Affiliations: [a] Department of Computer Science and Engineering, Bharathiyar Institute of Engineering for Women, Salem, Tamil Nadu, India
| [b] Information Technology Department, College of Science, University of Warith Al-Anbiyaa, Karbala, Iraq
| [c] Computer Science Department, College of Computer Science and Information Technology, University of Kerbala, Karbala, Iraq
| [d] Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, Tamil Nadu, India
| [e] Department of Mathematics, VIT Bhopal, Bhopal
Correspondence:
[*]
Corresponding author. Sudhakar Sengan, Department of Computer Science and Engineering, PSN College of Engineering and Technology, Tirunelveli, 627152 Tamil Nadu, India, E-mail: [email protected].
Abstract: The medical domain faces unique challenges in Information Retrieval (IR) due to the complexity of medical language and terminology discrepancies between user queries and documents. While traditional Keyword-Based Methods (KBM) have limitations, the integration of semantic knowledge bases and concept mapping techniques enhances data organization and retrieval. Addressing the growing demands in the biomedical field, a novel medical Information Retrieval System (IRS) is proposed that employs Deep Learning (DL) and KBM. This system comprises five core steps: pre-processing of texts, document indexing using DL (ELMo) and KBM, advanced query processing, a BiLSTM-based retrieval network for contextual representation, and a KR-R re-ranking algorithm to refine document relevance. The purpose of the system is to give users improved biomedical search results through the integration of all of these techniques into a method that takes into consideration the semantic problems of medical records. An in-depth examination of the TREC-PM track samples from 2017 to 2019 observed an impressive leading MRR score of 0.605 in 2017 and a best-in-class rPrec score of 0.350 in 2019, proving how well able the system is to detect and rank relevant medical records accurately.
