Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation

ABSTRACT The incidence of type 2 diabetes (T2D) has been increasing globally, and a growing body of evidence links type 2 diabetes with altered microbiota composition. Type 2 diabetes is preceded by a long prediabetic state characterized by changes in various metabolic parameters. We tested whether...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Oliver Aasmets, Kreete Lüll, Jennifer M. Lang, Calvin Pan, Johanna Kuusisto, Krista Fischer, Markku Laakso, Aldons J. Lusis, Elin Org
Formato:	article
Lenguaje:	EN
Publicado:	American Society for Microbiology 2021
Materias:	T2D gut microbiome machine learning prediction analysis type 2 diabetes Microbiology QR1-502
Acceso en línea:	https://doaj.org/article/f257e30117d14b4c92887fd9da5785fa
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f257e30117d14b4c92887fd9da5785fa
record_format	dspace
spelling	oai:doaj.org-article:f257e30117d14b4c92887fd9da5785fa2021-12-02T17:07:26ZMachine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation10.1128/mSystems.01191-202379-5077https://doaj.org/article/f257e30117d14b4c92887fd9da5785fa2021-02-01T00:00:00Zhttps://journals.asm.org/doi/10.1128/mSystems.01191-20https://doaj.org/toc/2379-5077ABSTRACT The incidence of type 2 diabetes (T2D) has been increasing globally, and a growing body of evidence links type 2 diabetes with altered microbiota composition. Type 2 diabetes is preceded by a long prediabetic state characterized by changes in various metabolic parameters. We tested whether the gut microbiome could have predictive potential for T2D development during the healthy and prediabetic disease stages. We used prospective data of 608 well-phenotyped Finnish men collected from the population-based Metabolic Syndrome in Men (METSIM) study to build machine learning models for predicting continuous glucose and insulin measures in a shorter (1.5 year) and longer (4 year) period. Our results show that the inclusion of the gut microbiome improves prediction accuracy for modeling T2D-associated parameters such as glycosylated hemoglobin and insulin measures. We identified novel microbial biomarkers and described their effects on the predictions using interpretable machine learning techniques, which revealed complex linear and nonlinear associations. Additionally, the modeling strategy carried out allowed us to compare the stability of model performance and biomarker selection, also revealing differences in short-term and long-term predictions. The identified microbiome biomarkers provide a predictive measure for various metabolic traits related to T2D, thus providing an additional parameter for personal risk assessment. Our work also highlights the need for robust modeling strategies and the value of interpretable machine learning. IMPORTANCE Recent studies have shown a clear link between gut microbiota and type 2 diabetes. However, current results are based on cross-sectional studies that aim to determine the microbial dysbiosis when the disease is already prevalent. In order to consider the microbiome as a factor in disease risk assessment, prospective studies are needed. Our study is the first study that assesses the gut microbiome as a predictive measure for several type 2 diabetes-associated parameters in a longitudinal study setting. Our results revealed a number of novel microbial biomarkers that can improve the prediction accuracy for continuous insulin measures and glycosylated hemoglobin levels. These results make the prospect of using the microbiome in personalized medicine promising.Oliver AasmetsKreete LüllJennifer M. LangCalvin PanJohanna KuusistoKrista FischerMarkku LaaksoAldons J. LusisElin OrgAmerican Society for MicrobiologyarticleT2Dgut microbiomemachine learningprediction analysisgut microbiometype 2 diabetesMicrobiologyQR1-502ENmSystems, Vol 6, Iss 1 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	T2D gut microbiome machine learning prediction analysis gut microbiome type 2 diabetes Microbiology QR1-502
spellingShingle	T2D gut microbiome machine learning prediction analysis gut microbiome type 2 diabetes Microbiology QR1-502 Oliver Aasmets Kreete Lüll Jennifer M. Lang Calvin Pan Johanna Kuusisto Krista Fischer Markku Laakso Aldons J. Lusis Elin Org Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
description	ABSTRACT The incidence of type 2 diabetes (T2D) has been increasing globally, and a growing body of evidence links type 2 diabetes with altered microbiota composition. Type 2 diabetes is preceded by a long prediabetic state characterized by changes in various metabolic parameters. We tested whether the gut microbiome could have predictive potential for T2D development during the healthy and prediabetic disease stages. We used prospective data of 608 well-phenotyped Finnish men collected from the population-based Metabolic Syndrome in Men (METSIM) study to build machine learning models for predicting continuous glucose and insulin measures in a shorter (1.5 year) and longer (4 year) period. Our results show that the inclusion of the gut microbiome improves prediction accuracy for modeling T2D-associated parameters such as glycosylated hemoglobin and insulin measures. We identified novel microbial biomarkers and described their effects on the predictions using interpretable machine learning techniques, which revealed complex linear and nonlinear associations. Additionally, the modeling strategy carried out allowed us to compare the stability of model performance and biomarker selection, also revealing differences in short-term and long-term predictions. The identified microbiome biomarkers provide a predictive measure for various metabolic traits related to T2D, thus providing an additional parameter for personal risk assessment. Our work also highlights the need for robust modeling strategies and the value of interpretable machine learning. IMPORTANCE Recent studies have shown a clear link between gut microbiota and type 2 diabetes. However, current results are based on cross-sectional studies that aim to determine the microbial dysbiosis when the disease is already prevalent. In order to consider the microbiome as a factor in disease risk assessment, prospective studies are needed. Our study is the first study that assesses the gut microbiome as a predictive measure for several type 2 diabetes-associated parameters in a longitudinal study setting. Our results revealed a number of novel microbial biomarkers that can improve the prediction accuracy for continuous insulin measures and glycosylated hemoglobin levels. These results make the prospect of using the microbiome in personalized medicine promising.
format	article
author	Oliver Aasmets Kreete Lüll Jennifer M. Lang Calvin Pan Johanna Kuusisto Krista Fischer Markku Laakso Aldons J. Lusis Elin Org
author_facet	Oliver Aasmets Kreete Lüll Jennifer M. Lang Calvin Pan Johanna Kuusisto Krista Fischer Markku Laakso Aldons J. Lusis Elin Org
author_sort	Oliver Aasmets
title	Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
title_short	Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
title_full	Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
title_fullStr	Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
title_full_unstemmed	Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation
title_sort	machine learning reveals time-varying microbial predictors with complex effects on glucose regulation
publisher	American Society for Microbiology
publishDate	2021
url	https://doaj.org/article/f257e30117d14b4c92887fd9da5785fa
work_keys_str_mv	AT oliveraasmets machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT kreetelull machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT jennifermlang machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT calvinpan machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT johannakuusisto machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT kristafischer machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT markkulaakso machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT aldonsjlusis machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation AT elinorg machinelearningrevealstimevaryingmicrobialpredictorswithcomplexeffectsonglucoseregulation
_version_	1718381591659544576

Machine Learning Reveals Time-Varying Microbial Predictors with Complex Effects on Glucose Regulation

Ejemplares similares