Population-centric risk prediction modeling for gestational diabetes mellitus: A machine learning approach

The role of machine learning algorithms in detection of gestational diabetes; a narrative review of current evidence

Gestational Diabetes Mellitus (GDM) poses significant health risks to mothers and infants. Early prediction and effective management are crucial to improving outcomes. Machine learning techniques have emerged as powerful tools for GDM prediction. This review compiles and analyses the available studies to highlight key findings and trends in the application of machine learning for GDM prediction. A comprehensive search of relevant studies published between 2000 and September 2023 was conducted. Fourteen studies were selected based on their focus on machine learning for GDM prediction. These studies were subjected to rigorous analysis to identify common themes and trends. The review revealed several key themes. Models capable of predicting GDM risk during the early stages of pregnancy were identified from the studies reviewed. Several studies underscored the necessity of tailoring predictive models to specific populations and demographic groups. These findings highlighted the limitations of uniform guidelines for diverse populations. Moreover, studies emphasised the value of integrating clinical data into GDM prediction models. This integration improved the treatment and care delivery for individuals diagnosed with GDM. While different machine learning models showed promise, selecting and weighing variables remains complex. The reviewed studies offer valuable insights into the complexities and potential solutions in GDM prediction using machine learning. The pursuit of accurate, early prediction models, the consideration of diverse populations, clinical data, and emerging data sources underscore the commitment of researchers to improve healthcare outcomes for pregnant individuals at risk of GDM.

Prediction of gestational diabetes mellitus at the first trimester: machine-learning algorithms

PURPOSE

Short- and long-term complications of gestational diabetes mellitus (GDM) involving pregnancies and offspring warrant the development of an effective individualized risk prediction model to reduce and prevent GDM together with its associated co-morbidities. The aim is to use machine learning (ML) algorithms to study data gathered throughout the first trimester in order to predict GDM.

METHODS

Two independent cohorts with forty-five features gathered through first trimester were included. We constructed prediction models based on three different algorithms and traditional logistic regression, and deployed additional two ensemble algorithms to identify the importance of individual features.

RESULTS

4799 and 2795 pregnancies were included in the Xinhua Hospital Chongming branch (XHCM) and the Shanghai Pudong New Area People's Hospital (SPNPH) cohorts, respectively. Extreme gradient boosting (XGBoost) predicted GDM with moderate performance (the area under the receiver operating curve (AUC) = 0.75) at pregnancy initiation and good-to-excellent performance (AUC = 0.99) at the end of the first trimester in the XHCM cohort. The trained XGBoost showed moderate performance in the SPNPH cohort (AUC = 0.83). The top predictive features for GDM diagnosis were pre-pregnancy BMI and maternal abdominal circumference at pregnancy initiation, and FPG and HbA1c at the end of the first trimester.

CONCLUSION

Our work demonstrated that ML models based on the data gathered throughout the first trimester achieved moderate performance in the external validation cohort.

Development of machine learning models to predict gestational diabetes risk in the first half of pregnancy

BACKGROUND

Early prediction of Gestational Diabetes Mellitus (GDM) risk is of particular importance as it may enable more efficacious interventions and reduce cumulative injury to mother and fetus. The aim of this study is to develop machine learning (ML) models, for the early prediction of GDM using widely available variables, facilitating early intervention, and making possible to apply the prediction models in places where there is no access to more complex examinations.

METHODS

The dataset used in this study includes registries from 1,611 pregnancies. Twelve different ML models and their hyperparameters were optimized to achieve early and high prediction performance of GDM. A data augmentation method was used in training to improve prediction results. Three methods were used to select the most relevant variables for GDM prediction. After training, the models ranked with the highest Area under the Receiver Operating Characteristic Curve (AUCROC), were assessed on the validation set. Models with the best results were assessed in the test set as a measure of generalization performance.

RESULTS

Our method allows identifying many possible models for various levels of sensitivity and specificity. Four models achieved a high sensitivity of 0.82, a specificity in the range 0.72-0.74, accuracy between 0.73-0.75, and AUCROC of 0.81. These models required between 7 and 12 input variables. Another possible choice could be a model with sensitivity of 0.89 that requires just 5 variables reaching an accuracy of 0.65, a specificity of 0.62, and AUCROC of 0.82.

CONCLUSIONS

The principal findings of our study are: Early prediction of GDM within early stages of pregnancy using regular examinations/exams; the development and optimization of twelve different ML models and their hyperparameters to achieve the highest prediction performance; a novel data augmentation method is proposed to allow reaching excellent GDM prediction results with various models.

