Computational intelligence methods in personalized pharmacotherapy

Abstract

Effective pharmacologic therapy of chronic diseases remains a challenge to physicians. Individual dose-response characteristics of patients may vary significantly across patient populations. In addition, due to the chronic nature of the process, they may change over time within individual patients as well. Current state of the art protocols for dose adjustment of pharmacologic agents rely heavily on data from drug approval process and physician’s expertise. However, they do not directly incorporate the wealth of knowledge hidden in patient data collected in the course of the treatment. In this chapter, we review the application of two Computational Intelligence methods, Artificial Neural Networks and Fuzzy Set Theory, to personalized pharmacologic treatment of a chronic condition using patient data stored in Electronic Medical Records. As the application example, we use anemia management in patients with renal failure. To demonstrate the potential of Computational Intelligence methods in improving the disease management, we discuss three human studies in which the discussed methods proved to be an effective decision support aid to the physician.