Early Diabetes Prediction: A Comparative Study Using Machine Learning Techniques

Poly, Tahmina Nasrin; Islam, Md. Mohaimenul; Li, Yu-Chuan

doi:10.3233/shti220752

Cited by 6 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its importance is highlighted by the startling data, which show that 1.37 million people worldwide died from diabetes in 2017 and almost 450 million individuals were diagnosed with the disease [2]. Over 100 million persons in the US suffer with diabetes, and by 2020, it ranked as the seventh most common cause of death in the nation [3].…”

Section: Background To the Studmentioning

confidence: 99%

“…It's important to bear in mind that, like any scientific research, these studies have their own set of limitations. [2] introduces a data mining-based method for T2DM prediction, utilizing improved Logistic Regression with Multilayer Perception (LRMLP) and Naïve Bayes algorithms with preprocessing techniques. However, the study falls short in including key parameters like specificity and the area under the receiver operating characteristic curve (AUC-ROC), which are essential for a comprehensive assessment of the model's performance.…”

Section: Improving Patient Outcomes Depends On Type II Diabetes Early...mentioning

confidence: 99%

See 1 more Smart Citation

A Logistic Regression-Based Technique for Predicting Type II Diabetes

Babatunde,

Balogun

et al. 2024

AIMS Research Journal

View full text Add to dashboard Cite

In recent years, diabetes has emerged as one of the main causes of death for people. The spread of unhealthy foods, sedentary lifestyles, and eating habits have all contributed to the annual increase in the incidence of diabetes. A diabetes prediction model can help with clinical management decision-making. Diabetes prevention may be aided by being aware of potential risk factors and early detection of high-risk individuals. Numerous diabetes prediction models have been created. The size of the data set to be used was an issue in earlier research, but more recent studies have incorporated the use of high-quality, trustworthy data sets, such as the Vanderbilt and PIMA India data sets. Recent research has demonstrated that a few variables, including glucose, pregnancy, body mass index (BMI), the function of the diabetic pedigree, and age, can be used to predict Type II diabetes. Machine learning models of these parameters can be used to accurately predict the chance of the disease occurring as it was investigated in this study. In order to predict Type II diabetes, this study used the machine learning method Logistic Regression. Keywords: Type II Diabetes, Logistic Regression, Hyperparameter and Prediction ACity FCSI Journal Citation Format Babatunde, R.S., Babatunde, A.N., Balogun, B.F., Abdulrahman, T.A., Umar, E., Ajiboye, R.A., Mohammed, S.B., Oke, A.A. & Obiwusi, K.Y. (2024): A Logistic Regression-Based Technique for Predicting Type II Diabetes. Journal of Computational Sciences & Informatics. Academic City University College, Accra, Ghana. Vol 4 No. 1 March, 2024 Pp 1-14. https://www.isteams.net/ghanabespoke2023. dx.doi.org/10.22624/AIMS/FCSIJ/2024/P1

show abstract

Section: Background To the Studmentioning

confidence: 99%

Section: Improving Patient Outcomes Depends On Type II Diabetes Early...mentioning

confidence: 99%

A Logistic Regression-Based Technique for Predicting Type II Diabetes

Babatunde,

Balogun

et al. 2024

AIMS Research Journal

View full text Add to dashboard Cite

show abstract

“…accuracy of 100% was unmatched. Based on these results, it is plausible that an easyto-use questionnaire coupled with a machine-learning algorithm might be used to identify people with undiagnosed DM [9] accurately.…”

Section: Introductionmentioning

confidence: 97%

Early Diagnosis of Diabetes: A Comparison of Machine Learning Methods

Salem Alzboon,

Subhi Al-Batah,

Alqaraleh

et al. 2023

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Detection and management of diabetes at an early stage is essential since it is rapidly becoming a global health crisis in many countries. Predictions of diabetes using machine learning algorithms have been promising. In this work, we use data collected from the Pima Indians to assess the performance of multiple machine-learning approaches to diabetes prediction. Ages, body mass indexes, and glucose levels for 768 patients are included in the data set. The methods evaluated are Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbors, Naive Bayes, Support Vector Machine, Gradient Boosting, and Neural Network. The findings indicate that the Logistic Regression and Neural Network models perform the best on most criteria when considering all classes together. The SVM, Random Forest, and Naive Bayes models also receive moderate to high scores, suggesting their strength as classification models. However, the kNN and Tree models show poorer scores on most criteria across all classes, making them less favorable choices for this dataset. The SGD, AdaBoost, and CN2 rule inducer models perform the poorest when comparing all models using a weighted average of class scores. The results of the study suggest that machine learning algorithms may help predict the onset of diabetes and for detecting the disease at an early stage.

show abstract