Scholarlink

<p>Diabetes represents a persistent and financially demanding challenge that increases the susceptibility of individuals to develop depression. Consequently, effective management of the co-occurrence of diabetes and depression is likely to significantly improve the quality of patient care. This research study presents a comprehensive comparative analysis of eight distinct machine learning (ML) algorithms to predict depression among individuals with diabetes. The algorithms evaluated include logistic regression (LR), k-nearest neighbors (KNN), decision tree (DT), random forest (RF), Adaptive Boosting (AdaBoost), support vector machine (SVM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). The study utilizes a dataset from Morocco, specifically curated for this purpose, and employs the Synthetic Minority Over-sampling Technique (SMOTE) to balance the dataset. Feature selection is performed using ExtraTreesClassifier, while hyperparameter tuning is accomplished through a grid search approach. The obtained results showcase promising performance of the ML algorithms in predicting depression among individuals with diabetes. Notably, the RF and CatBoost classifiers emerge as top performers, achieving an impressive accuracy rate of 82%. These findings hold significant implications for further research, aiming to refine prediction models in this context. This study underscores the considerable potential of ML algorithms in effectively predicting depression disorders in individuals living with diabetes. The remarkable accuracy demonstrated by the RF and CatBoost classifiers highlights their potential viability as reliable tools, particularly in clinical settings. Ongoing investigations are essential to validate and extend these results, exploring the real-world applicability of these models. Ultimately, this research contributes to advancing the management and overall well-being of individuals with diabetes and coexisting depressive disorders.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative analysis of machine learning algorithms for predicting depression among individuals with diabetes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月9日

查看全文
  • Hind Bourkhime,
  • Noura Qarmiche,
  • Soumaya Benmaamar,
  • Nada Lazar,
  • Mohammed Omari,
  • Mohamed Berraho,
  • Nabil Tachfouti,
  • Samira El Fakir,
  • Hanan El Ouahabi,
  • Nada Otmani

摘要

Diabetes represents a persistent and financially demanding challenge that increases the susceptibility of individuals to develop depression. Consequently, effective management of the co-occurrence of diabetes and depression is likely to significantly improve the quality of patient care. This research study presents a comprehensive comparative analysis of eight distinct machine learning (ML) algorithms to predict depression among individuals with diabetes. The algorithms evaluated include logistic regression (LR), k-nearest neighbors (KNN), decision tree (DT), random forest (RF), Adaptive Boosting (AdaBoost), support vector machine (SVM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). The study utilizes a dataset from Morocco, specifically curated for this purpose, and employs the Synthetic Minority Over-sampling Technique (SMOTE) to balance the dataset. Feature selection is performed using ExtraTreesClassifier, while hyperparameter tuning is accomplished through a grid search approach. The obtained results showcase promising performance of the ML algorithms in predicting depression among individuals with diabetes. Notably, the RF and CatBoost classifiers emerge as top performers, achieving an impressive accuracy rate of 82%. These findings hold significant implications for further research, aiming to refine prediction models in this context. This study underscores the considerable potential of ML algorithms in effectively predicting depression disorders in individuals living with diabetes. The remarkable accuracy demonstrated by the RF and CatBoost classifiers highlights their potential viability as reliable tools, particularly in clinical settings. Ongoing investigations are essential to validate and extend these results, exploring the real-world applicability of these models. Ultimately, this research contributes to advancing the management and overall well-being of individuals with diabetes and coexisting depressive disorders.