top of page


Predicting cancer outcomes using machine learning models

Priti Singh,Pankaj Dholaniya,Ikenna Nometa,Gbocho Masato Terasaki


In this project, we aim to apply knowledge from the boot camp to analyze data from the Health Information National Trends Survey (HINTS) by the National Cancer Institute. HINTS gathers nationally representative data on the American public’s knowledge, attitudes, and use of cancer- and health-related information. This data monitors changes in health communication and technology to develop more effective communication strategies for diverse populations.
We will use survey data from the second cycle of HINTS 4, collected between October 2012 and January 2013. This dataset includes responses from 3,630 individuals across the US and contains 357 features. See for more information.
Our investigation examines the relationship between cancer incidence and three key factors: Demographics, Utilization of Health Information Technology, and Medical History. We aim to identify features that best predict cancer outcomes using classification models and evaluate their performance.

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page