Optimal drug dosage regimens in cancer chemotherapy with neural networks

Abstract

2134 Background: An important problem in cancer chemotherapy is the design of drug dosage regimens such that at the end of treatment, the tumor burden is minimized, and the benefits are balanced against the toxic effects. We propose an approach based on neural networks (NN) control to optimize chemotherapy regimens. Methods: The tumor growth and the effect of chemotherapy are modeled by a modified Gompertz differential equation. The drugs' pharmacokinetic is modeled by differential equations composed by delivery and elimination rates. We impose constraints on the drugs' dose size and on the cumulative drugs' effect - AUC. The tumor size is forced to reduce by at least 50% at the end of every 3 weeks, as the probability of emergence of drug resistant cells is supposed to increases with the mutation rate and the size of the tumor. The task of the NN is to compute the optimal dosage regimens necessary to attain the mathematically formulated therapeutic goal satisfying all the constraints. Results: The therap...