Detecting High-Risk Factors and Early Diagnosis of Diabetes Using Machine Learning Methods

Abstract

Diabetes is a chronic disease that can cause several forms of chronic damage to the human body, including heart problems, kidney failure, depression, eye damage, and nerve damage. There are several risk factors involved in causing this disease, with some of the most common being obesity, age, insulin resistance, and hypertension. Therefore, early detection of these risk factors is vital in helping patients reverse diabetes from the early stage to live healthy lives. Machine learning (ML) is a useful tool that can easily detect diabetes from several risk factors and, based on the findings, provide a decision-based model that can help in diagnosing the disease. This study aims to detect the risk factors of diabetes using ML methods and to provide a decision support system for medical practitioners that can help them in diagnosing diabetes. Moreover, besides various other preprocessing steps, this study has used the synthetic minority over-sampling technique integrated with the edited nearest neighbor (SMOTE-ENN) method for balancing the BRFSS dataset. The SMOTE-ENN is a more powerful method than the individual SMOTE method. Several ML methods were applied to the processed BRFSS dataset and built prediction models for detecting the risk factors that can help in diagnosing diabetes patients in the early stage. The prediction models were evaluated using various measures that show the high performance of the models. The experimental results show the reliability of the proposed models, demonstrating that k-nearest neighbor (KNN) outperformed other methods with an accuracy of 98.38%, sensitivity, specificity, and ROC/AUC score of 98%. Moreover, compared with the existing state-of-the-art methods, the results confirm the efficacy of the proposed models in terms of accuracy and other evaluation measures. The use of SMOTE-ENN is more beneficial for balancing the dataset to build more accurate prediction models. This was the main reason it was possible to achieve models more accurate than the existing ones.

Improving the Classification of PCNSL and Brain Metastases by Developing a Machine Learning Model Based on 18F-FDG PET

“…The method combines SOMTE with edited nearest neighbors (ENN), an under-sampling technique that removes the majority class to match the minority class [ 36 ]. The method has been used in several clinical studies [ 37 , 38 , 39 , 40 ].…”

Intelligent fuzzy system to assess the risk of type 2 diabetes and diagnosis in marginalized regions

“…Akanksha et al [26], through machine learning (ML), pinpoint the effects of some diabetes risk factors, such as BMI, blood pressure, and physical activity. Similarly, and also using ML, Ullah et al [27] detect risk factors and provide clinicians with a decision support system (SMOTE-ENN model) that can help them diagnose diabetes. The results are satisfactory to continue improving the existing methods of this global disease.…”

Diabetes Diagnosis through Machine Learning: Investigating Algorithms and Data Augmentation for Class Imbalanced BRFSS Dataset

“…We meticulously curated the most pertinent features for our study through an exhaustive review of existing literature (Robertson et al, 2011; Dinh et al, 2019; Hill-Briggs et al, 2021; Shriraam et al, 2021; Asiimwe et al, 2020; Budreviciute et al, 2020; Supakul et al, 2019; Ullah et al, 2022), resulting in a selection of 20 variables. Our independent variables encompass BMI, AGE, Income, Smoking, Blood Pressure, Cholesterol, Heart Disease, Asthma, Kidney Disease, Marital Status, Education, General Health Condition, Exercise, Arthritis, Depression, Food and Vegetable Consumption, Sex, and Diabetes as the dependent variable.…”