Integration of Clinical and Genomic Data for Decision Support in Cancer

Integration of Clinical and Genomic Data for Decision Support in Cancer

Yorgos Goletsis, Themis P. Exarchos, Nikolaos Giannakeas, Markos G. Tsipouras, Dimitrios I. Fotiadis
DOI: 10.4018/978-1-60960-561-2.ch212
(Individual Chapters)
No Current Special Offers


In this article, we address decision support for cancer by exploiting clinical data and identifying mutations on tumour suppressor genes. The goal is to perform data integration between medicine and molecular biology by developing a framework where clinical and genomic features are appropriately combined in order to handle cancer diseases. The constitution of such a decision support system is based on (a) cancer clinical data and (b) biological information that is derived from genomic sources. Through this integration, real time conclusions can be drawn for early diagnosis, staging and more effective cancer treatment.
Chapter Preview


Clinical Decision Support Systems are active knowledge systems which use two or more items of patient data to generate case-specific advice (Fotiadis, Goletsis, Likas, & Papadopoulos, 2006). CDSSs are used to enhance diagnostic efforts and include computer based programs that, based on information entered by the clinician, provide extensive differential diagnosis, staging (if possible), treatment, follow-up, and so forth. CDSSs consist of an inference engine that is used to associate the input variables with the target outcome. This inference engine can be developed based either on explicit medical knowledge, expressed in a set of rules (knowledge based systems) or on data driven techniques, such as machine learning (Mitchel, 2006) and data mining (intelligent systems) (Tan, Steinbach, & Kumar, 2005). CDSSs require the input of patient-specific clinical variables (medical data) and as a result provide patient specific recommendation.

Complete Chapter List

Search this Book: