Application of artificial intelligence and machine learning in non-alcoholic fatty liver research
10.3969/j.issn.1001-5256.2022.10.029
- VernacularTitle:人工智能及机器学习在非酒精性脂肪性肝病中的应用
- Author:
Gong FENG
1
;
Xueying WANG
2
;
Shanshan LI
3
;
Na HE
4
;
Haoyun ZHENG
3
;
Man MI
1
;
Qinqin YAN
1
Author Information
1. Institute of General Practice, Xi'an Medical University, Xi'an 710021, China, Xi'an 710021 China
2. School of General Practice, Xi'an Medical University, Xi'an 710021, China, Xi'an 710021 China
3. Institute of Public Health, Xi'an Medical University, Xi'an 710021, China, Xi'an 710021 China
4. Department of Gastroenterology, The First Affiliated Hospital of Xi'an Medical University, Xi'an 710077, China
- Publication Type:Reviews
- Keywords:
Non-alcoholic Fatty Liver Disease;
Artificial Intelligence;
Machine Learning
- From:
Journal of Clinical Hepatology
2022;38(10):2352-2356
- CountryChina
- Language:Chinese
-
Abstract:
Non-alcoholic fatty liver disease (NAFLD) incidence is rapidly increasing and become the most common chronic liver disease globally. NAFLD also possesses a risk of developing cardiovascular, kidney, and other diseases. To date, NAFLD still faces difficulties in early diagnosis and treatment options. Thus, early detection, prevention, optimally individualized treatment selections, and prediction of prognosis all are the keys in clinical NAFLD control. Although there are assessment tools available for NAFLD severity appraisal using different clinical parameters, it becomes a hot topic of research in the field for how to optimize non-invasive assessment methodologies. Artificial intelligence (AI) and machine learning are increasingly being used in healthcare, especially in assessment and analysis of chronic liver disease, including NAFLD. This review summarized and discussed the most recent progress of AI and machine learning in differential diagnosis of NAFLD and evaluation of NAFLD severity, in order to provide treatment selections, i.e., the novel AI diagnosis models based on the electronic health records and laboratory tests, ultrasound and radiographic imaging, and liver histopathology data. The therapeutic models discussed the personalized lifestyle changes and NAFLD drug development. The NAFLD prognosis model reviewed and predicted how NAFLD-changed liver metabolisms affect prognosis of patients. This review also speculated future prospective research hot spots and development in the filed for how to utilize the existing AI models to distinguish NAFLD and non-alcoholic steatohepatitis (NASH) and assess NAFLD fibrosis status.
