{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T08:03:27Z","timestamp":1789632207286,"version":"build-2803163510"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,8,22]],"date-time":"2027-08-22T00:00:00Z","timestamp":1818892800000},"content-version":"am","delay-in-days":325,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2225229"],"award-info":[{"award-number":["2225229"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.jbi.2026.105093","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T06:55:36Z","timestamp":1787295336000},"page":"105093","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Quality-aware multi-source data fusion and enhancement for Medical Concept Normalization using Large Language Models"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3655-1527","authenticated-orcid":false,"given":"Yuhan","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6677-5222","authenticated-orcid":false,"given":"Ruochi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9867-9418","authenticated-orcid":false,"given":"Ana","family":"Cleveland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7016-4583","authenticated-orcid":false,"given":"Junhua","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3750-163X","authenticated-orcid":false,"given":"Kewei","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-9752","authenticated-orcid":false,"given":"Haihua","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jbi.2026.105093_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104812","article-title":"Enhancing data quality in medical concept normalization through large language models","volume":"165","author":"Chen","year":"2025","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b2","series-title":"Machine Learning for Health Workshop","first-page":"246","article-title":"Medical concept normalization by encoding target knowledge","author":"Pattisapu","year":"2020"},{"key":"10.1016\/j.jbi.2026.105093_b3","doi-asserted-by":"crossref","DOI":"10.2196\/41446","article-title":"Data quality in health research: integrative literature review","volume":"25","author":"Bernardi","year":"2023","journal-title":"J. Med. Internet Res."},{"issue":"2","key":"10.1016\/j.jbi.2026.105093_b4","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1109\/TR.2021.3070863","article-title":"Data evaluation and enhancement for quality improvement of machine learning","volume":"70","author":"Chen","year":"2021","journal-title":"IEEE Trans. Reliab."},{"issue":"9","key":"10.1016\/j.jbi.2026.105093_b5","doi-asserted-by":"crossref","first-page":"2076","DOI":"10.1093\/jamia\/ocae133","article-title":"Fine-tuning large language models for rare disease concept normalization","volume":"31","author":"Wang","year":"2024","journal-title":"J. Am. Med. Informatics Assoc."},{"issue":"8","key":"10.1016\/j.jbi.2026.105093_b6","doi-asserted-by":"crossref","first-page":"btae474","DOI":"10.1093\/bioinformatics\/btae474","article-title":"BELHD: improving biomedical entity linking with homonym disambiguation","volume":"40","author":"Garda","year":"2024","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jbi.2026.105093_b7","series-title":"2017 IEEE International Conference on Healthcare Informatics","first-page":"462","article-title":"Medical concept normalization for online user-generated texts","author":"Lee","year":"2017"},{"key":"10.1016\/j.jbi.2026.105093_b8","doi-asserted-by":"crossref","unstructured":"M. Belousov, W.G. Dixon, G. Nenadic, Mednorm: A corpus and embeddings for cross-terminology medical concept normalisation, in: Proceedings of the Fourth Social Media Mining for Health Applications (# SMM4H) Workshop & Shared Task, 2019, pp. 31\u201339.","DOI":"10.18653\/v1\/W19-3204"},{"key":"10.1016\/j.jbi.2026.105093_b9","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing","first-page":"3122","article-title":"COMETA: A corpus for medical entity linking in the social media","author":"Basaldella","year":"2020"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105093_b11","series-title":"International Conference on Pattern Recognition","first-page":"154","article-title":"SNOBERT: A benchmark for clinical notes entity linking in the SNOMED ct clinical terminology","author":"Kulyabin","year":"2025"},{"key":"10.1016\/j.jbi.2026.105093_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2019.103132","article-title":"MCN: A comprehensive corpus for medical concept normalization","volume":"92","author":"Luo","year":"2019","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2025.110108","article-title":"From silos to synthesis: A comprehensive review of domain adaptation strategies for multi-source data integration in healthcare","volume":"191","author":"Tuly","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.jbi.2026.105093_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111323","article-title":"LMKG: A large-scale and multi-source medical knowledge graph for intelligent medicine applications","volume":"284","author":"Yang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jbi.2026.105093_b15","doi-asserted-by":"crossref","unstructured":"K. Yang, T. Zhang, Z. Kuang, Q. Xie, J. Huang, S. Ananiadou, MentaLLaMA: interpretable mental health analysis on social media with large language models, in: Proceedings of the ACM on Web Conference 2024, 2024, pp. 4489\u20134500.","DOI":"10.1145\/3589334.3648137"},{"key":"10.1016\/j.jbi.2026.105093_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113211","article-title":"Enhancing cross-encoders using knowledge graph hierarchy for medical entity linking in zero-and few-shot scenarios","volume":"314","author":"Gallego","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"10.1016\/j.jbi.2026.105093_b17","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/s41666-023-00136-3","article-title":"NeighBERT: Medical entity linking using relation-induced dense retrieval","volume":"8","author":"Singh","year":"2024","journal-title":"J. Heal. Informatics Res."