University/Organization
Department of Mathematical Sciences and Computational Science Program
University of Texas at El Paso
El Paso, Texas
Computational Science Program
University of Texas at El Paso
El Paso, Texas
Title
Statistical Data Mining Algorithms for the Prognosis of Diabetes and Autism
Synopsis:
The early detection of these diseases could help the prognosis and chance of survival significantly. This manuscript is devoted to the application of Machine Learning (ML) technique to Diabetes and Autism disease data. Several important variables that cause diabetes and autism disease are studied in this work. We propose three supervised machine learning (ML) techniques, which can predict with great accuracy the likelihood of diabetes and autism in patients. These techniques allow computers to learn and to order the important variables that causes the diseases. We predict the test data based on the key variables and compute the prediction accuracy using the Receiver Operating Characteristic (ROC) curve to train a good classifier. The results suggest that the ML techniques are effective in classifying the patients regarding diabetes and autism disorder. Similar methodology can also be applied to other diseases such as Cancer and Heart Disease data.