Estimating the risk of gestational diabetes mellitus based on the 2013 WHO criteria: a prediction model based on clinical and biochemical variables in early pregnancy

Benhalima, Katrien; Crombrugge, Paul Van; Moyson, Carolien; Verhaeghe, Johan; Vandeginste, Sofie; Verlaenen, Hilde; Vercammen, Chris; Maes, Toon; Dufraimont, Els; Block, Christophe De; Jacquemyn, Yves; Mekahli, Farah; Clippel, Katrien De; Bruel, Annick Van den; Loccufier, Anne; Laenen, Annouschka; Minschart, Caro; Devlieger, Roland; Mathieu, Chantal

doi:10.1007/s00592-019-01469-5

Cited by 40 publications

(41 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most models showed moderate discrimination, with AUCs mostly above 0.70, which is consistent with previous findings [21,22,24,29]. Previous studies have investigated models derived from electronic health records for the predictions of GDM in machine learning models or conventional logistic regressions, but these studies included fewer participants than ours, did not compare the two methods, involved limited variables, or did not comprehensively estimate the performance of discriminations and calibrations [18,21,22,24,29]. The current studies extend these previous studies by validating predictive ratio cutoff points of 0.3 and 0.7 originating from general maternal characteristics and biochemical data by comparing the performance of machine learning and traditional logistic regression models for the prediction of GDM.…”

Section: Comparisons Andsupporting

confidence: 89%

See 1 more Smart Citation

Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study

Xiong

Zhou

et al. 2020

Journal of Diabetes Research

View full text Add to dashboard Cite

Background. Gestational diabetes mellitus (GDM) contributes to adverse pregnancy and birth outcomes. In recent decades, extensive research has been devoted to the early prediction of GDM by various methods. Machine learning methods are flexible prediction algorithms with potential advantages over conventional regression. Objective. The purpose of this study was to use machine learning methods to predict GDM and compare their performance with that of logistic regressions. Methods. We performed a retrospective, observational study including women who attended their routine first hospital visits during early pregnancy and had Down’s syndrome screening at 16-20 gestational weeks in a tertiary maternity hospital in China from 2013.1.1 to 2017.12.31. A total of 22,242 singleton pregnancies were included, and 3182 (14.31%) women developed GDM. Candidate predictors included maternal demographic characteristics and medical history (maternal factors) and laboratory values at early pregnancy. The models were derived from the first 70% of the data and then validated with the next 30%. Variables were trained in different machine learning models and traditional logistic regression models. Eight common machine learning methods (GDBT, AdaBoost, LGB, Logistic, Vote, XGB, Decision Tree, and Random Forest) and two common regressions (stepwise logistic regression and logistic regression with RCS) were implemented to predict the occurrence of GDM. Models were compared on discrimination and calibration metrics. Results. In the validation dataset, the machine learning and logistic regression models performed moderately (AUC 0.59-0.74). Overall, the GBDT model performed best (AUC 0.74, 95% CI 0.71-0.76) among the machine learning methods, with negligible differences between them. Fasting blood glucose, HbA1c, triglycerides, and BMI strongly contributed to GDM. A cutoff point for the predictive value at 0.3 in the GBDT model had a negative predictive value of 74.1% (95% CI 69.5%-78.2%) and a sensitivity of 90% (95% CI 88.0%-91.7%), and the cutoff point at 0.7 had a positive predictive value of 93.2% (95% CI 88.2%-96.1%) and a specificity of 99% (95% CI 98.2%-99.4%). Conclusion. In this study, we found that several machine learning methods did not outperform logistic regression in predicting GDM. We developed a model with cutoff points for risk stratification of GDM.

show abstract

Section: Comparisons Andsupporting

confidence: 89%

“…Recent prediction models for GDM have been developed using conventional regression analyses [17][18][19]. However, machine learning, a data analysis technique that develops algorithms to predict outcomes by "learning" from data, is increasingly emphasized as a competitive alternative to regression analysis.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study

Xiong

Zhou

et al. 2020

Journal of Diabetes Research

View full text Add to dashboard Cite

show abstract

“…Thus, elevated triglycerides at early gestation may be regarded as a potential biomarker for prediabetic disorders that will lead to hyperglycemia when pregnancy progresses and the physiologic environment changes. Although the establishment of early risk assessment tools is challenging due to the heterogeneity of the disease [25], a recent study by Benhalima et al found that the inclusion of biomarkers such as triglycerides improves the accuracy of risk assessment models to predict the risk for the development of GDM at the start of pregnancy, as also underlined by the data of our study [26]. Of note, we observed no association between cholesterol (LDL, HDL or total cholesterol) with GDM development.…”

