This project investigated and applied computational techniques to enlarge a pancreatic cancer database and to enhance the medical decision-making process supported by this database. The database was previously developed by the Department of Surgical Oncology of the University of Massachusetts Medical School in conjunction with the Department of Computer Science at WPI. We substantially increased the number of patients included in the database, and conducted data mining experiments. These experiments compared the accuracies of predictions made by medical doctors and by data mining methods for two separate patient outcomes: tumor malignancy and survival time after surgery. The results of our experiments show that data mining techniques can be used to enhance the quality of medical decisions.
Worcester Polytechnic Institute
Interactive Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.