Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Nutritional and Metabo lic Diseases and Conditions-Diabetes Mellitus is the subject of a report. Acco rding to news originating from Dinajpur, Bangladesh, by NewsRx correspondents, r esearch stated, "Diabetes is a persistent metabolic disorder linked to elevated levels of blood glucose, commonly referred to as blood sugar. This condition can have detrimental effects on the heart, blood vessels, eyes, kidneys, and nerves as time passes." Our news journalists obtained a quote from the research from Hajee Mohammad Dane sh Science and Technology University, "It is a chronic ailment that arises when the body fails to produce enough insulin or is unable to effectively use the ins ulin it produces. When diabetes is not properly managed, it often leads to hyper glycemia, a condition characterized by elevated blood sugar levels or impaired g lucose tolerance. This can result in significant harm to various body systems, i ncluding the nerves and blood vessels. In this paper, we propose a multiclass di abetes mellitus detection and classification approach using an extremely imbalan ced Laboratory of Medical City Hospital data dynamics. We also formulate a new d ataset that is moderately imbalanced based on the Laboratory of Medical City Hos pital data dynamics. To correctly identify the multiclass diabetes mellitus, we employ three machine learning classifiers namely support vector machine, logisti c regression, and k-nearest neighbor. We also focus on dimensionality reduction (feature selection-filter, wrapper, and embedded method) to prune the unnecessar y features and to scale up the classification performance. To optimize the class ification performance of classifiers, we tune the model by hyperparameter optimi zation with 10-fold grid search cross-validation. In the case of the original ex tremely imbalanced dataset with 70:30 partition and support vector machine class ifier, we achieved maximum accuracy of 0.964, precision of 0.968, recall of 0.96 4, F1-score of 0.962, Cohen kappa of 0.835, and AUC of 0.99 by using top 4 featu re according to filter method. By using the top 9 features according to wrapper- based sequential feature selection, the k-nearest neighbor provides an accuracy of 0.935 and 1.0 for the other performance metrics. For our created moderately i mbalanced dataset with an 80:20 partition, the SVM classifier achieves a maximum accuracy of 0.938, and 1.0 for other performance metrics."
NETL
NSTL