Developing Healthcare Knowledge Graphs through Graph Neural Networks
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P117Keywords:
Healthcare Knowledge Graphs, Graph Neural Networks, Clinical Data Mining, Medical Ontologies, Data Integration, Deep Learning, Health Informatics, Knowledge RepresentationAbstract
Healthcare Knowledge Graphs (KGs) have evolved into many powerful tools for organizing & connecting huge amounts of medical information into meaningful connections that may help with these clinical insights & decision-making. Nonetheless, the creation of effective knowledge graphs in their healthcare is challenging because of the diversity & complexity of medical data sources, including electronic health records, biological literature & genetic databases, each with unique formats & terminologies. This heterogeneity often leads to these inconsistencies, hindering the achievement of semantic interoperability & accurate data integration. This research explores the use of Graph Neural Networks (GNNs) for improving the intelligence as well as adaptability of medical data graphs in addressing those challenges. The proposed strategy leverages the representational capabilities of GNNs to increase learning from graph-structured information, therefore clarifying more complex relationships across many patients, diseases, treatments & biological entities. By finding subconscious patterns, identifying missing interactions & improving the knowledge graph's whole reasoning ability stronger, the method makes knowledge inference stronger. Experiments indicate that the use of GNNs substantially improves entity connections, connection estimations & diagnostic proposals in comparison to these traditional rule-based or statistical approaches. The results show how integrating graph-based instructional methods with their way of displaying health-related data might lead to evolving, interpretable & adaptable platforms that improve clinical choice-making, individualized treatment planning & medical research. This study demonstrates how enhanced GNN medical understanding graphs might boost the interconnection, data-driven nature & cognitive abilities of healthcare systems.
References
[1] Zafeiropoulos, Nikolaos, et al. "Evaluating ontology-based pd monitoring and alerting in personal health knowledge graphs and graph neural networks." Information 15.2 (2024): 100.
[2] Paul, Showmick Guha, et al. "A systematic review of graph neural network in healthcare-based applications: Recent advances, trends, and future directions." IEEE Access 12 (2024): 15145-15170.
[3] Rajabi, Enayat, and Somayeh Kafaie. "Knowledge graphs and explainable AI in healthcare." Information 13.10 (2022): 459.
[4] Wang, Xu, et al. "Novel medical question and answer system: graph convolutional neural network based with knowledge graph optimization." Expert Systems with Applications 227 (2023): 120211.
[5] Peng, Ciyuan, et al. "Knowledge graphs: Opportunities and challenges." Artificial intelligence review 56.11 (2023): 13071-13102.
[6] Ye, Zi, et al. "A comprehensive survey of graph neural networks for knowledge graphs." IEEE Access 10 (2022): 75729-75741.
[7] Sheth, Amit, Swati Padhee, and Amelie Gyrard. "Knowledge graphs and knowledge networks: the story in brief." IEEE Internet Computing 23.4 (2019): 67-75.
[8] Abu-Salih, Bilal, et al. "Healthcare knowledge graph construction: A systematic review of the state-of-the-art, open issues, and opportunities." Journal of Big Data 10.1 (2023): 81.
[9] Mishra, Rajat, and S. Shridevi. "Knowledge graph driven medicine recommendation system using graph neural networks on longitudinal medical records." Scientific Reports 14.1 (2024): 25449.
[10] Cui, Hejie, et al. "A survey on knowledge graphs for healthcare: Resources, application progress, and promise." ICML 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH). 2023.
[11] Lu, Haohui, and Shahadat Uddin. "A weighted patient network-based framework for predicting chronic diseases using graph neural networks." Scientific reports 11.1 (2021): 22607.
[12] Hasan, Md Tarek. "GRAPH NEURAL NETWORK MODELS FOR DETECTING FRAUDULENT INSURANCE CLAIMS IN HEALTHCARE SYSTEMS." American Journal of Advanced Technology and Engineering Solutions 2.01 (2022): 88-109.
[13] Gao, Chao, et al. "Medical-knowledge-based graph neural network for medication combination prediction." IEEE Transactions on Neural Networks and Learning Systems 35.10 (2023): 13246-13257.
[14] Tao, Xiaohui, et al. "Mining health knowledge graph for health risk prediction." World Wide Web 23.4 (2020): 2341-2362.
[15] Malik, Khalid Mahmood, et al. "Automated domain-specific healthcare knowledge graph curation framework: Subarachnoid hemorrhage as phenotype." Expert Systems with Applications 145 (2020): 113120.