Section: Discussionsupporting

confidence: 75%

Association between maternal triglycerides and disturbed glucose metabolism in pregnancy

et al. 2021

View full text Add to dashboard Cite

Aims Dyslipidemia in pregnancy is associated with adverse pregnancy outcomes as elevated triglycerides might be considered as a risk factor for hyperglycemia and gestational diabetes. As only a few studies have addressed the association between maternal triglycerides and glucose metabolism, we aimed to explore the pathophysiologic associations of moderate hypertriglyceridemia and maternal glucose metabolism in pregnancy. Methods Sixty-seven pregnant women received a detailed metabolic characterization at 12+0–22+6 weeks of gestation by an extended 2h-75g OGTT (oral glucose tolerance test); with measurements of glucose, insulin and C-peptide at fasting and every 30 min after ingestion and assessment of triglycerides at fasting state. All examinations were repeated at 24+0–27+6 weeks of gestation. Results Elevated triglycerides in early gestation were associated with insulin resistance and β-cell dysfunction. Mean glucose concentrations during the OGTT in early pregnancy were already higher in women with hypertriglyceridemia as compared to women with triglycerides in the normal range. A higher degree of insulin resistance and increased OGTT glucose levels were also observed when metabolic assessments were repeated between 24 and 28 weeks of gestation. Of note, elevated triglycerides at early gestation were associated with development of gestational diabetes by logistic regression (odds ratio: 1.16, 95%CI: 1.03–1.34, p=0.022 for an increase of 10 mg/dl). Conclusions Hypertriglyceridemia at the start of pregnancy is closely related to impaired insulin action and β-cell function. Women with hypertriglyceridemia have higher mean glucose levels in early- and mid-gestation. Pregnant women with elevated triglycerides in early pregnancy are at increased risk of developing gestational diabetes.

show abstract

“…Advancing age [ 6 , 7 ], a family history of diabetes [ 7 ], and ethnicity of a non-Anglo-European decent [ 8 ] are well-established risk factors for GDM. Multiparity is also associated with an increased risk of GDM [ 6 ], although advancing maternal age and weight gain both during and between pregnancies seem to mediate the effect [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

The impact of educational attainment on the occurrence of gestational diabetes mellitus in two successive pregnancies of Finnish primiparous women: a population-based cohort study

et al. 2020

View full text Add to dashboard Cite

Aims To assess the impact of educational attainment on the occurrence and recurrence of gestational diabetes mellitus (GDM) in two successive pregnancies in primiparous women. Methods This is a population-based observational cohort study including all 2347 Finnish women without previously diagnosed diabetes, aged ≥ 20 years from the city of Vantaa, Finland, who gave birth to their first and second child between 2009 and 2015. National registries provided data on study participants. We divided the population into four groups according to the presence of GDM in the two pregnancies (GDM−/−, n = 1820; GDM−/+, n = 223; GDM+/−, n = 113; GDM+/+, n = 191). Results The occurrence of GDM in the first pregnancy was 13.0% ( n = 304) and 17.6% ( n = 414) in the second. The recurrence rate of GDM was 62.8%. The four groups did not differ in relation to educational attainment ( p = 0.11). In multinomial regression analysis, educational attainment protected from GDM in the second pregnancy [relative risk ratio 0.93 (95% confidence interval (CI) 0.86–0.99) per year of schooling for being GDM−/+ compared with GDM−/−]. In multivariate logistics models, prepregnancy body mass index at the first pregnancy [odds ratio (OR) 1.53 per 1-standard deviation (SD) (95% CI 1.22–1.91)], first-born birth weight z -score [OR 1.30 per 1-SD (95% CI 1.00–1.67)], and inter-pregnancy weight change [OR 1.66 per 1-SD (95% CI 1.27–2.16)], but not educational attainment, predicted recurrence of GDM. Conclusions The recurrence rate of GDM was high. Education protected from novel GDM in the second pregnancy, but was not associated with GDM recurrence.

show abstract

Estimating the risk of gestational diabetes mellitus based on the 2013 WHO criteria: a prediction model based on clinical and biochemical variables in early pregnancy

Cited by 40 publications

References 33 publications

Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study

Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study

Association between maternal triglycerides and disturbed glucose metabolism in pregnancy

The impact of educational attainment on the occurrence of gestational diabetes mellitus in two successive pregnancies of Finnish primiparous women: a population-based cohort study

Contact Info

Product

Resources

About