Please use this identifier to cite or link to this item:
DC FieldValue
dc.titleAutomated Machine Learning (AutoML)-Derived Preconception Predictive Risk Model to Guide Early Intervention for Gestational Diabetes Mellitus
dc.contributor.authorMukkesh Kumar
dc.contributor.authorLi Ting Ang
dc.contributor.authorHang Png
dc.contributor.authorMaisie Ng
dc.contributor.authorKaren Tan
dc.contributor.authorSee Ling Loy
dc.contributor.authorTan, K.H.
dc.contributor.authorChan, J.K.Y.
dc.contributor.authorKeith M. Godfrey
dc.contributor.authorChan, S.-Y.
dc.contributor.authorChong, Y.S.
dc.contributor.authorEriksson, J.G.
dc.contributor.authorMengling Feng
dc.contributor.authorKarnani, N.
dc.identifier.citationMukkesh Kumar, Li Ting Ang, Hang Png, Maisie Ng, Karen Tan, See Ling Loy, Tan, K.H., Chan, J.K.Y., Keith M. Godfrey, Chan, S.-Y., Chong, Y.S., Eriksson, J.G., Mengling Feng, Karnani, N. (2022). Automated Machine Learning (AutoML)-Derived Preconception Predictive Risk Model to Guide Early Intervention for Gestational Diabetes Mellitus. International Journal of Environmental Research and Public Health 19 (11). ScholarBank@NUS Repository.
dc.description.abstractThe increasing prevalence of gestational diabetes mellitus (GDM) is contributing to the rising global burden of type 2 diabetes (T2D) and intergenerational cycle of chronic metabolic disorders. Primary lifestyle interventions to manage GDM, including second trimester dietary and exercise guidance, have met with limited success due to late implementation, poor adherence and generic guidelines. In this study, we aimed to build a preconception-based GDM predictor to enable early intervention. We also assessed the associations of top predictors with GDM and adverse birth outcomes. Our evolutionary algorithm-based automated machine learning (AutoML) model was implemented with data from 222 Asian multi-ethnic women in a preconception cohort study, Singapore Preconception Study of Long-Term Maternal and Child Outcomes (S-PRESTO). A stacked ensemble model with a gradient boosting classifier and linear support vector machine classifier (stochastic gradient descent training) was derived using genetic programming, achieving an excellent AUC of 0.93 based on four features (glycated hemoglobin A1c (HbA1c), mean arterial blood pressure, fasting insulin, triglycerides/HDL ratio). The results of multivariate logistic regression model showed that each 1 mmol/mol increase in preconception HbA1c was positively associated with increased risks of GDM (p = 0.001, odds ratio (95% CI) 1.34 (1.13–1.60)) and preterm birth (p = 0.011, odds ratio 1.63 (1.12–2.38)). Optimal control of preconception HbA1c may aid in preventing GDM and reducing the incidence of preterm birth. Our trained predictor has been deployed as a web application that can be easily employed in GDM intervention programs, prior to conception.
dc.contributor.departmentDEAN'S OFFICE (DUKE-NUS MEDICAL SCHOOL)
dc.contributor.departmentDUKE-NUS MEDICAL SCHOOL
dc.contributor.departmentDEPT OF OBSTETRICS & GYNAECOLOGY
dc.contributor.departmentDEAN'S OFFICE (MEDICINE)
dc.contributor.departmentOBSTETRICS & GYNAECOLOGY
dc.contributor.departmentDEPT OF BIOCHEMISTRY
dc.description.sourcetitleInternational Journal of Environmental Research and Public Health
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
(15) Automated Machine Learning (AutoML)-Derived Preconception Predictive Risk Model to Guide Early Intervention for Gestational Diabetes Mellitus.pdf845.74 kBAdobe PDF




checked on Nov 25, 2022

Page view(s)

checked on Dec 1, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.