Time-Series-Forcasting

Cancer proliferation is an inherently complex process, influenced by a myriad of factors such as the tumor microenvironment and the host immune system. Despite significant strides in cancer research, accurately modeling the temporal evolution of tumors remains a challenge. In this project, I sought to gain a deeper understanding of cancer growth dynamics that could enable decision-making for personalized cancer therapies. This study determines predictions using data from murine models of a metastatic variant of human triple-negative breast carcinoma. To examine tumor volume measurements over time, I applied three predictive models: Transformer, Artificial Neural Network, and Linear, to forecast the volume measurements for the next time step.