Predictive Modeling of Patient State and Therapy Optimization

Dr. Zoran Obradovic
Director, Data Analytics and Biomedical Informatics Center, Temple University


Abstract

This talk will discuss the results of our ongoing project aimed to develop and validate effective predictive modeling technology to achieve the following sepsis treatment related aims for acute inflammation on high dimensional and noisy data at a clinically relevant scale: (1) Personalized sepsis therapy optimization for an individual patientís state improvement; (2) Early diagnosis of sepsis and accurate detection of change in the state of sepsis, and (3): Gene expression analysis for sepsis biomarkers identification. These aims are addressed by developing advanced methods for analysis of temporal dependencies in high dimensional multi-source sepsis related data, which show significant mortality reduction in severe sepsis patients. This is joint research with my Postdoctoral Associate Dr. Vladan Radosavljevic and my Ph.D. students Mohamed Ghalwash, Dusan Ramljak, and Kosta Ristovski.