Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting

Yang Liu; Guillaume Méric; Aki S Havulinna; Shu Mei Teo; Fredrik Åberg; Matti Ruuskanen; Jon Sanders; Qiyun Zhu; Anupriya Tripathi; Karin Verspoor; Susan Cheng; Mohit Jain; Pekka Jousilahti; Yoshiki Vázquez-Baeza; Rohit Loomba; Leo Lahti; Teemu Niiranen; Veikko Salomaa; Rob Knight; Michael Inouye

doi:10.1016/j.cmet.2022.03.002

Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting

Yang Liu, Guillaume Méric, Aki S Havulinna, Shu Mei Teo, Fredrik Åberg, Matti Ruuskanen, Jon Sanders, Qiyun Zhu, Anupriya Tripathi, Karin Verspoor, Susan Cheng, Mohit Jain, Pekka Jousilahti, Yoshiki Vázquez-Baeza, Rohit Loomba, Leo Lahti, Teemu Niiranen, Veikko Salomaa, Rob Knight, Michael Inouye

Research output: Contribution to journal › Article › peer-review

65 Citations (SciVal)

Abstract

The gut microbiome has shown promise as a predictive biomarker for various diseases. However, the potential of gut microbiota for prospective risk prediction of liver disease has not been assessed. Here, we utilized shallow shotgun metagenomic sequencing of a large population-based cohort (N > 7,000) with ∼15 years of follow-up in combination with machine learning to investigate the predictive capacity of gut microbial predictors individually and in conjunction with conventional risk factors for incident liver disease. Separately, conventional and microbial factors showed comparable predictive capacity. However, microbiome augmentation of conventional risk factors using machine learning significantly improved the performance. Similarly, disease-free survival analysis showed significantly improved stratification using microbiome-augmented models. Investigation of predictive microbial signatures revealed previously unknown taxa for liver disease, as well as 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 prediction of liver diseases.

Original language	English
Pages (from-to)	719-730.e4
Journal	Cell Metabolism
Volume	34
Issue number	5
Early online date	29 Mar 2022
DOIs	https://doi.org/10.1016/j.cmet.2022.03.002
Publication status	Published - 3 May 2022

Bibliographical note

Acknowledgements

V.S. was supported by the Finnish Foundation for Cardiovascular Research. M.I. was supported by the Munz Chair of Cardiovascular Prediction and Prevention. A.S.H. was supported by the Academy of Finland, grant no. 321356. L.L. was supported by the Academy of Finland grant nos. 295741 and 307127. T.N. was supported by the Emil Aaltonen Foundation, the Finnish Foundation for Cardiovascular Research, the Finnish Medical Foundation, and the Academy of Finland, grant no. 321351. R.L. receives funding support from NIEHS (5P42ES010337), NCATS (5UL1TR001442), NIDDK (U01DK061734, R01DK106419, P30DK120515, R01DK121378, and R01DK124318), and DOD PRCRP (W81XWH-18-2-0026). This study was supported by the Victorian Government’s Operational Infrastructure Support (OIS) program and by core funding from the British Heart Foundation (RG/13/13/30194; RG/18/13/33946) and the NIHR Cambridge Biomedical Research Centre (BRC-1215-20014). The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care. This work was supported by Health Data Research UK, which is funded by the UK Medical Research Council, Engineering and Physical Sciences Research Council, Economic and Social Research Council, Department of Health and Social Care (England), Chief Scientist Office of the Scottish Government Health and Social Care Directorates, Health and Social Care Research and Development Division (Welsh Government), Public Health Agency (Northern Ireland), British Heart Foundation, and Wellcome.

Keywords

Gastrointestinal Microbiome/genetics
Humans
Liver Diseases
Metagenomics
Microbiota
Prospective Studies
Risk Factors

Access to Document

10.1016/j.cmet.2022.03.002Licence: CC BY-NC-ND

Cite this

Liu, Y., Méric, G., Havulinna, A. S., Teo, S. M., Åberg, F., Ruuskanen, M., Sanders, J., Zhu, Q., Tripathi, A., Verspoor, K., Cheng, S., Jain, M., Jousilahti, P., Vázquez-Baeza, Y., Loomba, R., Lahti, L., Niiranen, T., Salomaa, V., Knight, R., & Inouye, M. (2022). Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting. Cell Metabolism, 34(5), 719-730.e4. https://doi.org/10.1016/j.cmet.2022.03.002

Liu, Y, Méric, G, Havulinna, AS, Teo, SM, Åberg, F, Ruuskanen, M, Sanders, J, Zhu, Q, Tripathi, A, Verspoor, K, Cheng, S, Jain, M, Jousilahti, P, Vázquez-Baeza, Y, Loomba, R, Lahti, L, Niiranen, T, Salomaa, V, Knight, R & Inouye, M 2022, 'Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting', Cell Metabolism, vol. 34, no. 5, pp. 719-730.e4. https://doi.org/10.1016/j.cmet.2022.03.002

