Longitudinal datasets provide a unique view of the evolution of a disease over both time and space. Using these datasets, we are building complex data visualization tools that can be easily understood by all researchers, medical providers, and patients. The system that we are developing will provide a way for various institutions to share and integrate their own data with others in an effort to better understand the dynamics of each disease. The forecasting models that we are building from these datasets will help us to answer several questions such as:
1. Is cancer progression predictable? Is it random? Can we quantify the predictability/randomness?
2. How does treatment affect the pathways of progression? How does it affect the speed of progression?
3. What are the most common pathways from liver disease to liver cancer? Who is most at risk?
4. Will metastatic adrenal gland resection in lung cancer provide similar benefits as metastatic liver resection in colon cancer?
Support provided by the Big Data – Scientist Training Enhancement Program (BD-STEP) in collaboration with the Department of Veterans Affairs (VA) and the National Cancer Institute.