Improved modelling of breast cancer cells using machine learning heuristic algorithms

Computational and machine learning frameworks have greatly contributed to early diagnosis and rapid therapeutic interventions due to breakthroughs in science and technology. This study aims to develop a mathematical model that utilizes machine learning and integrates both innate and adaptive immunological components to examine the progression of breast cancer. The proposed framework utilizes a set of ordinary differential equations to represent the interactions between breast cancer cells, cytotoxic T lymphocytes, T-helper cells, and macrophages. We used machine learning optimization techniques to enhance the computational framework, enabling accurate modeling of the dynamic alterations occurring in the tumor microenvironment. This approach also considers the different properties and responses of immune cells. Our validated results, obtained using metaheuristic algorithms and sensitivity analysis, provide significant insights into the correlation between the advancement of breast cancer and the innate and adaptive immune systems. This study supports the theory that advanced programming tools may enhance healthcare systems by offering reliable techniques for understanding and possibly controlling the progression of cancer via the manipulation of the immune system.