LEARN algorithm: a novel option for predicting non-alcoholic steatohepatitis

Gang Li; Tian-Lei Zheng; Xiao-Ling Chi; Yong-Fen Zhu; Jin-Jun Chen; Liang Xu; Jun-Ping Shi; Xiao-Dong Wang; Wei-Guo Zhao; Christopher D Byrne; Giovanni Targher; Rafael S Rios; Ou-Yang Huang; Liang-Jie Tang; Shi-Jin Zhang; Shi Geng; Huan-Ming Xiao; Sui-Dan Chen; Rui Zhang; Ming-Hua Zheng

doi:10.21037/hbsn-21-523

LEARN algorithm: a novel option for predicting non-alcoholic steatohepatitis

Hepatobiliary Surg Nutr. 2023 Aug 1;12(4):507-522. doi: 10.21037/hbsn-21-523. Epub 2023 Mar 30.

Authors

Gang Li^#¹, Tian-Lei Zheng^#², Xiao-Ling Chi³, Yong-Fen Zhu⁴, Jin-Jun Chen^{5

6}, Liang Xu⁷, Jun-Ping Shi⁸, Xiao-Dong Wang⁹, Wei-Guo Zhao², Christopher D Byrne¹⁰, Giovanni Targher¹¹, Rafael S Rios¹, Ou-Yang Huang¹, Liang-Jie Tang¹, Shi-Jin Zhang², Shi Geng², Huan-Ming Xiao³, Sui-Dan Chen¹², Rui Zhang¹³, Ming-Hua Zheng^{1

9

14}

Affiliations

¹ MAFLD Research Center, Department of Hepatology, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
² Artificial Intelligence Unit, Department of Medical Equipment, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
³ Department of Hepatology, Guangdong Provincial Hospital of Chinese Medicine, the Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China.
⁴ Department of Hepatology and Infection, Sir Run Run Shaw Hospital, Affiliated with School of Medicine, Zhejiang University, Hangzhou, China.
⁵ Hepatology Unit, Department of Infectious Diseases, Nanfang Hospital, Southern Medical University, Guangzhou, China.
⁶ Hepatology Unit, Zengcheng Branch, Nanfang Hospital, Southern Medical University, Guangzhou, China.
⁷ Department of Hepatology, Tianjin Second People's Hospital, Tianjin, China.
⁸ Department of Liver Diseases, Hangzhou Normal University Affiliated Hospital, Hangzhou, China.
⁹ Key Laboratory of Diagnosis and Treatment for the Development of Chronic Liver Disease in Zhejiang Province, Wenzhou, China.
¹⁰ Southampton National Institute for Health and Care Research Biomedical Research Centre, University Hospital Southampton & University of Southampton, Southampton General Hospital, Southampton, UK.
¹¹ Section of Endocrinology, Diabetes and Metabolism, Department of Medicine, University of Verona, Verona, Italy.
¹² Department of Pathology, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
¹³ Department of Nutrition, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
¹⁴ Institute of Hepatology, Wenzhou Medical University, Wenzhou, China.

^# Contributed equally.

Abstract

Background: There is an unmet need for accurate non-invasive methods to diagnose non-alcoholic steatohepatitis (NASH). Since impedance-based measurements of body composition are simple, repeatable and have a strong association with non-alcoholic fatty liver disease (NAFLD) severity, we aimed to develop a novel and fully automatic machine learning algorithm, consisting of a deep neural network based on impedance-based measurements of body composition to identify NASH [the bioeLectrical impEdance Analysis foR Nash (LEARN) algorithm].

Methods: A total of 1,259 consecutive subjects with suspected NAFLD were screened from six medical centers across China, of which 766 patients with biopsy-proven NAFLD were included in final analysis. These patients were randomly subdivided into the training and validation groups, in a ratio of 4:1. The LEARN algorithm was developed in the training group to identify NASH, and subsequently, tested in the validation group.

Results: The LEARN algorithm utilizing impedance-based measurements of body composition along with age, sex, pre-existing hypertension and diabetes, was able to predict the likelihood of having NASH. This algorithm showed good discriminatory ability for identifying NASH in both the training and validation groups [area under the receiver operating characteristics (AUROC): 0.81, 95% CI: 0.77-0.84 and AUROC: 0.80, 95% CI: 0.73-0.87, respectively]. This algorithm also performed better than serum cytokeratin-18 neoepitope M30 (CK-18 M30) level or other non-invasive NASH scores (including HAIR, ION, NICE) for identifying NASH (P value <0.001). Additionally, the LEARN algorithm performed well in identifying NASH in different patient subgroups, as well as in subjects with partial missing body composition data.

Conclusions: The LEARN algorithm, utilizing simple easily obtained measures, provides a fully automated, simple, non-invasive method for identifying NASH.

Keywords: Non-alcoholic fatty liver disease (NAFLD); bioeLectrical impEdance Analysis foR Nash (LEARN) algorithm; body composition; non-alcoholic steatohepatitis (NASH).