Early prediction of liver disease using conventional risk factors and gut microbiome-augmented gradient boosting
Early prediction of liver disease using conventional risk factors and gut microbiome-augmented gradient boosting
ABSTRACT Gut microbiome sequencing has shown promise as a predictive biomarker for a wide range of diseases, including classification of liver disease and severity grading. However, the potential of gut microbiota for prospective risk prediction of liver disease has not been assessed. Here, we utilise shallow gut metagenomic sequencing data of a large population-based cohort (N=>7,115) and ～15 years of electronic health register follow-up together with machine-learning to investigate the predictive capacity of gut microbial predictors, individually and in conjunction with conventional risk factors, for incident liver disease and alcoholic liver disease. Separately, conventional and microbiome risk factors showed comparable predictive capacity for incident liver disease. However, microbiome augmentation of conventional risk factor models using gradient boosted classifiers significantly improved performance, with average AUROCs of 0.834 for incident liver disease and 0.956 for alcoholic liver disease (AUPRCs of 0.185 and 0.304, respectively). Disease-free survival analysis showed significantly improved stratification using microbiome-augmented risk models as compared to conventional risk factors alone. Investigation of predictive microbial signatures revealed a wide range of bacterial taxa, including those previously associated with hepatic function and disease. This study supports the potential clinical validity of gut metagenomic sequencing to complement conventional risk factors for risk prediction of liver diseases.
Cheng Susan、Lahti Leo、Liu Yang、Havulinna Aki S.、Zhu Qiyun、Tripathi Anupriya、Salomaa Veikko、Jain Mo、Verspoor Karin、Sanders Jon、Ruuskanen Matti、Knight Rob、Loomba Rohit、Jousilahti Pekka、Meric Guillaume、Inouye Michael、Vazquez-Baeza Yoshiki、Teo Shu Mei、Niiranen Teemu
Smidt Heart Institute, Cedars-Sinai Medical CenterDepartment of Medicine, Turku University Hospital and University of Turku||Department of Future Technologies, University of TurkuCambridge Baker Systems Genomics Initiative, Baker Heart and Diabetes Institute||Department of Clinical Pathology, Melbourne Medical School, The University of MelbourneDepartment of Public Health Solutions, Finnish Institute for Health and Welfare||Institute of Molecular Medicine Finland, University of HelsinkiDepartment of Pediatrics, School of Medicine, University of California San DiegoDepartment of Pediatrics, School of Medicine, University of California San Diego||Division of Biological Sciences, University of California San DiegoDepartment of Public Health Solutions, Finnish Institute for Health and WelfareDepartment of Pediatrics, School of Medicine, University of California San Diego||Center for Microbiome Innovation, University of California San DiegoSchool of Computing and Information Systems, University of MelbourneDepartment of Pediatrics, School of Medicine, University of California San DiegoDepartment of Medicine, Turku University Hospital and University of Turku||Department of Future Technologies, University of TurkuDepartment of Pediatrics, School of Medicine, University of California San Diego||Center for Microbiome Innovation, University of California San Diego||Department of Computer Science & Engineering, Jacobs School of Engineering, University of California San DiegoNAFLD Research Center, Department of Medicine, University of California San DiegoDepartment of Public Health Solutions, Finnish Institute for Health and Welfare||Department of Medicine, Turku University Hospital and University of TurkuCambridge Baker Systems Genomics Initiative, Baker Heart and Diabetes Institute||Department of Infectious Diseases, Central Clinical School, Monash UniversityCambridge Baker Systems Genomics Initiative, Baker Heart and Diabetes Institute||Department of Clinical Pathology, Melbourne Medical School, The University of Melbourne||Cambridge Baker Systems Genomics Initiative, Department of Public Health and Primary Care, University of Cambridge||Health Data Research UK Cambridge, Wellcome Genome Campus and University of Cambridge||British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge||British Heart Foundation Centre of Research Excellence, University of Cambridge||National Institute for Health Research Cambridge Biomedical Research Centre, University of Cambridge and Cambridge University Hospitals||The Alan Turing InstituteCenter for Microbiome Innovation, University of California San Diego||Department of Computer Science & Engineering, Jacobs School of Engineering, University of California San DiegoCambridge Baker Systems Genomics Initiative, Baker Heart and Diabetes Institute||Cambridge Baker Systems Genomics Initiative, Department of Public Health and Primary Care, University of CambridgeDepartment of Medicine, Turku University Hospital and University of Turku||Department of Future Technologies, University of Turku
医学研究方法微生物学内科学
Cheng Susan,Lahti Leo,Liu Yang,Havulinna Aki S.,Zhu Qiyun,Tripathi Anupriya,Salomaa Veikko,Jain Mo,Verspoor Karin,Sanders Jon,Ruuskanen Matti,Knight Rob,Loomba Rohit,Jousilahti Pekka,Meric Guillaume,Inouye Michael,Vazquez-Baeza Yoshiki,Teo Shu Mei,Niiranen Teemu.Early prediction of liver disease using conventional risk factors and gut microbiome-augmented gradient boosting[EB/OL].(2025-03-28)[2025-04-28].https://www.medrxiv.org/content/10.1101/2020.06.24.20138933.点此复制
评论