A Comprehensive Study on Data Mining Techniques used in Bioinformatics for Breast Cancer Prognosis

Rapid growth of genomics and proteomics in biology has resulted in exponential growth of data which needs sophisticated computational analysis to discover intelligence. Research on computational biology or bioinformatics with application of data mining focuses on leveraging bioinformatics to address many real world problems in healthcare domain. Breast cancer is the second most lethal type of cancer causing death of woman. Many researchers contributed towards early detection, prognosis and better treatment of breast cancer in the last two decades causing decline of mortality rate. However, the breast cancer problem is still alarming and needs further research in the area of betterment of detection and prediction besides methods for treating it. This is the motivation behind this research work which is aimed at proposing a framework for breast cancer prognosis which includes susceptibility or risk assessment, recurrence or redevelopment of the cancer after resolution, and survivability. New algorithms are proposed and implemented for risk assessment, recurrence and survivability predictions. These algorithms are integrated with the proposed framework for making an application can demonstrate the proof of concept. Latest SEER linked datasets and datasets from American Cancer Society are used for empirical study. The framework with underlying mechanisms becomes useful tool for breast cancer prognosis. Such tool can discover valuable business intelligence from biomedical data which can help in devising strategies and making well-informed decisions in healthcare domain. Its impact on the society is significant when the framework provides efficient prognosis and help physicians and stakeholders by rendering quality services.