Adaptive neural networks control of drug dosage regimens in cancer chemotherapy

This paper presents the optimal control chemotherapy scheduling in cancer using neural networks. Unlike conventional methods, the proposed neural networks methodology, feedback linearization, is simple and capable of automatically finding the optimal solutions for complex cancer chemotherapy problems. Also, it allows the application of the well developed standard linear control techniques. Simulation results produce excellent control of drug dosage regimens in cancer chemotherapy, which are better than the solutions published in literature. Using specific chemotherapy concepts like dose size, dose intensity, and cumulative dose, allows the design of realistic dosage regimens from the optimal control computed by neural networks.