Prevalence and Early Prediction of Diabetes Using Machine Learning in North Kashmir: A Case Study of District Bandipora

Abstract

Diabetes is one of the biggest health problems that affect millions of people across the world. Uncontrolled diabetes can increase the risk of heart attack, cancer, kidney damage, blindness, and other illnesses. Researchers are motivated to create a Machine Learning methodology that can predict diabetes in the future. Exploiting Machine Learning Algorithms (MLA) is essential if healthcare professionals are able to identify diseases more effectively. In order to improve the medical diagnosis of diabetes this research explored and contrasts various MLA that can identify diabetes risk early. The research includes the analysis on real datasets such as a clinical dataset gathered from a doctor in the Indian district of Bandipora in the years April 2021–Feb2022. MLA are currently important in the healthcare sector due to their prediction abilities. Researchers are using MLA to improve disease prediction and reduce cost. In this Paper author developed a methodology using Machine Learning Algorithms for Diabetes Disease Risk Prediction in North Kashmir. Six MLA have been successfully used in the experimental study such as Random Forest (RF), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boost (GB), Decision Tree (DT), and Logistic Regression (LR). RF is the most accurate classifier with the uppermost accuracy rate of 98 percent followed by MLP (90.99%), SVM (92%), GBC (97%), DT (96%), and LR (69%), respectively, with the balanced data set. Lastly, this study enables us to effectively identify the prevalence and prediction of diabetes.

Stacking with Recursive Feature Elimination-Isolation Forest for classification of diabetes mellitus

“…Nevertheless, as evolution happens, humankind has started integrating computer technology with the healthcare system. The utilization of artificial intelligence assists healthcare providers to be more efficient in the diagnosis of patients, better healthcare delivery, and more patient eccentric [ 10 ]. Therefore, it would benefit everyone regardless of socioeconomic and geographical location.…”

Identifying diagnostic indicators for type 2 diabetes mellitus from physical examination using interpretable machine learning approach

“…For the construction of T2DM diagnostic models, the existing problems are as follows: (I) The effective extraction of T2DM diagnostic indicators through machine learning often relies on their interpretability ( 10 , 12 , 18 – 23 ). However, some of the current work lacks evaluation of important indicators, and some rely on third-party tools such as Shapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) ( 8 , 9 , 11 ), which may bring potential deviation in clinical understanding ( 24 ).…”

Analyze Important Features of PIMA Indian Database For Diabetes Prediction Using KNN

“…In terms of prediction, in addition to accuracy, the performance of calculations in training also needs to be improved. There are several datasets commonly used in machine learning research for diabetes, such as (1) the NHANES or National Health and Nutrition Examination Survey, a dataset that contains information on diabetes and other health conditions, obtained by CDC or the Centers for Disease Control and Prevention [5], (2) Global Health Observatory (GHO) data, a dataset belong to World Health Organization (WHO) that contains information on diabetes prevalence and other health indicators for countries around the world [6] (3) the ELSA (English Longitudinal Study of Ageing) database [7], (4) the Diabetes Data Set of 130-US hospitals from years 1999 to 2008, which contains over 100,000 hospital visits for diabetes and includes information on patient demographics, diagnosis, medications, and hospital outcomes [8], (5) The Framingham Heart Study, a long-term study that has collected data on cardiovascular disease risk factors, including diabetes, in a large population sample [9,10], (6) the German Diabetes Risk Score (DRS) dataset from the German National Cohort (NAKO Health Study) that contains information on diabetes risk factors such as age, sex, and weight, as well as lab test results and other health information [11], (7) The Pima Indian Diabetes dataset, which contains data from over 800 patients of Pima Indian heritage with diabetes [12], (8) Early Classification of Diabetes, a dataset that comprises of 520 observations, including 17 characteristics that are obtained from the Bangladesh patients at the Sylhet Diabetes Hospital through direct questionnaires and diagnosis results [13,14], (9) The National Diabetes Data Group (NDDG) dataset, which contains data from over 1,200 patients with diabetes and (10) the Hospital Frankfurt Germany Diabetes Data Set [15]. These datasets can be found on different sources, such as UCI Machine Learning Repository, Kaggle, and from the institutions that collected the data.…”