Multi-objective optimisation for multi-drug chemotherapy scheduling

This paper presents a multi-drug chemotherapy scheduling method for cancer treatment using multi-objective optimisation technique. Cancer cells, very often, grows resistance to a drug if it is administered alone for a long time and drug resistance eventually causes failure to treatment in most cases. The adaptation of multi-drug treatment in cancer increases the drug performance by reducing the drug resistance. But care must be taken to design the multi-drug scheduling so as to equilibrium the drug beneficial and adverse side effects of the treatment. Conventional clinical methods can hardly find optimum dosages of drugs that can kill maximum cancerous cells with minimum toxic side effects. This is because of the inherent conflict between the cell killing and the toxic side effects in case of cancer. This paper presents a novel method of multi-drug scheduling using multi-objective genetic algorithm (MOGA) that can trading-off between the cell killing and toxic side effects during the whole period of treatment. A close-loop control method, namely Integral-Proportional-Derivative (I-PD) is designed to control dosages of drugs to be infused to the patient's body and MOGA is used to find suitable/acceptable parameters of the controller. A cell compartments model is developed and used to describe the effects of the drugs on different type of cells, plasma drug concentration and toxic side effects. Results show that drug scheduling obtained through the proposed method can reduce the tumour size more than 99% with relatively lower toxic side effects. Moreover, the drug dosage and drug concentration remain at low level throughout the whole period.