Using a Karnauph Model to Predict the Relationship between Smoking and Diabetes Type 2

In health care, artificial intelligence plays a crucial role in early detection and prevention of different diseases. Machine learning algorithms can analyze a huge amount of data in a short time to find a hidden pattern or to find a hidden relationship between the features used and the results, to predict or prevent some diseases. In this paper, we present the results of applying our proposed algorithm Karnauph algorithm on a real dataset collected about patients diagnosed as diabetics or not diabetics, to find the most important factors that influence the development of the disease. Our proposed algorithm works on binary data to predict the class of unclassified data. Our results show that the performance of our Karnauph algorithm in terms of accuracy, and precision is good, where the accuracy obtained in Karnauph algorithm is 90.2 % which is similar than the results obtained for other machine learning algorithms such as Ada-boost.