Machine Learning Approaches Reveal Metabolic Signatures of Incident Chronic Kidney Disease in Individuals With Prediabetes and Type 2 Diabetes
Autor: | Freimut Schliess, Rui Wang-Sattler, Christian Gieger, Markus F. Scheerer, Marcela Covic, Cornelia Huth, Martin Hrabé de Angelis, Jonathan Adam, Martina Troll, Sven Zukunft, Cornelia Prehn, Michael Laxy, Jana Nano, Gabi Kastenmüller, Jerzy Adamski, Annette Peters, Li Wang, Karsten Suhre, Susanne Neschen, Jialing Huang |
---|---|
Rok vydání: | 2020 |
Předmět: |
0301 basic medicine
Adult Blood Glucose Endocrinology Diabetes and Metabolism Metabolite Population 030209 endocrinology & metabolism Type 2 diabetes Machine learning computer.software_genre Machine Learning Prediabetic State 03 medical and health sciences chemistry.chemical_compound 0302 clinical medicine Diabetes mellitus Internal Medicine Medicine Humans Prediabetes Renal Insufficiency Chronic education Aged Aged 80 and over education.field_of_study Receiver operating characteristic business.industry Middle Aged medicine.disease 030104 developmental biology chemistry Diabetes Mellitus Type 2 Cohort Artificial intelligence business computer Biomarkers Kidney disease |
Zdroj: | Diabetes 69, 2756-2765 (2020) |
ISSN: | 1939-327X |
Popis: | Early and precise identification of individuals with prediabetes and type 2 diabetes (T2D) at risk for progressing to chronic kidney disease (CKD) is essential to prevent complications of diabetes. Here, we identify and evaluate prospective metabolite biomarkers and the best set of predictors of CKD in the longitudinal, population-based Cooperative Health Research in the Region of Augsburg (KORA) cohort by targeted metabolomics and machine learning approaches. Out of 125 targeted metabolites, sphingomyelin C18:1 and phosphatidylcholine diacyl C38:0 were identified as candidate metabolite biomarkers of incident CKD specifically in hyperglycemic individuals followed during 6.5 years. Sets of predictors for incident CKD developed from 125 metabolites and 14 clinical variables showed highly stable performances in all three machine learning approaches and outperformed the currently established clinical algorithm for CKD. The two metabolites in combination with five clinical variables were identified as the best set of predictors, and their predictive performance yielded a mean area value under the receiver operating characteristic curve of 0.857. The inclusion of metabolite variables in the clinical prediction of future CKD may thus improve the risk prediction in people with prediabetes and T2D. The metabolite link with hyperglycemia-related early kidney dysfunction warrants further investigation. |
Databáze: | OpenAIRE |
Externí odkaz: |