},{"key":"10.1016\/j.jbi.2026.105093_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2022.104252","article-title":"An overview of biomedical entity linking throughout the years","volume":"137","author":"French","year":"2023","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104806","article-title":"Contextual information contributes to biomedical named entity normalization","volume":"165","author":"Luo","year":"2025","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b20","unstructured":"Y. Fan, K. Xue, Z. Li, X. Zhang, T. Ruan, An LLM-based Framework for Biomedical Terminology Normalization in Social Media via Multi-Agent Collaboration, in: Proceedings of the 31st International Conference on Computational Linguistics, 2025, pp. 10712\u201310726."},{"key":"10.1016\/j.jbi.2026.105093_b21","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.ins.2022.11.158","article-title":"XRR: Extreme multi-label text classification with candidate retrieving and deep ranking","volume":"622","author":"Xiong","year":"2023","journal-title":"Inform. Sci."},{"key":"10.1016\/j.jbi.2026.105093_b22","series-title":"International Conference of the Cross-Language Evaluation Forum for European Languages","first-page":"109","article-title":"Graph-enriched biomedical entity representation transformer","author":"Sakhovskiy","year":"2023"},{"key":"10.1016\/j.jbi.2026.105093_b23","series-title":"International Conference on Machine Learning","first-page":"24457","article-title":"Tuning language models as training data generators for augmentation-enhanced few-shot learning","author":"Meng","year":"2023"},{"key":"10.1016\/j.jbi.2026.105093_b24","doi-asserted-by":"crossref","unstructured":"F. Liu, E. Shareghi, Z. Meng, M. Basaldella, N. Collier, Self-alignment pretraining for biomedical entity representations, in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 4228\u20134238.","DOI":"10.18653\/v1\/2021.naacl-main.334"},{"key":"10.1016\/j.jbi.2026.105093_b25","doi-asserted-by":"crossref","unstructured":"N. Limsopatham, N. Collier, Normalising medical concepts in social media texts by learning semantic representation, in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, pp. 1014\u20131023.","DOI":"10.18653\/v1\/P16-1096"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b26","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1038\/s41597-024-03317-w","article-title":"A dataset for evaluating contextualized representation of biomedical concepts in language models","volume":"11","author":"Rouhizadeh","year":"2024","journal-title":"Sci. Data"},{"key":"10.1016\/j.jbi.2026.105093_b27","doi-asserted-by":"crossref","unstructured":"A. Magge, A. Klein, A. Miranda-Escalada, M.A. Al-Garadi, I. Alimova, Z. Miftahutdinov, E. Farre, S. Lima-L\u00f3pez, I. Flores, K. O\u2019Connor, et al., Overview of the sixth social media mining for health applications (# SMM4H) shared tasks at NAACL 2021, in: Proceedings of the Sixth Social Media Mining for Health (# SMM4H) Workshop and Shared Task, 2021, pp. 21\u201332.","DOI":"10.18653\/v1\/2021.smm4h-1.4"},{"issue":"10","key":"10.1016\/j.jbi.2026.105093_b28","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1093\/jamia\/ocy114","article-title":"Data and systems for medication-related text classification and concept normalization from Twitter: insights from the social media mining for health (SMM4H)-2017 shared task","volume":"25","author":"Sarker","year":"2018","journal-title":"J. Am. Med. Informatics Assoc."},{"key":"10.1016\/j.jbi.2026.105093_b29","series-title":"International Conference of the Cross-Language Evaluation Forum for European Languages","first-page":"173","article-title":"Overview of BioASQ 2025: The thirteenth BioASQ challenge on large-scale biomedical semantic indexing and question answering","author":"Nentidis","year":"2025"},{"key":"10.1016\/j.jbi.2026.105093_b30","series-title":"2023 14th International Conference on Intelligent Systems: Theories and Applications","first-page":"1","article-title":"Adverse drug reactions detection from social media: an empirical evaluation of machine learning techniques","author":"Elbiach","year":"2023"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b31","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1146\/annurev-biodatasci-030320-040844","article-title":"Mining social media data for biomedical signals and health-related