Fatty Liver Disease Prediction Model Based on Big Data of Electronic Physical Examination Records

Frontiers in Public Health

Changjun Song¹  Shiming Lin²  Tianyue Huang³  Tao Luo⁴  Mingqi Zhao⁴ 

[1] Department of Computer Engineering, Changji University, Changji, China;Department of Computer Engineering, Changji University, Changji, China;School of Informatics Xiamen University (National Demonstrative Software School), Xiamen, China;School of Informatics Xiamen University (National Demonstrative Software School), Xiamen, China;School of Mathematical Sciences Xiamen University, Xiamen, China;

关键词: fatty liver disease;    electronic medical records;    genetic algorithm;    machine learning;    XGBoost;    chi-square binning algorithm;   

DOI  :  10.3389/fpubh.2021.668351

来源: Frontiers

【 摘 要 】

Fatty liver disease (FLD) is a common liver disease, which poses a great threat to people's health, but there is still no optimal method that can be used on a large-scale screening. This research is based on machine learning algorithms, using electronic physical examination records in the health database as data support, to a predictive model for FLD. The model has shown good predictive ability on the test set, with its AUC reaching 0.89. Since there are a large number of electronic physical examination records in most of health database, this model might be used as a non-invasive diagnostic tool for FLD for large-scale screening.

【 授权许可】

CC BY