107 vs 543,874 person months of follow-up, NAFLD incidence of 25.7% (6584 individuals) vs 14.4% (2322 individuals), and median time to NAFLD onset of 60 (interquartile range 38-75) vs 24 (interquartile range 13-37) months, respectively. The ML models achieved a good c-index of >0.7 in the validation cohort-random survival forest 0.751 (95% confidence interval 0.742-0.759), extra survival trees 0.752 (95% confidence interval 0.744-0.762).

Conclusion: ML models can predict time-to-onset of NAFLD based on routine patient data. They can be used by clinicians to deliver personalized predictions to patients, which may facilitate patient counseling and clinical decision making on interval imaging timing.

References

Sanyal D, Mukherjee P, Raychaudhuri M, Ghosh S, Mukherjee S, Chowdhury S . Profile of liver enzymes in non-alcoholic fatty liver disease in patients with impaired glucose tolerance and newly detected untreated type 2 diabetes. Indian J Endocrinol Metab. 2015; 19(5):597-601. PMC: 4566337. DOI: 10.4103/2230-8210.163172. View

Lee C, Choe E, Choi J, Hwang Y, Lee Y, Park B . Health and Prevention Enhancement (H-PEACE): a retrospective, population-based cohort study conducted at the Seoul National University Hospital Gangnam Center, Korea. BMJ Open. 2018; 8(4):e019327. PMC: 5914782. DOI: 10.1136/bmjopen-2017-019327. View

Sun D, Wu S, Liu W, Wang L, Chen Y, Zhang D . Association of low-density lipoprotein cholesterol within the normal range and NAFLD in the non-obese Chinese population: a cross-sectional and longitudinal study. BMJ Open. 2016; 6(12):e013781. PMC: 5168665. DOI: 10.1136/bmjopen-2016-013781. View

Liang Y, Chen H, Liu Y, Hou X, Wei L, Bao Y . Association of MAFLD With Diabetes, Chronic Kidney Disease, and Cardiovascular Disease: A 4.6-Year Cohort Study in China. J Clin Endocrinol Metab. 2021; 107(1):88-97. PMC: 8684479. DOI: 10.1210/clinem/dgab641. View

Cheung A, Ahmed A . Nonalcoholic Fatty Liver Disease and Chronic Kidney Disease: A Review of Links and Risks. Clin Exp Gastroenterol. 2021; 14:457-465. PMC: 8607580. DOI: 10.2147/CEG.S226130. View

Yip T, Ma A, Wong V, Tse Y, Chan H, Yuen P . Laboratory parameter-based machine learning model for excluding non-alcoholic fatty liver disease (NAFLD) in the general population. Aliment Pharmacol Ther. 2017; 46(4):447-456. DOI: 10.1111/apt.14172. View

Darmawan G, Hamijoyo L, Hasan I . Association between Serum Uric Acid and Non-Alcoholic Fatty Liver Disease: A Meta-Analysis. Acta Med Indones. 2017; 49(2):136-147. View

Fracanzani A, Petta S, Lombardi R, Pisano G, Russello M, Consonni D . Liver and Cardiovascular Damage in Patients With Lean Nonalcoholic Fatty Liver Disease, and Association With Visceral Obesity. Clin Gastroenterol Hepatol. 2017; 15(10):1604-1611.e1. DOI: 10.1016/j.cgh.2017.04.045. View

Wong S, Ting Y, Chan W . Epidemiology of non-alcoholic fatty liver disease-related hepatocellular carcinoma and its implications. JGH Open. 2018; 2(5):235-241. PMC: 6206984. DOI: 10.1002/jgh3.12070. View

10.

Lee J, Kim D, Kim H, Lee C, Yang J, Kim W . Hepatic steatosis index: a simple screening tool reflecting nonalcoholic fatty liver disease. Dig Liver Dis. 2009; 42(7):503-8. DOI: 10.1016/j.dld.2009.08.002. View

11.

Hagstrom H, Nasr P, Ekstedt M, Hammar U, Stal P, Hultcrantz R . Risk for development of severe liver disease in lean patients with nonalcoholic fatty liver disease: A long-term follow-up study. Hepatol Commun. 2018; 2(1):48-57. PMC: 5776871. DOI: 10.1002/hep4.1124. View

12.

Goldman O, Ben-Assuli O, Rogowski O, Zeltser D, Shapira I, Berliner S . Non-alcoholic Fatty Liver and Liver Fibrosis Predictive Analytics: Risk Prediction and Machine Learning Techniques for Improved Preventive Medicine. J Med Syst. 2021; 45(2):22. DOI: 10.1007/s10916-020-01693-5. View

13.

Bulusu S, Sharma M . What does serum γ-glutamyltransferase tell us as a cardiometabolic risk marker?. Ann Clin Biochem. 2015; 53(Pt 3):312-32. DOI: 10.1177/0004563215597010. View

14.

Younossi Z, Otgonsuren M, Henry L, Venkatesan C, Mishra A, Erario M . Association of nonalcoholic fatty liver disease (NAFLD) with hepatocellular carcinoma (HCC) in the United States from 2004 to 2009. Hepatology. 2015; 62(6):1723-30. DOI: 10.1002/hep.28123. View

15.

Pan X, Xie X, Peng H, Cai X, Li H, Hong Q . Risk Prediction for Non-alcoholic Fatty Liver Disease Based on Biochemical and Dietary Variables in a Chinese Han Population. Front Public Health. 2020; 8:220. PMC: 7346601. DOI: 10.3389/fpubh.2020.00220. View

16.

Wang J, Tang Y, Peng K, Liu H, Xu J . Development and validation of a nomogram for predicting nonalcoholic fatty liver disease in the non-obese Chinese population. Am J Transl Res. 2020; 12(10):6149-6159. PMC: 7653603. View

17.

Chalasani N, Younossi Z, Lavine J, Charlton M, Cusi K, Rinella M . The diagnosis and management of nonalcoholic fatty liver disease: Practice guidance from the American Association for the Study of Liver Diseases. Hepatology. 2017; 67(1):328-357. DOI: 10.1002/hep.29367. View

18.

Ma H, Xu C, Shen Z, Yu C, Li Y . Application of Machine Learning Techniques for Clinical Predictive Modeling: A Cross-Sectional Study on Nonalcoholic Fatty Liver Disease in China. Biomed Res Int. 2018; 2018:4304376. PMC: 6192080. DOI: 10.1155/2018/4304376. View

19.

Fujii H, Doi H, Ko T, Fukuma T, Kadono T, Asaeda K . Frequently abnormal serum gamma-glutamyl transferase activity is associated with future development of fatty liver: a retrospective cohort study. BMC Gastroenterol. 2020; 20(1):217. PMC: 7350574. DOI: 10.1186/s12876-020-01369-x. View