| Abstrakt: |
One of the deadliest diseases, diabetes mellitus, affects a large number of people. Diabetes mellitus can be brought on by a number of reasons,including obesity, age, genetic diabetes, a poor diet, inactivity, high blood pressure, and others. Diabetes escalates the likelihood of acquiring various ailments, including heart and kidney disease, nerve damage, and visual issues. To diagnose diabetes and deliver suitable therapy, hospitals employ a range of tests. The healthcare industry benefits greatly from big data analytics due to the vast size of its databases. By utilizing big data analytics to examine extensive datasets, one can extract valuable insights, uncover concealed patterns and information, and generate accurate future predictions. This study presents a proposed model for the prediction of diabetes that incorporates a few extrinsic factors that contribute to the development of the disease along with more widely used indicators such as glycol level, body mass ratio (BMI), age, etc. This course covers data collection and analysis in order tospot patterns and trends that help with result prediction and evaluation. The dataset is described in the section below. This diabetes dataset contains 800 records and 10 characteristics. For this, a number of machine learning classification and ensemble approaches are utilized to anticipate diabetes using the Pima Indian Diabetes Dataset. A purposeful training method for computers and other machines is called machine learning. Various machine learning algorithms effectively provide information by building numerous classifications and ensemble models from collected datasets. [ABSTRACT FROM AUTHOR] |
