Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. MEDS Public Health and Preventive Medicine
  4. Vol 6, Issue 1, 2026

Constructing a Fatty Liver Prediction Model Based on Physical Examination Data and Machine Learning Algorithm

Download as PDF

DOI: 10.23977/phpm.2026.060101 | Downloads: 5 | Views: 180

Author(s)

Tao Meiyu 1, Huang Jiehong 1, Qin Qingrong 1, Yao Shunhan 1, Li Zi 1, Yao Jianmin 1, Qi Yue 1, Zeng Lanqing 1, Wu Xiangjun 1

Affiliation(s)

1 Health Management Center of Guangxi Medical University Kaiyuan Langdong Hospital, Nanning, 530000, Guangxi, China

Corresponding Author

Wu Xiangjun

ABSTRACT

Fatty liver disease is one of the most common chronic liver diseases and is closely associated with metabolic disorders. Early identification of high-risk populations is essential for prevention and intervention. Based on large-scale physical examination data, this study aimed to identify predictors of fatty liver disease and construct a prediction model using machine learning algorithms. A total of 4,700 individuals who underwent physical examinations at the Health Management Center of Guangxi Medical University Kaiyuan Langdong Hospital from 2020 to 2023 were retrospectively included and divided into a fatty liver group (1,372 cases) and a normal group (3,328 cases) according to abdominal ultrasound results. Demographic characteristics and biochemical indicators, including age, sex, body mass index (BMI), alanine aminotransferase (ALT), uric acid (UA), fasting plasma glucose (FPG), total cholesterol (TC), triglycerides (TG), high-density lipoprotein cholesterol (HDL-C), and low-density lipoprotein cholesterol (LDL-C), were collected. Univariate analysis and multivariate logistic regression were used to identify independent risk factors for fatty liver disease, and five machine learning models, including logistic regression, support vector machine (SVM), random forest, k-nearest neighbors (KNN), and neural network, were constructed to predict fatty liver risk. The predictive performance of each model was evaluated using accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC). The results showed that age, sex, BMI, ALT, UA, FPG, and TG were independent risk factors for fatty liver disease. Among the five models, logistic regression achieved the best performance with an accuracy of 0.7675 and an AUC of 0.7975. A nomogram based on the logistic regression model was further established and showed good calibration and predictive consistency. These findings suggest that a prediction model based on routine physical examination indicators can effectively assess the risk of fatty liver disease and may provide a convenient tool for early screening and risk assessment in health examination populations.

KEYWORDS

Fatty liver; Physical examination data; Machine learning; Logistic regression; Prediction model; Nomogram

CITE THIS PAPER

Tao Meiyu, Huang Jiehong, Qin Qingrong, Yao Shunhan, Li Zi, Yao Jianmin, Qi Yue, Zeng Lanqing, Wu Xiangjun. Constructing a Fatty Liver Prediction Model Based on Physical Examination Data and Machine Learning Algorithm. MEDS Public Health and Preventive Medicine (2026). Vol. 6, No.1, 1-9. DOI: http://dx.doi.org/10.23977/phpm.2026.060101.
 

