Multi-objective Optimization and Feedback-based Chemotherapy Drug Scheduling

Cancer is a major global health issue, causing significant suffering and deaths worldwide. To minimize the adverse effects of cancer and optimize the effectiveness of chemotherapy, the implementation of chemotherapy dose scheduling procedures is necessary for treatment. By administering the proper amount of chemotherapy drug dose, the treatment can maintain optimal therapeutic levels in the body while providing enough period for healthy cells to recover. Furthermore, cell cycle-specific chemotherapy enhances treatment outcomes by targeting dividing cancer cells at specific cell cycle phases, resulting in improved efficacy and reduced toxicity to normal cells. This study proposes a novel approach combining a multi-objective particle swarm optimization (MOPSO) with a feedback generator to develop a cell cycle-specific chemotherapy drug dose scheduling system. The multi-objective optimization algorithm considers conflicting objectives such as targeting cancerous cells, preserving normal cells, and minimizing toxicity. The feedback generator plays a significant role by assessing the impact of the optimized drug doses and adjusting them to ensure the desired number of normal cells. The system incorporates a comprehensive cell-cycle-specific model to monitor relevant parameters throughout chemotherapy. Extensive simulations and comparative assessments with existing computational models validate the superior effectiveness of our proposed approach over other methods reported in related studies.