Cancer is a serious and often fatal disease, widespread in the developed world. One of the most common methods of treating cancer is chemotherapy with toxic drugs. These drugs themselves can often have debilitating or life-threatening effects on patients undergoing chemotherapy. Clinicians attempting to treat cancer are therefore faced with the complex problem of how to balance the need for tumor treatment against the undesirable and dangerous side effects that the treatment may cause.

In this chapter we will consider ways in which evolutionary algorithms (EAs) can be used to assist clinicians in developing approaches to chemotherapy that offer improvements over current clinical practice. Section 12.2 provides a general introduction into the nature of cancer in its many forms. In Section 12.3 we explain how chemotherapy is used to control or reverse tumor growth by exposing cells to the action of toxic drugs. The section explores the complexity that clinicians face in managing toxic side effects and the process of clinical optimization that leads to the treatments conventionally used in practice. In order to apply computational power to this problem, it is first necessary to generate in silico models that, to an acceptable degree, can be relied upon to simulate the growth of cancerous tumors and the effect upon them of chemotherapy. Section 12.4 describes the process of modeling tumor growth and its response to chemotherapy while Section 12.5 develops mathematical