DocumentCode
707332
Title
Big data analytics of genomic and clinical data for Diagnosis and Prognosis of Cancer
Author
Patel, Veeresh ; Adhil, Mohammad ; Bhardwaj, Trishansh ; Talukder, Asoke K.
Author_Institution
Dept. of Comput. Sci. & Eng., Nat. Inst. of Technol., Warangal, India
fYear
2015
fDate
11-13 March 2015
Firstpage
611
Lastpage
615
Abstract
Sooner the Cancer is diagnosed, better the chances of overall survival. Diagnosis and Prognosis are the two major challenging aspects which are to be addressed in treating cancer. Early diagnosis helps treating cancer before they become metastatic; in addition, prognosis will reveal the survival pattern for different attributes i.e., for specific drug, before and after the treatment. Better the diagnosis and prognosis, better the treatment outcome for Cancer. The very high-throughput technologies like NGS generatesexome data of a single cancer patient that ranges from 10 Giga bytes to 15 Giga bytes. This large amount of Omics data can only be analyzed and interpreted using data-sciences techniques and big-data computational models. Here we present a clinical expert system for predicting the outcome of cancer patients from big-data genomics using the inference engine which makes decision from our in-house knowledge base.
Keywords
Big Data; cancer; data analysis; expert systems; genomics; inference mechanisms; medical computing; patient diagnosis; NGS generatesexome data; big data analytics; big-data computational models; big-data genomics; cancer diagnosis; cancer prognosis; clinical data; clinical expert system; data-sciences techniques; high-throughput technologies; in-house knowledge base; inference engine; metastatic; omics data; Bioinformatics; Cancer; Databases; Drugs; Expert systems; Genomics; Diagnosis; Prognosis; knowledge base;
fLanguage
English
Publisher
ieee
Conference_Titel
Computing for Sustainable Global Development (INDIACom), 2015 2nd International Conference on
Conference_Location
New Delhi
Print_ISBN
978-9-3805-4415-1
Type
conf
Filename
7100322
Link To Document