[vc_row][vc_column][vc_column_text]
The team used machine learning to discover correlations between various lifestyle behaviors and two chronic illness: depression and cognitive dysfunction. They found a way to identify these diseases early on, and to provide recommendations for lifestyle changes in order to lessen their debilitating effects.
[/vc_column_text][vc_column_text]Team: Herbreteau Eléonore, Papanikolaou Vasileios, Ramesh Kapilesh, Shi Yiyu, Vyas Arpit
Advisor: Dr. Anil Aswani[/vc_column_text][vc_row_inner][vc_column_inner width=”2/3″][vc_column_text]Chronic diseases are the leading cause of death and disabilities in the United States. About half of all adults have had one or more chronic health conditions and these account for 86% of the US healthcare expenses.
Our project aims to identify correlations between people’s lifestyle behaviors and two chronic diseases, namely mental depression and cognitive dysfunction using machine learning approaches. We utilized advanced analytical tools and machine learning algorithms to accomplish this. The result is early identification of these chronic diseases and lifestyle change recommendation to minimize people’s exposure to them.
Example of most correlated features for depression:
- Smoking
- Moderate recreational activities
- Type of work done last week
- Minutes of sedentary activities
- Moderate work activities
[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/3″][vc_video link=”https://www.youtube.com/watch?v=BAv2sLQUzmU&feature=youtu.be”][vc_column_text]
Algorithms used:
- Logistic Regression
- Decision Tree
- Random Forest
- Clustering
- SVM
- Gradient Boosting
[/vc_column_text][/vc_column_inner][/vc_row_inner][vc_separator][vc_single_image image=”41112″ img_size=”full”][/vc_column][/vc_row]