In this project I performed statistical tests with STATA to predict the risk of diabetes with certain explanatory variables, namely: Insulin Serum Concentration after 2hours, Plasma Glucose concentration, Age Group and Smoking Status
Here, I developed a web scraping module to extract certain articles from PubMed given a set of keywords and a window of publication. I extracted the articles into a csv file, and created a visualization module to show the trend of publications per month
In this project, I performed machine learning: random forest, boosting, svm linear and radial to predict Parkinson's disease diagnoses with patient vocal samples. Lastly, I compared model accuracy, sensitivity and specificity rates for each model to see which model predicted Alzheimer's better.
View my data visualization projects in Tableau.