Please use this identifier to cite or link to this item: https://gnanaganga.inflibnet.ac.in:8443/jspui/handle/123456789/15695
Full metadata record
DC FieldValueLanguage
dc.contributor.authorJagan, S-
dc.contributor.authorParthasarathi, H-
dc.contributor.authorLondhe, G V-
dc.contributor.authorSrinivas, K-
dc.contributor.authorManchanda, M-
dc.contributor.authorKrishna, G R-
dc.date.accessioned2024-05-29T08:53:05Z-
dc.date.available2024-05-29T08:53:05Z-
dc.date.issued2024-
dc.identifier.citationVol. 30, No. 1; pp. 81-91en_US
dc.identifier.issn1310-4772-
dc.identifier.urihttps://scibulcom.net/en/article/QmwrzYdijXsyZcAUqr65-
dc.identifier.urihttp://gnanaganga.inflibnet.ac.in:8080/jspui/handle/123456789/15695-
dc.description.abstractHepatic cancer and particularly hepatocellular carcinoma leads to larger global health concerns with the highest mortality and morbidity rates. Precision medicine provides an exact solution for individual patients with their disease. The mechanism of hepatic cancer progression and identification of prognostic indications for personalized therapeutic interpolations are obtained through tissue microenvironment analysis and molecular profiling. The proposed system involves the extraction and identification of critical prognostic factors from molecular datasets using deep learning with hybrid optimization techniques such as ant colony optimization and genetic algorithm. The important objective of this innovation is to identify the intricate interplay between genetic, epigenetic and microenvironment factors within the cancer tissues. This is initiated through a multi-omics approach, which involves genomics, epigenomics, transcriptomics and proteomics data. These obtained datasets are preprocessed in order to obtain consistency in the system. Various external noise factors and dimensions are reduced using feature extraction techniques to extract the necessary information attributes. The hybrid optimization techniques are initiated to provide optimal features for accurate prognostic predictions. The integration of GA and ACO helps in enhancing the exploration and exploitation of the feature space. The validation process is performed on a large dataset, which contains the exact information of hepatic cancer patients. The observed prognostic features are calculated for consistency and robustness with clinical relevance. The patient outcomes are trained and tested using selected features for identifying the prognostic values of tissue microenvironment analysis. The uniqueness of hybrid optimization techniques is assessed through a comparative analysis of the proposed system using existing models. Thus precision medicine is developed through the personalization of a patient’s condition in hepatic cancer. Thus the accuracy of the prognostic predictions is obtained through the complex interrelationship between the molecular attributes and the tissue microenvironment. © 2024, Scibulcom Ltd.. All rights reserved.en_US
dc.language.isoenen_US
dc.publisherJournal of the Balkan Tribological Associationen_US
dc.publisherScibulcom Ltd.en_US
dc.subjectDeep Learningen_US
dc.subjectHepatic Canceren_US
dc.subjectHybrid Optimization Techniquesen_US
dc.subjectPrecision Medicineen_US
dc.subjectTissue Microenvironmental Analysisen_US
dc.titleDevelopment of Precision Medicine for Hepatic Cancer Evolving Molecular Profiling Techniques Through Artificial Intelligenceen_US
dc.typeArticleen_US
Appears in Collections:Journal Articles

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.