Statistical Methods and Artificial Intelligence Deep Learning to Identify the Risk Factors of Colorectal Cancer
Principal Investigator
Name
Ranju Karki
Degrees
Ph.D.(seeking)
Institution
University of South Florida
Position Title
Student(Doctoral Candidate)
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-684
Initial CDAS Request Approval
Oct 27, 2020
Title
Statistical Methods and Artificial Intelligence Deep Learning to Identify the Risk Factors of Colorectal Cancer
Summary
We are going to utilize artificial intelligence deep learning and advance statistical methods to identify the individual risk factors and their interaction that causes colorectal cancer. Identification of the influential risk factors is necessary for preventing possible causes of disease. Also, it helps to design treatment protocols and increase awareness about colorectal cancer.
We also want to rank the risk factor and their interactions according to their percent contribution to colorectal cancer. This helps us to find significantly contributing risk factors. We also going to perform surface response analysis to identify the behavior of the risk factor and its interactions this will minimize colorectal cancer. If possible, we will identify the probability distribution of survival time and shape the parametric and nonparametric models. These statistical models could provide crucial clues about colorectal cancer and help to make a decision about the disease and implement prevention.
We also want to rank the risk factor and their interactions according to their percent contribution to colorectal cancer. This helps us to find significantly contributing risk factors. We also going to perform surface response analysis to identify the behavior of the risk factor and its interactions this will minimize colorectal cancer. If possible, we will identify the probability distribution of survival time and shape the parametric and nonparametric models. These statistical models could provide crucial clues about colorectal cancer and help to make a decision about the disease and implement prevention.
Aims
1. We are going to utilize artificial intelligence deep learning and advance statistical methods to identify the individual risk factors and their interaction that causes colorectal cancer.
2. We want to rank the risk factor and their interactions according to their percent contribution to colorectal cancer.
3. We are going to perform surface response analysis to identify the behavior of the risk factor and its interactions.
Collaborators
Dr. Chris P. Tsokos (Ph.D. Supervisor)
Distinguished University Professor of Mathematics and Statistics
Department of Mathematics and Statistics, University of South Florida
4202 E. Fowler Ave., CMC 366
Tampa, Florida 33620
Tel. (813) 974-9734
Fax: (813) 974-2700
Email: ctsokos@usf.edu
Website: http://www.math.usf.edu/~profcpt/