PuSH - Publikationsserver des Helmholtz Zentrums München

Webb-Robertson, B.M.* ; Nakayasu, E.S.* ; Frohnert, B.I.* ; Bramer, L.M.* ; Akers, S.M.* ; Norris, J.M.* ; Vehik, K.* ; Ziegler, A.-G. ; Metz, T.O.* ; Rich, S.S.* ; Rewers, M.J.*

Integration of infant metabolite, genetic and islet autoimmunity signatures to predict type 1 diabetes by 6 years of age.

J. Clin. Endocrinol. Metab. 107, 2329-2338 (2022)
Free by publisher: Verlagsversion online verfügbar 09/2023
CONTEXT: Biomarkers that can accurately predict risk of type 1 diabetes (T1D) in genetically predisposed children can facilitate interventions to delay or prevent the disease. OBJECTIVE: Determine if a combination of genetic, immunologic, and metabolic features, measured at infancy, can be utilized to predict the likelihood that a child will develop T1D by the age of 6 years. DESIGN: Newborns with HLA typing enrolled in the prospective birth cohort of The Environmental Determinants of Diabetes in the Young (TEDDY). SETTING: TEDDY ascertained children in Finland, Germany, Sweden, and the United States. PATIENTS: TEDDY children were either from the general population or from families with T1D with an HLA genotype associated with T1D specific to TEDDY eligibility criteria. From the TEDDY cohort there were 702 children will all data sources measured at 3, 6 and 9 months of age, 11.4% of which progressed to T1D by the age of 6. INTERVENTIONS: None. MAIN OUTCOME MEASURES: Diagnosis of T1D as diagnosed by American Diabetes Association criteria. RESULTS: Machine learning-based feature selection yielded classifiers based on disparate demographic, immunologic, genetic and metabolite features. The accuracy of the model utilizing all available data evaluated by the Area Under a Receiver Operating Characteristic Curve is 0.84. Reducing to only 3- and 9-month measurements did not reduce the AUC significantly. Metabolomics had the largest value when evaluating the accuracy at a low false positive rate. CONCLUSIONS: The metabolite features identified as important for progression to T1D by age 6 point to altered sugar metabolism in infancy. Integrating this information with classic risk factors improves prediction of the progression to T1D in early childhood.
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Integration ; Machine Learning ; Prediction ; Type 1 Diabetes
ISSN (print) / ISBN 0021-972X
e-ISSN 1945-7197
Quellenangaben Band: 107, Heft: 8, Seiten: 2329-2338 Artikelnummer: , Supplement: ,
Verlag Endocrine Society
Verlagsort Bethesda, Md.
Begutachtungsstatus Peer reviewed