Author(s): Golghate Ashish Anil and Manav Thakur

Abstract: This study focuses on enhancing cancer survival rate predictions by utilizing longitudinal data analysis combined with advanced feature engineering techniques. Cancer prognosis is inherently complex due to the dynamic nature of disease progression and the variation in individual patient responses to treatments. By analyzing time-series clinical data, such as patient demographics, tumor characteristics, treatment history, and response indicators over time, the study aims to develop more accurate and personalized predictive models. Advanced feature engineering methods are employed to extract meaningful patterns from raw medical data, which are then used to train machine learning algorithms like Random Forest, XGBoost, and Support Vector Machines. The study evaluates model performance using statistical metrics such as accuracy, sensitivity, specificity, and AUC-ROC to ensure reliable survival predictions. In addition, the research integrates qualitative insights from healthcare professionals and cancer survivors through structured surveys, providing real-world context to the findings and improving the interpretability of the predictive models. This mixed-methods approach bridges the gap between computational modeling and human-centered perspectives, contributing to the development of personalized cancer care strategies. Ultimately, the research aims to enhance clinical decision-making by providing tools for early identification of high-risk patients and facilitating tailored treatment plans. The outcomes of this study have the potential to significantly improve cancer prognosis accuracy and patient outcomes.

DOI: 10.33545/27075907.2025.v6.i1b.94

Pages: 120-126 | Views: 96 | Downloads: 43

Download Full Article: Click Here