Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Diabetes

Date Submitted: Jul 26, 2021
Date Accepted: Mar 21, 2022

The final, peer-reviewed published version of this preprint can be found here:

Machine Learning–Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study

Kumar M, Ang LT, Ho C, Soh SE, Tan KH, Chan JKY, Godfrey KM, Chan SY, Chong YS, Eriksson JG, Feng M, Karnani N

Machine Learning–Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study

JMIR Diabetes 2022;7(3):e32366

DOI: 10.2196/32366

PMID: 35788016

PMCID: 9297138

Machine Learning Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes

  • Mukkesh Kumar; 
  • Li Ting Ang; 
  • Cindy Ho; 
  • Shu E Soh; 
  • Kok Hian Tan; 
  • Jerry Kok Yen Chan; 
  • Keith M Godfrey; 
  • Shiao-Yng Chan; 
  • Yap Seng Chong; 
  • Johan G Eriksson; 
  • Mengling Feng; 
  • Neerja Karnani

ABSTRACT

Background:

The increasing prevalence of Gestational Diabetes Mellitus (GDM) is concerning as women with GDM are at high risk of later Type 2 Diabetes (T2D). The magnitude of this risk highlights the importance of intervening early to prevent progression of GDM to T2D. Rates of postpartum screening are sub-optimal, often as low as 13% in Asian countries. The lack of preventive care through structured postpartum screening in several healthcare systems and low public awareness are key barriers.

Objective:

In this study, we developed a machine learning model for early prediction of postpartum T2D following routine antenatal GDM screening. The early prediction of postpartum T2D during prenatal care would enable strategies to effectively implement diabetes prevention interventions.

Methods:

Data from 561 pregnancies in Singapore’s most deeply phenotyped mother-offspring cohort study, Growing Up in Singapore Towards healthy Outcomes (GUSTO), was used for predictive modeling. We used a CatBoost gradient boosting algorithm, and the Shapley feature attribution framework for model building and interpretation of T2D risk attributes.

Results:

A high performance prediction model for postpartum T2D, comprising of 2 mid-gestation features (mid-pregnancy BMI after gestational weight gain; diagnosis of GDM) was developed [AUC: 0.86 (95% CI 0.72, 0.99)]. Pre-pregnancy BMI alone was inadequate in predicting postpartum T2D risk [AUC: 0.62 (0.39, 0.86)].

Conclusions:

Mid-gestation weight gain effects combined with the metabolic derangements underlying GDM during pregnancy signal future T2D risk in Singaporean women. Further studies will be required to examine the influence of metabolic adaptations in pregnancy on postpartum maternal metabolic health outcomes. The state-of-the art machine learning model can be leveraged as a rapid risk stratification tool during prenatal care. Clinical Trial: ClinicalTrials.gov NCT01174875


 Citation

Please cite as:

Kumar M, Ang LT, Ho C, Soh SE, Tan KH, Chan JKY, Godfrey KM, Chan SY, Chong YS, Eriksson JG, Feng M, Karnani N

Machine Learning–Derived Prenatal Predictive Risk Model to Guide Intervention and Prevent the Progression of Gestational Diabetes Mellitus to Type 2 Diabetes: Prediction Model Development Study

JMIR Diabetes 2022;7(3):e32366

DOI: 10.2196/32366

PMID: 35788016

PMCID: 9297138

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.