International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Novel Approach for Disease Diagnosis using Knowledge Graphs and Cross-model Representation |
|---|---|
| ABSTRACT | The Disease Diagnosis System aims to assist in early and accurate detection of diseases by analyzing user-provided symptoms through text embeddings and knowledge graph–based reasoning. Traditional diagnostic systems often rely on keyword matching or predefined rules, which limit their ability to understand semantic relationships between medical terms. To overcome this, the proposed system integrates Natural Language Processing (NLP) techniques with a Knowledge Graph to capture the contextual meaning of symptoms and their associations with diseases. The input symptoms are first processed and transformed into vector embeddings, which are then compared with disease entities in the knowledge graph using cosine similarity and cross-modal representation methods. This enables the system to generate accurate and explainable disease predictions. The model provides a user-friendly interface for symptom input and displays the top probable diseases with corresponding confidence scores. Experimental results demonstrate that combining text embeddings with knowledge graph representation significantly improves diagnostic accuracy and interpretability |
| AUTHOR | DR. ARUN KUMAR G H, ARVINDRAJ D THEVAR, RASHMITHA K, TANUSHREE T, TARUN L V |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311095 |
| pdf/95_A Novel Approach for Disease Diagnosis using Knowledge Graphs and Cross-model Representation.pdf | |
| KEYWORDS |
