(584p) Model-Based Decision Support Tool for Personalized Treatment of Cancer

Model-based Decision Support Tool for Personalized Treatment of Cancer

Jayachandran Devaraj^a, Tuhina Ghanty^b, Doraiswami Ramkrishna^a,*

^a School of Chemical Engineering, Purdue University, 480 Stadium Mall Way, West Lafayette, IN 47907, USA

^bDepartment of Chemical Engineering, Indian Institute of Technology, Mumbai, India                    

^*Corresponding author at: School of Chemical Engineering, Purdue University, 480 Stadium Mall Way, West Lafayette, IN 47907, USA. Tel: +1 765 494 4066; fax: +1 765 494 0805; email: ramkrish@purdue.edu

Abstract

Personalized medicine has been in practice in some form or the other ever since medicine has been in existence. With the discovery of new complex diseases, elevated incidence and mortality rate of existing diseases, and advancements in high throughput technologies, the focus and importance on personalized medicine has been gaining momentum in the recent times. Every individual is unique both genetically and phenotypically. Hence, the gist of personalized medicine lies in evaluating genetic and biomolecular traits specific to a patient, followed by clinical decision making based upon the patient’s genetic and phenotypic make-up. Since several important processes interfere during the manifestation of gene sequence to molecular phenotypes and further into cellular responses, a holistic approach, integrating many levels of biomolecular entities and events, provides superior information for clinical decision making. Given the complexity of the biological processes and amount of information, it is impossible to reach a conclusion through simple deductive reasoning. Quantitative tools, suitably empowered by systems theoretic approach, could serve as a decision-support mechanism to physicians to quantitatively predict the response and adjust the dose for a given patient.

In this work, we present a model-based standalone GUI to quantitatively predict the clinical outcome for a specific patient and determine the optimal chemotherapeutic dose to achieve a desired clinical response. We demonstrate an application of such a tool using an important chemotherapeutic drug known as 6-Mercaptopurine in tailoring treatment for Leukemia patients.