REFERENCES

[1] Qu, J.C., Qin, J.T., Wang, A.P. and Others. (2024) Study on the correlation between fatty liver index and risk of incident diabetes in different glucose metabolism populations. Chinese Journal of Diabetes Mellitus, 32, 726-730.
[2] Tu, Y., Yang, C.J., Huang, Y. and Others. (2022) A study on the correlation between non-alcoholic fatty liver and cardiovascular diseases. Natural Magazine, 44, 149-154.
[3] Yip, T.C., Fan, J.G. and Wong, V.W. (2023) China's fatty liver crisis: A looming public health emergency. Gastroenterology, 165, 825-827.
[4] Eslam, M., Sarin, S.K., Wong, V.W. and Others. (2020) The Asian Pacific Association for the Study of the Liver clinical practice guidelines for the diagnosis and management of metabolic associated fatty liver disease. Hepatology International, 14, 889-919.
[5] Xu, H., Fang, D., Zhou, W.H. and Others. (2025) A retrospective cohort study on the association between Chinese visceral adiposity index and the risk of fatty liver. Chinese General Practice, 28, 1336-1341, 1366.
[6] Zhao, Q.W., Peng, D.L., Liu, S.S. and Others. (2024) An age-period-cohort effect analysis of liver cancer mortality burden caused by non-alcoholic fatty liver disease in China from 1990 to 2019. Journal of Hepatopancreaticobiliary Surgery, 36, 667-672.
[7] Mu, L. (2024) The clinical significance of ultrasound examination in the diagnosis of fatty liver. China Medical Device Information, 30, 108-110.
[8] Zhong, J.J., Li, W.T., Huang, Y.F. and Others. (2024) Design characteristics and methodological quality of machine learning prediction model studies in primary healthcare: A scoping review. Chinese General Practice, 27, 1271-1276.
[9] Cai, N.X., Ma, Y.N. and Wen, D.L. (2024) Application of machine learning in the prediction of non-alcoholic fatty liver. China Health Statistics, 41, 316-318.
[10] Chang, Q.X., Wang, X.M., Wang, C. and Others. (2022) A study on risk factors related to fatty liver in the elderly based on association rules. China Health Statistics, 39, 558-561.
[11] Chen, Z.B. (2015) Publication of the book "Chinese Guidelines for the Prevention and Treatment of Fatty Liver (Popular Science Edition)". Practical Hepatology, 18, 248.
[12] Marengo, A., Rosso, C. and Bugianesi, E. (2016) Liver cancer: Connections with obesity, fatty liver, and cirrhosis. Annual Review of Medicine, 67, 103-117.
[13] Polyzos, S.A., Chrysavgis, L., Vachliotis, I.D., Chartampilas, E. and Cholongitas, E. (2023) Nonalcoholic fatty liver disease and hepatocellular carcinoma: Insights in epidemiology, pathogenesis, imaging, prevention and therapy. Seminars in Cancer Biology, 93, 20-35.
[14] Ouyang, D., Xu, D.D., Sun, Y.R. and Others. (2024) Construction of a non-alcoholic fatty liver disease prediction model for non-obese populations based on lifestyle-related indicators. Journal of Nursing, 31, 1-7.
[15] Feng, J.F., Feng, J.Z., Liu, S.H. and Others. (2024) Correlation between serum uric acid/creatinine ratio and non-alcoholic fatty liver disease in physical examination populations. Chinese Health Management, 18, 58-61.
[16] Li, W.W. and Li, W. (2024) Value analysis of combined detection of serum inflammatory factors, blood glucose, and uric acid in the diagnosis of fatty liver in the elderly. Journal of Experimental and Laboratory Medicine, 42, 17-19.
[17] Feng, Y.P., Zhang, Y.X. and Chen, D. (2024) Correlation analysis of triglyceride-glucose index and its combination with body mass index with non-alcoholic fatty liver in medical staff. Chinese General Practitioner, 23, 1168-1173.
[18] Lei, T., Liu, Y., Bu, H.Y., et al. (2023) Correlation analysis between body mass index and fatty liver in a health examination population. Xinjiang Medical Journal, 53, 1344–1346, 1354.
[19] Gu, X.D., Zhang, X.Y. and Sun, X.H. (2017) Analysis of risk factors for elevated ALT in patients with non-alcoholic fatty liver. Modern Journal of Laboratory Medicine, 32, 140-143.
[20] Fan, J. and Wang, D. (2024) Serum uric acid and nonalcoholic fatty liver disease. Frontiers in Endocrinology, 15, 1455132.
[21] Arefhosseini, S., Aghajani, T., Tutunchi, H. and Ebrahimi-Mameghani, M. (2024) Association of systemic inflammatory indices with anthropometric measures, metabolic factors, and liver function in non-alcoholic fatty liver disease. Scientific Reports, 14, 12829.
[22] Kyhl, L.K., Nordestgaard, B.G., Tybjærg-Hansen, A., Smith, G.D. and Nielsen, S.F. (2025) VLDL triglycerides and cholesterol in non-alcoholic fatty liver disease and myocardial infarction. Atherosclerosis, 401, 119094.
[23] Fu, S.T., He, B. and Xu, J.C. (2025) Establishment and validation of a machine learning algorithm-based prediction model for liver cirrhosis-related hepatic encephalopathy. Chinese Journal of Laboratory Medicine, 48, 93-102.
[24] Chu, J., Yuan, Z.R. and Mu, X. (2024) Logistic regression analysis of risk factors for malnutrition in patients with hepatocellular carcinoma undergoing hepatic artery chemoembolization and construction of a nomogram prediction model. Chinese Medical Journal, 59, 1354-1358.
[25] Dai, X., Li, J., Wang, C.Y. and Others. (2022) Construction of a machine learning-based prediction model for fatty liver. Journal of Hubei University of Medicine, 41, 574-577.
[26] Gu, L., Chen, X., Zhang, Y. and Others. (2025) Analysis of risk factors for hospital infection in patients with stroke and construction of a nomogram prediction model. Journal of Jiangsu University (Medical Science), 35, 56-61.
[27] Yu, L., Wang, X., Zhang, X. and Others. (2025) Construction of a nomogram model for predicting the onset of hepatocellular carcinoma based on abnormal serum prothrombin and alpha-fetoprotein, and model evaluation. Chinese Journal of Hepatobiliary Surgery, 31, 1-5.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 5565
Visits: 368873

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.