Answers are grounded in this paper and cite their sources.
In the current situation diabetes is the leading cause of death with the ranking of ninth among all diseases worldwide [1]. An estimation of approximately 1.5 million deaths by this disease [1]. The reports suggest that the diseases can be handled in better way if it is detected in the early stages There are several algorithms including machine learning algorithms can be helpful in disease diagnosis and detection including diabetes These algorithms are knearest neighbors (KNN), logistic regression (LR), Nave Bayes (NB), support vector machine (SVM), Decision Tree (DT), random forest (RF), convolutional neural network (CNN), etc. The clustering algorithms are also helpful in the same for these purposes like k-means and fuzzy c-means (FCM). The main aim of these approaches is to detect and predict the diseases in the early stage with higher accuracy. So, the main aim of this paper is to apply the combination of clustering and classification. In this approach k-means and the combination of kpoints have been considered for the betterment. Clustering algorithm will work better if the centroid estimation is accurate. So, our main aim is to improve the estimation through k-points.
No takes yet. Share an insight, caveat, or question.
A 2021 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: