Prediction of postpartum prediabetes by machine learning methods in women with gestational diabetes mellitus
Durga Parkhi,
Nishanthi Periyathambi,
Yonas Ghebremichael-Weldeselassie,
Vinod Patel,
Nithya Sukumar,
Rahul Siddharthan,
Leelavati Narlikar,
Ponnusamy Saravanan
Affiliations
Durga Parkhi
Populations, Evidence, and Technologies, Division of Health Sciences, University of Warwick, Coventry, UK
Nishanthi Periyathambi
Populations, Evidence, and Technologies, Division of Health Sciences, University of Warwick, Coventry, UK; Department of Diabetes, Endocrinology, and Metabolism, George Eliot Hospital, Nuneaton, UK
Yonas Ghebremichael-Weldeselassie
Populations, Evidence, and Technologies, Division of Health Sciences, University of Warwick, Coventry, UK; School of Mathematics and Statistics, The Open University, Milton Keynes, UK
Vinod Patel
Department of Diabetes, Endocrinology, and Metabolism, George Eliot Hospital, Nuneaton, UK
Nithya Sukumar
Populations, Evidence, and Technologies, Division of Health Sciences, University of Warwick, Coventry, UK; Department of Diabetes, Endocrinology, and Metabolism, George Eliot Hospital, Nuneaton, UK
Rahul Siddharthan
Department of Computational Biology, The Institute of Mathematical Sciences, Chennai, India
Leelavati Narlikar
Department of Data Science, Indian Institute of Science Education and Research, Pune, India
Ponnusamy Saravanan
Populations, Evidence, and Technologies, Division of Health Sciences, University of Warwick, Coventry, UK; Department of Diabetes, Endocrinology, and Metabolism, George Eliot Hospital, Nuneaton, UK; Corresponding author
Summary: Early onset of type 2 diabetes and cardiovascular disease are common complications for women diagnosed with gestational diabetes. Prediabetes refers to a condition in which blood glucose levels are higher than normal, but not yet high enough to be diagnosed as type 2 diabetes. Currently, there is no accurate way of knowing which women with gestational diabetes are likely to develop postpartum prediabetes. This study aims to predict the risk of postpartum prediabetes in women diagnosed with gestational diabetes. Our sparse logistic regression approach selects only two variables – antenatal fasting glucose at OGTT and HbA1c soon after the diagnosis of GDM – as relevant, but gives an area under the receiver operating characteristic curve of 0.72, outperforming all other methods. We envision this to be a practical solution, which coupled with a targeted follow-up of high-risk women, could yield better cardiometabolic outcomes in women with a history of GDM.
