Diabetes Prediction Using Machine Learning

  • Dr. Kayal Vizhi, Aman Dash


Diabetes has evolved as one the most dangerous threat to the human world. Many are becoming its victims and are unable to come out of it regardless of the fact that they are working to avoid it for growing further. Cloud Computing and Internet of Things (IoT) are two tools that play a very important role in today’s life regarding many aspects and purposes including healthcare monitoring of patients and elderly society. Diabetes Healthcare Monitoring Services are very important nowadays because and that to remote healthcare monitoring because physically going to hospitals and standing in a queue is very ineffective version of patient monitoring. If a patient has very chronic diabetes and he spends his/her time standing in a queue anything dangerous can happen to him/her at any instance of time. So, this paper came up with smart sensors and different machine learning algorithms like xgboost algorithm, random forest. Diabetes can also act as a means for other diseases like heart attack, kidney damage and somewhat blindness.  This paper can make use of various machine learning algorithms such as support vector machine, linear regression, decision tree, xgboost and random forest with the help of which can easily find out the total efficiency and accuracy of predicting that a human will suffer from diabetes or not. There are variously many traditional methods which are totally different from software methods that can diagnose diabetes and predict pre conditions of diabetic patients. Diabetics is caused due to a vast uphill in the blood portion containing glucose. There is an optimization scheme available through the use of train test split and K fold cross validation using Sklit learn method.

Keywords: Indian Pima Diabetes Dataset, Kaggle, Diabetes Prediction through Machine Learning Schemes.

How to Cite
Dr. Kayal Vizhi, Aman Dash. (2020). Diabetes Prediction Using Machine Learning. International Journal of Advanced Science and Technology, 29(06), 2842 - 2852. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/13795