behavior","volume":"3","author":"Correia","year":"2020","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"10.1016\/j.jbi.2026.105093_b32","doi-asserted-by":"crossref","unstructured":"S. Scepanovic, E. Martin-Lopez, D. Quercia, K. Baykaner, Extracting medical entities from social media, in: Proceedings of the ACM Conference on Health, Inference, and Learning, 2020, pp. 170\u2013181.","DOI":"10.1145\/3368555.3384467"},{"key":"10.1016\/j.jbi.2026.105093_b33","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.jbi.2018.06.006","article-title":"Medical concept normalization in social media posts with recurrent neural networks","volume":"84","author":"Tutubalina","year":"2018","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b34","series-title":"Proceedings of Knowledgeable NLP: The First Workshop on Integrating Structured Knowledge and Neural Networks for NLP","first-page":"21","article-title":"Social media medical concept normalization using RoBERTa in ontology enriched text similarity framework","author":"Kalyan","year":"2020"},{"issue":"3","key":"10.1016\/j.jbi.2026.105093_b35","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1093\/jamia\/ocaa269","article-title":"Ambiguity in medical concept normalization: An analysis of types and coverage in electronic health record datasets","volume":"28","author":"Newman-Griffis","year":"2021","journal-title":"J. Am. Med. Informatics Assoc."},{"key":"10.1016\/j.jbi.2026.105093_b36","series-title":"2024 IEEE International Conference on Artificial Intelligence Testing (AITest)","first-page":"120","article-title":"A survey on data quality dimensions and tools for machine learning invited paper","author":"Zhou","year":"2024"},{"issue":"2","key":"10.1016\/j.jbi.2026.105093_b37","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1089\/big.2016.0054","article-title":"Diversity in big data: A review","volume":"5","author":"Drosou","year":"2017","journal-title":"Big Data"},{"key":"10.1016\/j.jbi.2026.105093_b38","doi-asserted-by":"crossref","first-page":"baac067","DOI":"10.1093\/database\/baac067","article-title":"Task reformulation and data-centric approach for Twitter medication name extraction","volume":"2022","author":"Zhang","year":"2022","journal-title":"Database"},{"key":"10.1016\/j.jbi.2026.105093_b39","doi-asserted-by":"crossref","unstructured":"Z. Lin, Z. Zhang, X. Wu, Y. Zheng, Biomedical Entity Linking as Multiple Choice Question Answering, in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 2390\u20132396.","DOI":"10.63317\/2sovdnivm7fr"},{"key":"10.1016\/j.jbi.2026.105093_b40","doi-asserted-by":"crossref","unstructured":"B. Portelli, S. Scaboro, E. Santus, H. Sedghamiz, E. Chersoni, G. Serra, Generalizing over Long Tail Concepts for Medical Term Normalization, in: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022, pp. 8580\u20138591.","DOI":"10.18653\/v1\/2022.emnlp-main.588"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b41","doi-asserted-by":"crossref","first-page":"bbab421","DOI":"10.1093\/bib\/bbab421","article-title":"MDF-SA-DDI: predicting drug\u2013drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism","volume":"23","author":"Lin","year":"2022","journal-title":"Brief. Bioinform."},{"key":"10.1016\/j.jbi.2026.105093_b42","series-title":"A novel multi-layer task-centric and data quality framework for autonomous driving","author":"Zhou","year":"2025"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b43","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41746-024-01196-4","article-title":"The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review","volume":"7","author":"Schwabe","year":"2024","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.jbi.2026.105093_b44","first-page":"1","article-title":"A comprehensive survey on data augmentation","author":"Wang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"10.1016\/j.jbi.2026.105093_b45","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.eng.2024.04.024","article-title":"On the data quality and imbalance in machine learning-based design and manufacturing\u2014A systematic review","volume":"45","author":"Xie","year":"2025","journal-title":"Engineering"},{"issue":"1","key":"10.1016\/j.jbi.2026.105093_b46","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann","year":"2023","journal-title":"Commun. Med."},{"key":"10.1016\/j.jbi.2026.105093_b47","doi-asserted-by":"crossref","first-page":"baae104","DOI":"10.1093\/database\/baae104","article-title":"Optimized biomedical entity relation extraction method with data augmentation and classification using GPT-4 and Gemini","volume":"2024","author":"Phan","year":"2024","journal-title":"Database"},{"key":"10.1016\/j.jbi.2026.105093_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.108189","article-title":"A comprehensive evaluation of large language models on benchmark biomedical text processing tasks","volume":"171","author":"Jahan","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.jbi.2026.105093_b49","first-page":"1","article-title":"Generalizable and scalable multistage biomedical concept normalization leveraging large language models","author":"Dobbins","year":"2024","journal-title":"Res. Synth. Methods"},{"key":"10.1016\/j.jbi.2026.105093_b50","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.jbi.2015.03.010","article-title":"Cadec: