Lectures and seminars Faculty event: Yunyang Deng

Title 

Machine Learning for Cancer Risk Prediction: Applications to Cervical and Colorectal Precancers and Cancers in Sweden

Abstract

Machine learning, together with large-scale health data, provides new opportunities for individualized cancer risk prediction and more targeted prevention. In this seminar, I will present two applications of machine learning for cancer risk prediction using Swedish register data. First, I will introduce our recently completed study developing random forest models to predict the risk of high-grade cervical lesions or worse. The study demonstrates how routinely collected cervical screening, HPV-related, and sociodemographic information can be used for risk prediction. I will then present our ongoing work on predicting colorectal precancer and cancer among people with HIV. We are developing random survival forest models incorporating HIV-related factors, comorbidities, and sociodemographic characteristics. Together, these studies may illustrate the potential of machine learning for cancer risk prediction, as well as the practical and methodological challenges involved in developing clinically relevant prediction models.

About the speaker

Yunyang Deng is a postdoctoral researcher at MEB. His research focuses on cancer epidemiology and prevention, with particular interests in HPV vaccination, cervical cancer screening, and machine learning–based risk prediction using nationwide health register data.

Faculty lunch

Join the faculty event in Wargentin! After the seminar, the faculty lunch will be served in Ljusgården. The faculty lunches are intended for employees at MEB, and a monthly net salary deduction of 260 SEK will be made for those who work here 20% or more. If you have any questions about the lunch or specific dietary needs due to allergies, etc., please contact internservice@meb.ki.se. If you won’t be participating in the lunches for all or part of the spring term, our new routine is that you need to contact hr-support@meb.ki.se at the start of a new term, to be removed from the list. Retroactive adjustments will not be possible.  

Please, check the labeling on the salads not to take special diet foods that were pre-ordered by your colleagues.