Can Statistical Relational Learning help in Sustainable Health?
|Sriraam Natarajan||Wake Forest University||[Home Page]|
Notice: Hosted by Rodrigo Braz.
Date: 2012-02-21 at 16:00
Location: EJ228 (SRI E building) (Directions)
Sustainability is defined as the framework to achieve higher quality of life for all people. The onset of diseases such as Coronary Heart disease (CHD), Alzheimer's Disease (AD) etc., however, hamper sustainable development and reduce the quality of life. So, predicting the occurence of such diseases would be the first step in the direction of preventive treatment planning.
Statistical Relational Learning (SRL) combines the powerful formalisms of probability theory and first-order logic to handle uncertainty in large, complex problems. In this talk, I illustrate the great potential SRL has to achieve sustainable health. Specifically, I will present SRL approaches for (1) Identifying young adults who are at high risk of developing CHD in middle and later life and (2) Identifying the set of patients who have or will have AD by analyzing their brain MRI images. I will start off by presenting a general approach for learning SRL models based on Functional-Gradient Boosting and later adapt this algorithm for the above mentioned challenging tasks. The algorithm is evaluated in two real studies and is demonstrated to produce state-of-the-art results in these two problems. This is an encouraging sign that sustainable health is achievable.
Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page.