@article{a947a6b02a084c8493badb2adfa9b7c9,

title = "Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting",

abstract = "The gut microbiome has shown promise as a predictive biomarker for various diseases. However, the potential of gut microbiota for prospective risk prediction of liver disease has not been assessed. Here, we utilized shallow shotgun metagenomic sequencing of a large population-based cohort (N > 7,000) with ∼15 years of follow-up in combination with machine learning to investigate the predictive capacity of gut microbial predictors individually and in conjunction with conventional risk factors for incident liver disease. Separately, conventional and microbial factors showed comparable predictive capacity. However, microbiome augmentation of conventional risk factors using machine learning significantly improved the performance. Similarly, disease-free survival analysis showed significantly improved stratification using microbiome-augmented models. Investigation of predictive microbial signatures revealed previously unknown taxa for liver disease, as well as 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 prediction of liver diseases.",

keywords = "Gastrointestinal Microbiome/genetics, Humans, Liver Diseases, Metagenomics, Microbiota, Prospective Studies, Risk Factors",

author = "Yang Liu and Guillaume M{\'e}ric and Havulinna, \{Aki S\} and Teo, \{Shu Mei\} and Fredrik {\AA}berg and Matti Ruuskanen and Jon Sanders and Qiyun Zhu and Anupriya Tripathi and Karin Verspoor and Susan Cheng and Mohit Jain and Pekka Jousilahti and Yoshiki V{\'a}zquez-Baeza and Rohit Loomba and Leo Lahti and Teemu Niiranen and Veikko Salomaa and Rob Knight and Michael Inouye",

year = "2022",

month = may,

day = "3",

doi = "10.1016/j.cmet.2022.03.002",

language = "English",

volume = "34",

pages = "719--730.e4",

journal = "Cell Metabolism",

issn = "1550-4131",

publisher = "Cell Press",

number = "5",

}

TY - JOUR

T1 - Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting

AU - Liu, Yang

AU - Méric, Guillaume

AU - Havulinna, Aki S

AU - Teo, Shu Mei

AU - Åberg, Fredrik

AU - Ruuskanen, Matti

AU - Sanders, Jon

AU - Zhu, Qiyun

AU - Tripathi, Anupriya

AU - Verspoor, Karin

AU - Cheng, Susan

AU - Jain, Mohit

AU - Jousilahti, Pekka

AU - Vázquez-Baeza, Yoshiki

AU - Loomba, Rohit

AU - Lahti, Leo

AU - Niiranen, Teemu

AU - Salomaa, Veikko

AU - Knight, Rob

AU - Inouye, Michael

PY - 2022/5/3

Y1 - 2022/5/3

N2 - The gut microbiome has shown promise as a predictive biomarker for various diseases. However, the potential of gut microbiota for prospective risk prediction of liver disease has not been assessed. Here, we utilized shallow shotgun metagenomic sequencing of a large population-based cohort (N > 7,000) with ∼15 years of follow-up in combination with machine learning to investigate the predictive capacity of gut microbial predictors individually and in conjunction with conventional risk factors for incident liver disease. Separately, conventional and microbial factors showed comparable predictive capacity. However, microbiome augmentation of conventional risk factors using machine learning significantly improved the performance. Similarly, disease-free survival analysis showed significantly improved stratification using microbiome-augmented models. Investigation of predictive microbial signatures revealed previously unknown taxa for liver disease, as well as 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 prediction of liver diseases.

AB - The gut microbiome has shown promise as a predictive biomarker for various diseases. However, the potential of gut microbiota for prospective risk prediction of liver disease has not been assessed. Here, we utilized shallow shotgun metagenomic sequencing of a large population-based cohort (N > 7,000) with ∼15 years of follow-up in combination with machine learning to investigate the predictive capacity of gut microbial predictors individually and in conjunction with conventional risk factors for incident liver disease. Separately, conventional and microbial factors showed comparable predictive capacity. However, microbiome augmentation of conventional risk factors using machine learning significantly improved the performance. Similarly, disease-free survival analysis showed significantly improved stratification using microbiome-augmented models. Investigation of predictive microbial signatures revealed previously unknown taxa for liver disease, as well as 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 prediction of liver diseases.

KW - Gastrointestinal Microbiome/genetics

KW - Humans

KW - Liver Diseases

KW - Metagenomics

KW - Microbiota

KW - Prospective Studies

KW - Risk Factors

UR - https://www.scopus.com/pages/publications/85129542695

U2 - 10.1016/j.cmet.2022.03.002

DO - 10.1016/j.cmet.2022.03.002

M3 - Article

C2 - 35354069

SN - 1550-4131

VL - 34

SP - 719-730.e4

JO - Cell Metabolism

JF - Cell Metabolism

IS - 5

ER -

Early prediction of incident liver disease using conventional risk factors and gut-microbiome-augmented gradient boosting

Abstract

Bibliographical note

Acknowledgements

Keywords

Access to Document

Other files and links

Fingerprint

Cite this