Predicting Patients' Responses to Treatment for Personalized Medicine

• Activity Number: 186
• Type: Contributed
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Biometrics Section
• Author(s): Wei-Jiun Lin*+ and James J. Chen
• Companies: Feng Chia University and NCTR/FDA
• Keywords: personalized medicine ; tailored treatment ; predictive biomarkers ; reproducibility

Abstract

One goal of personalized medicine is to provide right diagnosis and tailor medical treatment to individual needs. For the realization of personalized medicine, patients must be distinguished according to relevant differences in disease types, risk factors, and responses to therapy. This study proposed an algorithm to build prediction models that can predict patients' responses to a specific treatment and then the treatment can be provided to the specific cases. We showed that the developed model performed well for prediction from the real microarray data of lung cancer. The reproducibility of predition was also evaluated using four different data for applying the model to predict the future samples.