Effect of Gestational Weight Gain during the First Half of Pregnancy on the Incidence of GDM, Results from a Pregnant Cohort in Northern Greece

The aim of this study was to evaluate the effect of gestational weight gain (GWG) up to 23⁺⁶ weeks of gestation on the incidence of Gestational Diabetes Mellitus (GDM). A pregnant cohort of 5948 women in Northern Greece was recruited. Anthropometric features before and during pregnancy were recorded, the GWG by 23⁺⁶ weeks was calculated and a Generalized Linear Regression Model (GLM) with subgroup analyses based on weight status were computed. GDM was diagnosed in 5.5% of women. GLM results showed that GDM likelihood increased with maternal age (MA) and pre-pregnancy BMI (aOR: 1.08, 95%CI: [1.06, 1.11] and aOR: 1.09, 95%CI: [1.09, 1.11], respectively). Ιn the normal pre-pregnancy weight group, when the extra weight gain was >8 kgs, the odds of GDM increased (OR: 2.13, 95%CI: [0.98, 4.21], p = 0.03). Women with pre-pregnancy level 2 clinical obesity (OB2 pre) (BMI > 35 and <40 kg/m²) that shifted to OB3 category (BMI ≥ 40 kg/m²) had an increased GDM likelihood (OR: 4.85, 95%CI: [1.50, 15.95]). Women of higher MA may require stricter monitoring for GDM from early pregnancy, while in obese women, recommended GWG may need to be re-evaluated, since refraining from any weight gain may have a preventive effect for GDM.

Effective Handling of Missing Values in Datasets for Classification Using Machine Learning Methods

The existence of missing values reduces the amount of knowledge learned by the machine learning models in the training stage thus affecting the classification accuracy negatively. To address this challenge, we introduce the use of Support Vector Machine (SVM) regression for imputing the missing values. Additionally, we propose a two-level classification process to reduce the number of false classifications. Our evaluation of the proposed method was conducted using the PIMA Indian dataset for diabetes classification. We compared the performance of five different machine learning models: Naive Bayes (NB), Support Vector Machine (SVM), k-Nearest Neighbours (KNN), Random Forest (RF), and Linear Regression (LR). The results of our experiments show that the SVM classifier achieved the highest accuracy of 94.89%. The RF classifier had the highest precision (98.80%) and the SVM classifier had the highest recall (85.48%). The NB model had the highest F1-Score (95.59%). Our proposed method provides a promising solution for detecting diabetes at an early stage by addressing the issue of missing values in the dataset. Our results show that the use of SVM regression and a two-level classification process can notably improve the performance of machine learning models for diabetes classification. This work provides a valuable contribution to the field of diabetes research and highlights the importance of addressing missing values in machine learning applications.

Cardiovascular Disease-Associated MicroRNAs as Novel Biomarkers of First-Trimester Screening for Gestational Diabetes Mellitus in the Absence of Other Pregnancy-Related Complications

We assessed the diagnostic potential of cardiovascular disease-associated microRNAs for the early prediction of gestational diabetes mellitus (GDM) in singleton pregnancies of Caucasian descent in the absence of other pregnancy-related complications. Whole peripheral venous blood samples were collected within 10 to 13 weeks of gestation. This retrospective study involved all pregnancies diagnosed with only GDM (n = 121) and 80 normal term pregnancies selected with regard to equality of sample storage time. Gene expression of 29 microRNAs was assessed using real-time RT-PCR. Upregulation of 11 microRNAs (miR-1-3p, miR-20a-5p, miR-20b-5p, miR-23a-3p, miR-100-5p, miR-125b-5p, miR-126-3p, miR-181a-5p, miR-195-5p, miR-499a-5p, and miR-574-3p) was observed in pregnancies destinated to develop GDM. Combined screening of all 11 dysregulated microRNAs showed the highest accuracy for the early identification of pregnancies destinated to develop GDM. This screening identified 47.93% of GDM pregnancies at a 10.0% false positive rate (FPR). The predictive model for GDM based on aberrant microRNA expression profile was further improved via the implementation of clinical characteristics (maternal age and BMI at early stages of gestation and an infertility treatment by assisted reproductive technology). Following this, 69.17% of GDM pregnancies were identified at a 10.0% FPR. The effective prediction model specifically for severe GDM requiring administration of therapy involved using a combination of these three clinical characteristics and three microRNA biomarkers (miR-20a-5p, miR-20b-5p, and miR-195-5p). This model identified 78.95% of cases at a 10.0% FPR. The effective prediction model for GDM managed by diet only required the involvement of these three clinical characteristics and eight microRNA biomarkers (miR-1-3p, miR-20a-5p, miR-20b-5p, miR-100-5p, miR-125b-5p, miR-195-5p, miR-499a-5p, and miR-574-3p). With this, the model identified 50.50% of GDM pregnancies managed by diet only at a 10.0% FPR. When other clinical variables such as history of miscarriage, the presence of trombophilic gene mutations, positive first-trimester screening for preeclampsia and/or fetal growth restriction by the Fetal Medicine Foundation algorithm, and family history of diabetes mellitus in first-degree relatives were included in the GDM prediction model, the predictive power was further increased at a 10.0% FPR (72.50% GDM in total, 89.47% GDM requiring therapy, and 56.44% GDM managed by diet only). Cardiovascular disease-associated microRNAs represent promising early biomarkers to be implemented into routine first-trimester screening programs with a very good predictive potential for GDM.