The Impact of the SMOTE Method on Machine Learning and Ensemble Learning Performance Results in Addressing Class Imbalance in Data Used for Predicting Total Testosterone Deficiency in Type 2 Diabetes Patients

Aug 6, 2026

Diabetes Mellitus requires long-term metabolic management, and hypogonadism serves as a clinical and biochemical indicator of testosterone deficiency. This study analyzes how machine learning (ML) and ensemble learning (EL) classifiers predict testosterone deficiency in patients with type 2 diabetes while addressing class imbalance. Using 3397 patients (1886 with type 2 diabetes), the workflow applies outlier and missing-value analyses plus SMOTE for minority-class synthetic sampling. Optimized traditional ML and EL models (MLP, RF, ELM, LR; ADA, XGBoost, SGB) are evaluated via grid search and stratified k-fold cross-validation. After SMOTE, sensitivity rises across classifiers, some models lose diagnostic accuracy, specificity drops, and F1 generally increases.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Background and Objective

Methods

Results

Conclusions

Introduction

Diabetes Mellitus and Type 2 Diabetes

Hypogonadism and Testosterone Deficiency

Methods and Data Preparation

Dataset and Participants

Preprocessing (LOF and Missing Values)

SMOTE for Class Imbalance

Base and Ensemble Classifiers

Article The Impact of the SMOTE Method on Machine Learning and Ensemble Learning Performance Results in Addressing Class Imbalance in Data Used for Predicting Total Testosterone Deficiency in Type 2 Diabetes Patients Mehmet Kivrak 1,*, Ugur Avci 2, Hakki Uzun 3 and Cuneyt Ardic 4 Citation: Kivrak, M.; Avci, U.; Uzun, H.; Ardic, C. The Impact of the SMOTE Method on Machine Learning and Ensemble Learning Performance Results in Addressing Class Imbalance in Data Used for Predicting Total Testosterone Deficiency in Type 2 Diabetes Patients. Diagnostics 2024, 14, 2634. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics14232634 Academic Editor: Dechang Chen Received: 15 October 2024 Revised: 13 November 2024 Accepted: 18 November 2024 Published: 22 November 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Faculty of Medicine, Biostatistics and Medical Informatics, Recep Tayyip Erdogan University, Rize 53100, Türkiye 2 Faculty of Medicine, Endocrinology and Metabolism, Recep Tayyip Erdogan University, Rize 53100, Türkiye; [ugur.avci@erdogan.edu.tr](ugur.avci@erdogan.edu.tr) 3 Faculty of Medicine, Urology, Recep Tayyip Erdogan University, Rize 53100, Türkiye; [hakki.uzun@erdogan.edu.tr](hakki.uzun@erdogan.edu.tr) 4 Faculty of Medicine, Primary Care Physician, Recep Tayyip Erdogan University, Rize 53100, Türkiye; [cuneyt.ardic@erdogan.edu.tr](cuneyt.ardic@erdogan.edu.tr) * [Correspondence: mehmet.kivrak@erdogan.edu.tr](Correspondence: mehmet.kivrak@erdogan.edu.tr) Abstract: Background and Objective: Diabetes Mellitus is a long-term, multifaceted metabolic condition that necessitates ongoing medical management. Hypogonadism is a syndrome that is a clinical and/or biochemical indicator of testosterone deficiency. Cross-sectional studies have reported that 20–80.4% of all men with Type 2 diabetes have hypogonadism, and Type 2 diabetes is related to low testosterone. This study presents an analysis of the use of ML and EL classifiers in predicting testosterone deficiency. In our study, we compared optimized traditional ML classifiers and three EL classifiers using grid search and stratified k-fold cross-validation. We used the SMOTE method for the class imbalance problem. Methods: This database contains 3397 patients for the assessment of testosterone deficiency. Among these patients, 1886 patients with Type 2 diabetes were included in the study. In the data preprocessing stage, firstly, outlier/excessive observation analyses were performed with LOF and missing value analyses were performed with random forest. The SMOTE is a method for generating synthetic samples of the minority class. Four basic classifiers, namely MLP, RF, ELM and LR, were used as first-level classifiers. Tree ensemble classifiers, namely ADA, XGBoost and SGB, were used as second-level classifiers. Results: After the SMOTE, while the diagnostic accuracy decreased in all base classifiers except ELM, sensitivity values increased in all classifiers. Similarly, while the specificity values decreased in all classifiers, F1 score increased. The RF classifier gave more successful results on the base-training dataset. The most successful ensemble classifierin the training dataset was the ADA classifier in the original data and in the SMOTE data. In terms of the testing data, XGBoost is the most suitable model for your intended use in evaluating model performance. XGBoost, which exhibits a balanced performance especially when the SMOTE is used, can be preferred to correct class imbalance. Conclusions: The SMOTE is used to correct the class imbalance in the original data. However, as seen in this st

FAQs

What problem does the SMOTE method address in this study?

SMOTE is used to correct class imbalance by generating synthetic samples of the minority class for better minority-class prediction.

Which classifiers are evaluated for predicting total testosterone deficiency?

The study tests base classifiers (MLP, RF, ELM, LR) and ensemble classifiers as second-level models (ADA, XGBoost, SGB).

What changes occur in performance metrics after applying SMOTE?

After SMOTE, sensitivity increases in all classifiers, specificity decreases in all classifiers, diagnostic accuracy decreases in most base models except ELM, and F1 score increases overall.

Aug 6, 2026

Upload by Ava Thompson