Résumé

Predicting Gestational Diabetes Mellitus (GDM) is crucial for
pregnant women to enable regular monitoring of their blood sugar levels and
adherence to a healthy diet. Early intervention can significantly lower the risk
of developing this condition. To assess this risk, Machine Learning (ML) and
Deep Learning techniques are employed. However, traditional ML models often
face challenges in accurately predicting GDM risk due to the complex
processing required to optimize their hyperparameters for the best performance.
This study presents a feature selection for GDM prediction using AutoML-XAI
techniques (Automatic Machine Learning – eXplainable Artificial Intelligence
techniques) approach, which aims to automatically predict GDM risk as
accurate as possible while providing meaningful interpretations of the
predictive results used in feature selection. The AutoML models generated
utilize a Kaggle dataset and several combinations of features selected based on
their scores of importance determinated with XAI techniques such as SHAP

(Shapley Additive Explanations) and LIME (Local Interpretable Model-
agnostic Explanations). The proposed approach of autoML and features

selection with XAI techniques leads to the creation of a precise, efficient, and
easily interpretable model which surpasses other machine learning models in
predicting GDM risk without the need for human intervention. The scores of
importance of features are involved in the feature selection process and
multiple AutoML models are generated and assessed, with the optimal AutoML
model being established automatically.

Résumé

Gestational Diabetes Mellitus (GDM) is a type of diabetes that develops during pregnancy. It is important for pregnant women to monitor their blood sugar levels regularly and follow a healthy diet. However, early intervention can greatly reduce risk of this type of diabetes. Machine Learning and Deep Learning techniques are utilized to predict this risk based on an individual's symptoms, lifestyle, and medical history. By identifying key features such as age, insulin, body mass index, and glucose levels, machine learning models such as Random Forest and XGBoost are used in this research work to classify patients at risk of a gestational diabetes. In addition, we propose an explainable feature selection approach to improve the accuracy of machine learning models for GDM prediction. This method involves iteratively eliminating features that exhibit a negative contribution as determined by the SHAP (Shapley Additive explanations) feature attribution explanations for the model’s predictions

Résumé

Gestational Diabetes Mellitus (GDM) is a type of diabetes that develops during pregnancy. It is important for pregnant women to monitor their blood sugar levels regularly and follow a healthy diet. However, early intervention can greatly reduce risk of this type of diabetes. Machine Learning and Deep Learning techniques are utilized to predict this risk based on an individual's symptoms, lifestyle, and medical history. By identifying key features such as age, insulin, body mass index, and glucose levels, machine learning models such as Random Forest and XGBoost are used in this research work to classify patients at risk of a gestational diabetes. In addition, we propose an explainable feature selection approach to improve the accuracy of machine learning models for GDM prediction. This method involves iteratively eliminating features that exhibit a negative contribution as determined by the SHAP (Shapley Additive explanations) feature attribution explanations for the model’s predictions.