Machine Learning Prediction Models for Gestational Diabetes Mellitus: Meta-analysis (Preprint)

Abstract

BACKGROUND Gestational diabetes mellitus (GDM) is a kind of common endocrine metabolic diseases, including carbohydrate intolerance of variable severity during pregnancy. The incidence rates of GDM related complications and adverse pregnancy outcomes will decline partly due to early screening. Nowadays, machine learning (ML) models have found an increasingly wide utilization, whether for risk factors selection or early prediction of GDM. OBJECTIVE Though many models for pregnancy women have been proposed and verified through experimental studies, few of them have been clinically recognized. Since seldom publication has evaluated the performance of ML prediction models for GDM, this meta-analysis was conducted and put forward some suggestions for model providers, users and policy makers basing on the findings. METHODS Four reliable electronic databases were searched for studies that developing ML prediction models for GDM in the general population, instead of the high-risk groups. The Prediction model Risk of Bias Assessment Tool (PROBAST) was used as a novel tool assessing the risk of bias of ML models. The software program Meta-Disc 1.4 was utilized to perform the Meta-analysis and determination of heterogeneity. To limit the influence of heterogeneity, results of sensitivity analysis, meta-regression and subgroups analysis were provided. RESULTS Twenty-five studies were analyzed which included women older than 18 years without a history of vital disease. The pooled area under receiver operating characteristic curve (AUC) and the pooled sensitivity and specificity for ML to predict GDM was 0.8492, 0.69 (95%CI: 0.68–0.69, P < .001, I2 = 99.6%)and 0.75 (95%CI:0.75–0.75, P < .001, I2 = 100%) respectively. As one of the most employed ML methods, logistic regression (LR) achieved an overall pooled AUC at 0.8151 while non-LR models performed better with an overall polled AUC at 0.8891. Additionally, maternal age, family history of diabetes, BMI and fasting blood glucose were the four mostly used features of models established by various feature selection methods. CONCLUSIONS ML methods could be cost-effective screening methods for GDM. The importance of quality assessment and unified diagnostic criteria should be further emphasized.

Clinical First-Trimester Prediction Models for Gestational Diabetes Mellitus: A Systematic Review and Meta-Analysis

“…Our findings are in line with previous studies, where 14 constructed prediction model studies were evaluated in a systematic review by Lamain-de Ruiter et al (2017), although not using the PROBAST tool, and in their quality evaluation, most of the model studies had a high risk of bias. In addition, Zhang et al (2022) compared prediction models constructed by machine learning methods in a recent meta-analysis, and their results for the apparent model discrimination performance of logistic regression models were comparable and slightly higher than those we observed (AUC = 0.8151). However, Zhang et al (2022) did not conduct a meta-analysis of model performance for a single model that has received several external validations, so we are unable to compare our results with theirs at this time.…”

“…In addition, Zhang et al (2022) compared prediction models constructed by machine learning methods in a recent meta-analysis, and their results for the apparent model discrimination performance of logistic regression models were comparable and slightly higher than those we observed (AUC = 0.8151). However, Zhang et al (2022) did not conduct a meta-analysis of model performance for a single model that has received several external validations, so we are unable to compare our results with theirs at this time.…”

“…Despite not conducting a quantitative analysis of model performance to identify which models have the greatest validity, the included studies assessed the methodological quality and found them to be of moderate to poor quality in terms of methodological quality. Accordingly, Zhang et al (2022) conducted a meta-analysis of machine learning prediction models for gestational diabetes mellitus. They included 25 prediction model development studies that predicted from 0 to 28 weeks before the diagnosis, but no external validation studies were included.…”