Li, Gang, Zheng, Tian-Lei, Chi, Xiao-Ling, Zhu, Yong-Fen, Chen, Jin-Jun, Xu, Liang, Shi, Jun-Ping, Wang, Xiao-Dong, Zhao, Wei-Guo, Byrne, Christopher, Targher, Giovanni, Rios, Rafael S., Huang, Ou-Yang, Tang, Liang-Jie, Zhang, Shi-Jin, Geng, Shi, Xiao, Huan-Ming, Chen, Sui-Dan, Zhang, Rui and Zheng, Ming-Hua (2023) LEARN algorithm: a novel option for predicting non-alcoholic steatohepatitis. Hepatobiliary Surgery and Nutrition.
Abstract
Background: there is an unmet need for accurate non-invasive methods to diagnosenon-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 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 biopsy121 proven NAFLD were included in final analysis. These patients were randomly 122 subdivided into the training and validation groups, in a ratio of 4:1. The LEARN 123 algorithm was developed in the training group to identify NASH, and subsequently, 124 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 (AUROC: 0.81, 95%CI 0.77-0.84 and 0.80, 0.73-0.87, respectively). This algorithm also 130 performed better than serum cytokeratin-18 neoepitope M30 level or other non131 invasive NASH scores (including HAIR, ION, NICE) for identifying NASH (p-value 132 <0.001). Additionally, the LEARN algorithm performed well in identifying NASH in 7 different patient subgroups, as well as in subjects with partial missing body composition data. Conclusion: the LEARN algorithm, utilizing simple easily obtained measures, provides a fully automated, simple, non-invasive method for identifying NASH. 137 Keywords: NAFLD, NASH, LEARN algorithm, body composition.
More information
Identifiers
Catalogue record
Export record
Contributors
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.