ABSTRACT

There are numerous deep learning approaches used to anticipate large-scale data analysis in different domains. Prescriptive modeling is a difficult undertaking in healthcare, but can eventually assist in solving problems and making prompt judgments with high data on the condition and treatment of patients. This article addresses predictive analytics and six alternative algorithms for the teaching of machines in healthcare. For experimental purposes, a people's clinical history set of data is gathered and the data set contains six distinct labeled compounds of machine-learning methods. The efficiency and precision of the capabilities provided are examined and contrasted. A comparison of the various machine learning techniques employed in this study shows which algorithm is most suitable for diabetic prevision. This research is designed to support physicians and clinicians in advanced diabetic diagnosis utilizing convolutional neural networks. Keywords: Dataset Analytics; Machine Learning; Health clinic; Labeled compounds; K-means; Healthcare
Publication date: 01/11/2021

https://ijbpas.com/pdf/2021/November/MS_IJBPAS_2021_NOV_SPCL1123.pdf

Download PDF
https://doi.org/10.31032/IJBPAS/2021/10.11.1123