The goal of this project is to develop the Sherlock Big Data Knowledge Discovery and Analysis software product. This software will apply knowledge management to Big Data repositories that focus on lung cancer. This will assist researchers to develop better treatments and expand the life of lung cancer patients.
The data source for this research will be the Stage 2 Non-Small Cell Lung Cancer (NSCLC) big data repository. The software product will initially use the same data source. Using NSCLC as the primary data source, we will focus our research on extracting knowledge at a specific stage, or progression, of the disease. According to the American Cancer Society about 85% to 90% of lung cancers are NSCLC. This is where the software product can make the most difference.
Using an advanced algorithm, the Sherlock BigData-KDA™ product will examine Big Data repositories to uncover patterns and extract knowledge. This algorithm is based on the patent pending tacit-explicit knowledge capture algorithm (TEKCA™). TEKCA was developed as the result of the 2005 NSF SBIR Grant award.
Having the ability to use Sherlock to uncover NSCLC knowledge from large lung cancer repositories will provide researchers in hospitals, universities, and pharmaceutical companies with the ability to use Big Data to identify anomalies, discover new treatment combinations and enhance diagnostic decision making.
For cancer researchers, the knowledge made available through the use of the Sherlock BigData-KDA™ will enhance the ability to bring about new and innovative treatments including but not limited to vaccines, preventive measures and new drugs.