A corpus of adverse drug event annotations","volume":"55","author":"Karimi","year":"2015","journal-title":"J. Biomed. Informatics"},{"key":"10.1016\/j.jbi.2026.105093_b51","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2019.103838","article-title":"The PsyTAR dataset: From patients generated narratives to a corpus of adverse drug events and effectiveness of psychiatric medications","volume":"24","author":"Zolnoori","year":"2019","journal-title":"Data Brief"},{"key":"10.1016\/j.jbi.2026.105093_b52","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2024.104744","article-title":"MultiADE: a multi-domain benchmark for adverse drug event extraction","volume":"160","author":"Dai","year":"2024","journal-title":"J. Biomed. Informatics"},{"issue":"3","key":"10.1016\/j.jbi.2026.105093_b53","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1109\/TMI.2024.3496862","article-title":"Integration of multi-source medical data for medical diagnosis question answering","volume":"44","author":"Peng","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"5","key":"10.1016\/j.jbi.2026.105093_b54","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1136\/amiajnl-2011-000155","article-title":"Using machine learning for concept extraction on clinical documents from multiple data sources","volume":"18","author":"Torii","year":"2011","journal-title":"J. Am. Med. Informatics Assoc."},{"key":"10.1016\/j.jbi.2026.105093_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2024.102965","article-title":"CMCN: Chinese medical concept normalization using continual learning and knowledge-enhanced","volume":"157","author":"Han","year":"2024","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.jbi.2026.105093_b56","doi-asserted-by":"crossref","unstructured":"R. Xu, W. Shi, Y. Yu, Y. Zhuang, B. Jin, M.D. Wang, J. Ho, C. Yang, Ram-ehr: Retrieval augmentation meets clinical predictions on electronic health records, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2024, pp. 754\u2013765.","DOI":"10.18653\/v1\/2024.acl-short.68"},{"issue":"14","key":"10.1016\/j.jbi.2026.105093_b57","doi-asserted-by":"crossref","first-page":"2474","DOI":"10.1093\/bioinformatics\/bty152","article-title":"Exploiting and assessing multi-source data for supervised biomedical named entity recognition","volume":"34","author":"Galea","year":"2018","journal-title":"Bioinformatics"},{"key":"10.1016\/j.jbi.2026.105093_b58","series-title":"2021 2nd International Symposium on Computer Engineering and Intelligent Communications","first-page":"64","article-title":"A multi-mode learning behavior real-time data acquisition method based on data quality","author":"Zhang","year":"2021"},{"key":"10.1016\/j.jbi.2026.105093_b59","series-title":"2017 IEEE 21st International Conference on Computer Supported Cooperative Work in Design","first-page":"233","article-title":"A method of electronic health data quality assessment: Enabling data provenance","author":"Sun","year":"2017"},{"issue":"2","key":"10.1016\/j.jbi.2026.105093_b60","doi-asserted-by":"crossref","DOI":"10.2196\/publichealth.6396","article-title":"TwiMed: Twitter and PubMed comparable corpus of drugs, diseases, symptoms, and their relations","volume":"3","author":"Alvaro","year":"2017","journal-title":"JMIR Public Health Surveill."},{"key":"10.1016\/j.jbi.2026.105093_b61","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.jbi.2026.105093_b62","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112947","article-title":"A dynamic ensemble learning based data mining framework for medical imbalanced big data","volume":"310","author":"Rithani","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jbi.2026.105093_b63","series-title":"Machine Learning for Health","first-page":"415","article-title":"Addressing the real-world class imbalance problem in dermatology","author":"Weng","year":"2020"},{"key":"10.1016\/j.jbi.2026.105093_b64","series-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"10.1016\/j.jbi.2026.105093_b65","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"11461","article-title":"Improving biomedical entity linking with retrieval-enhanced learning","author":"Lin","year":"2024"},{"key":"10.1016\/j.jbi.2026.105093_b66","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","first-page":"868","article-title":"Knowledge-rich self-supervision for biomedical entity linking","author":"Zhang","year":"2022"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001176?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001176?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T07:15:50Z","timestamp":1789629350000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426001176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":66,"alternative-id":["S1532046426001176"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105093","relation":{},"ISSN":["1532-0464"],"issn-type":[{"value":"1532-0464","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Quality-aware multi-source data fusion and enhancement for Medical Concept Normalization using Large Language Models","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105093","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105093"}}