Treffer: Diabetes and heart disease prediction using machine learning classifiers based on Weka, python.

Diabetes and heart disease are some of the most critical diseases for human beings. Lots of people are suffering from these two diseases. Early-stage diagnosing of these diseases is very essential for doctors and patients. Machine learning (ML)can play a vital role in this section. To this, ML algorithms can analyze the health data using various Data analytics tools. In this paper, we have found out the prediction of heart disease and diabetes patients. To validate the experimental analysis, we analyzed two datasets named diabetes dataset and heart disease prediction dataset in two popular analytics tools including WEKA and Python. Also, we used 6 supervised machine learning (SML) classifiers named Random forest (RF), Naive Bayes (NB), Decision Tree Classifier (DTC), Logistic regression (LR), K-NN, and support vector machine (SVM) for predicting heart and diabetes diseases. As a performance scale, we used accuracy, precision, recall, and F1 measure. In the case of diabetes disease, Random Forest outperforms the performance metrics by achieving 81% accuracy in python and DTC outperforms by placing 65% in Weka. On the other hand, in case of heart disease, LR achieves the highest score of 75% accuracy in Python and DTC gets the highest value of 79% accuracy in Weka. At last, the comparison result is shown between WEKA and Python tools in this paper. We got better results in Python than in the WEKA tool for the diabetes data set. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)