Detecting critical supervision intervals during in silico chemotherapy treatments

Abstract

Nowadays, in many countries, the number of newly registered cancer patients keeps growing despite the recent advancements in the medical field. For this reason, every advancement that could potentially get humanity one step closer to fighting this disease is valuable. The future goal of our research is to create a device capable of measuring the tumor parameters of the patients and applying doses continuously. However, with the current technology, it is not possible since the measurement of the tumor states is not automatized. This study presents an intermediate step towards that goal by creating methods that can identify critical time intervals on which the treatments of patients should be supervised by investigating the tumor state in a hospital. To generate an optimal therapy, we used a genetic algorithm capable of generating a therapy for a group of patients with similar parameters. We used a mathematical model that contains the unique patient parameters to simulate the reaction of the tumor to the injected doses. According to the results, we can reduce the time spent in the hospital to almost a third of the original treatment time, based on in silico tumor simulations.