A metabolome-derived score predicts metabolic dysfunction-associated steatohepatitis and mortality from liver disease

Qingxia Huang; Sami F Qadri; Hua Bian; Xiaoxuan Yi; Chenhao Lin; Xinyu Yang; Xiaopeng Zhu; Huandong Lin; Hongmei Yan; Xinxia Chang; Xiaoyang Sun; Shuai Ma; Qi Wu; Hailuan Zeng; Xiqi Hu; Yan Zheng; Hannele Yki-Järvinen; Xin Gao; Huiru Tang; Mingfeng Xia

doi:10.1016/j.jhep.2024.10.015

A metabolome-derived score predicts metabolic dysfunction-associated steatohepatitis and mortality from liver disease

J Hepatol. 2024 Oct 16:S0168-8278(24)02636-9. doi: 10.1016/j.jhep.2024.10.015. Online ahead of print.

Authors

Qingxia Huang¹, Sami F Qadri², Hua Bian³, Xiaoxuan Yi¹, Chenhao Lin⁴, Xinyu Yang³, Xiaopeng Zhu³, Huandong Lin³, Hongmei Yan³, Xinxia Chang³, Xiaoyang Sun³, Shuai Ma³, Qi Wu³, Hailuan Zeng³, Xiqi Hu⁵, Yan Zheng¹, Hannele Yki-Järvinen², Xin Gao⁶, Huiru Tang⁷, Mingfeng Xia⁸

Affiliations

¹ State Key Laboratory of Genetic Engineering, School of Life Sciences, Human Phenome Institute, Zhangjiang Fudan International Innovation Center, Zhongshan Hospital, Fudan University, Shanghai 200438, China.
² Department of Medicine, University of Helsinki and Helsinki University Hospital, Helsinki, Finland; Minerva Foundation Institute for Medical Research, Helsinki, Finland.
³ Department of Endocrinology and Metabolism, Zhongshan Hospital and Fudan Institute for Metabolic Diseases, Fudan University, Shanghai, China.
⁴ State Key Laboratory of Genetic Engineering, School of Life Sciences, Human Phenome Institute, Fudan University, Shanghai, China.
⁵ Department of Pathology, Medical College, Fudan University, Shanghai, China.
⁶ Department of Endocrinology and Metabolism, Zhongshan Hospital and Fudan Institute for Metabolic Diseases, Fudan University, Shanghai, China. Electronic address: zhongshan_endo@126.com.
⁷ State Key Laboratory of Genetic Engineering, School of Life Sciences, Human Phenome Institute, Zhangjiang Fudan International Innovation Center, Zhongshan Hospital, Fudan University, Shanghai 200438, China. Electronic address: Huiru_tang@fudan.edu.cn.
⁸ Department of Endocrinology and Metabolism, Zhongshan Hospital and Fudan Institute for Metabolic Diseases, Fudan University, Shanghai, China. Electronic address: dr_xiamingfeng@163.com.

PMID: 39423864
DOI: 10.1016/j.jhep.2024.10.015

Abstract

Background & aims: Metabolic dysfunction-associated steatohepatitis (MASH) is associated with a >10-fold increase in liver-related mortality. However, biomarkers predicting both MASH and mortality in patients with metabolic dysfunction-associated steatotic liver disease (MASLD) are missing. We developed a metabolome-derived prediction score for MASH and examined whether it predicts mortality in Chinese and European cohorts.

Methods: The MASH prediction score was developed using a multi-step machine learning strategy, based on 44 clinical parameters and 250 serum metabolites measured by proton nuclear magnetic resonance in 311 Chinese adults undergoing a liver biopsy. External validation was conducted in a Finnish liver biopsy cohort (n = 305). We investigated associations of the score with all-cause and cause-specific mortality in the population-based Shanghai Changfeng study (n = 5,893) and the UK biobank (n = 111,673).

Results: A total of 24 clinical parameters and 194 serum metabolites were significantly associated with MASH in the Chinese liver biopsy cohort. The final MASH score included BMI, aspartate aminotransferase, tyrosine, and the phospholipid-to-total lipid ratio in VLDL. The score identified patients with MASH with AUROCs of 0.87 (95% CI 0.83-0.91) and 0.81 (95% CI 0.75-0.88) in the Chinese and Finnish cohorts, with high negative predictive values. Participants with a high or intermediate risk of MASH based on the score had a markedly higher risk of MASLD-related mortality than those with a low risk in Chinese (hazard ratio 23.19; 95% CI 4.80-111.97) and European (hazard ratio 20.15; 95% CI 10.95-37.11) individuals after 7.2 and 12.6 years of follow-up, respectively. The MASH prediction score was superior to the Fibrosis-4 index and the NAFLD fibrosis score in predicting MASLD-related mortality.

Conclusion: The metabolome-derived MASH prediction score accurately predicts risk of MASH and MASLD-related mortality in both Chinese and European individuals.

Impact and implications: Metabolic dysfunction-associated steatohepatitis (MASH) is associated with more than a 10-fold increase in liver-related death. However, biomarkers predicting not only MASH, but also death due to liver disease, are missing. We established a MASH prediction score based on 44 clinical parameters and 250 serum metabolites using a machine learning strategy. This metabolome-derived MASH prediction score could accurately identify patients with MASH among both Chinese and Finnish individuals, and it was superior to the Fibrosis-4 index and the NAFLD fibrosis score in predicting MASLD-related death in the general population. Thus, the new MASH prediction score is a useful tool for identifying individuals with a markedly increased risk of serious liver-related outcomes among at-risk and general populations.

Keywords: machine learning; metabolic dysfunction-associated steatohepatitis; metabolomics; mortality; prediction score.