{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T02:46:45Z","timestamp":1785898005444,"version":"3.56.0"},"reference-count":47,"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":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010135","name":"Finska L\u00e4kares\u00e4llskapet","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010135","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008723","name":"Finnish Medical Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008723","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009047","name":"Strategic Research Council","doi-asserted-by":"publisher","award":["372591"],"award-info":[{"award-number":["372591"]}],"id":[{"id":"10.13039\/501100009047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010116","name":"Medical Association of Life and Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010116","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"publisher","award":["1562\/31\/2024"],"award-info":[{"award-number":["1562\/31\/2024"]}],"id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Medical Informatics"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.ijmedinf.2026.106563","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T23:37:37Z","timestamp":1782257857000},"page":"106563","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Clinical note comparison and data retrieval via embedding vectors: model selection, metrics, and convergence"],"prefix":"10.1016","volume":"219","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9401-6954","authenticated-orcid":false,"given":"Alexandra","family":"Dahlberg","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olli","family":"Tapiola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3970-282X","authenticated-orcid":false,"given":"Rami","family":"Luisto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6774-1171","authenticated-orcid":false,"given":"Tuukka","family":"Puranen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enni","family":"Sanmark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ville","family":"Vartiainen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ijmedinf.2026.106563_b0005","doi-asserted-by":"crossref","first-page":"23661","DOI":"10.1007\/s11042-024-20016-1","article-title":"Generative artificial intelligence: a systematic review and applications","volume":"84","author":"Sengar","year":"2025","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijmedinf.2024.105474","article-title":"Generative artificial intelligence in healthcare: a scoping review on benefits, challenges and applications","volume":"188","author":"Moulaei","year":"2024","journal-title":"Int. J. Med. Inf."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0015","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1038\/s41591-023-02366-9","article-title":"AI-generated text may have a role in evidence-based medicine","volume":"29","author":"Peng","year":"2023","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0020","doi-asserted-by":"crossref","first-page":"3270","DOI":"10.1038\/s41591-025-03983-2","article-title":"Generative artificial intelligence in medicine","volume":"31","author":"Teo","year":"2025","journal-title":"Nat. Med."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0025","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adx4082","article-title":"Understanding generative AI output with embedding models","volume":"11","author":"Vargas","year":"2025","journal-title":"Sci. Adv."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0030","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. Gomez, L. Kaiser, I. Polosukhin, Attention Is All You Need, (2017)."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0035","unstructured":"N. Muennighoff, SGPT: GPT Sentence Embeddings for Semantic Search, 2022."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0040","unstructured":"K.C. Enevoldsen, I. Chung, I. Kerboua, M. Kardos, A. Mathur, D. Stap, J. Gala, W. Siblini, D. Krzemi'nski, G.I. Winata, S. Sturua, S. Utpala, M. Ciancone, M. Schaeffer, G. Sequeira, D. Misra, S. Dhakal, J. Rystr\u00f8m, R.S. Solomatin, O.V. cCaugatan, A. Kundu, M. Bernstorff, S. Xiao, A. Sukhlecha, B. Pahwa, R. Poswiata, G. Kranthikiran, S. Ashraf, D. Auras, B. Pluster, J.P. Harries, L. Magne, I. Mohr, M. Hendriksen, D. Zhu, H. Gisserot-Boukhlef, T. Aarsen, J. Kostkan, K. Wojtasik, T. Lee, M. vSuppa, C. Zhang, R. Rocca, M. Hamdy, A. Michail, J. Yang, M. Faysse, A. Vatolin, N. Thakur, M. Dey, D. Vasani, P.A. Chitale, S. Tedeschi, N. Tai, A. Snegirev, M. Gunther, M. Xia, W. Shi, X.H. L\u00f9, J. Clive, G. Krishnakumar, A.D. Maksimova, S. Wehrli, M. Tikhonova, H.S. Panchal, A. Abramov, M. Ostendorff, Z. Liu, S. Clematide, L.J.V. Miranda, A. Fenogenova, G. Song, R.B. Safi, W.-D. Li, A. Borghini, F. Cassano, H. Su, J. Lin, H. Yen, L. Hansen, S. Hooker, C. Xiao, V. Adlakha, O. Weller, S. Reddy, N. Muennighoff, MMTEB: Massive Multilingual Text Embedding Benchmark, The Thirteenth International Conference on Learning Representations, (2025)."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0045","doi-asserted-by":"crossref","first-page":"1877","DOI":"10.1093\/jamia\/ocaf149","article-title":"A scalable framework for benchmark embedding models in semantic health-care tasks","volume":"32","author":"Soffer","year":"2025","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0050","unstructured":"J.-B. Excoffier, T. Roehr, A. Figueroa, J.-M. Papaioannou, K. Bressem, M. Ortala, Generalist embedding models are better at short-context clinical seman tic search than specialized embedding models, 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0055","doi-asserted-by":"crossref","first-page":"3635","DOI":"10.1093\/bioinformatics\/btw529","article-title":"Corpus domain effects on distributional semantic modeling of medical terms","volume":"32","author":"Pakhomov","year":"2016","journal-title":"Bioinformatics"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0060","doi-asserted-by":"crossref","unstructured":"K. Enevoldsen, M. Kardos, N. Muennighoff, K. Nielbo, The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding, 2024.","DOI":"10.52202\/079017-1276"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0065","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10791-022-09406-x","article-title":"On cross-lingual retrieval with multilingual text encoders","volume":"25","author":"Litschko","year":"2022","journal-title":"Inf. Retr. Boston"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0070","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","first-page":"2161","article-title":"Examining Multilingual Embedding Models Cross-Lingually through LLM-Ge nerated Adversarial examples","author":"Michail","year":"2025"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0075","doi-asserted-by":"crossref","unstructured":"J. Morris, E. Lifland, J. Lanchantin, Y. Ji, Y. Qi, Reevaluating Adversarial Examples in Natural Language, 2020.","DOI":"10.18653\/v1\/2020.findings-emnlp.341"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0080","doi-asserted-by":"crossref","unstructured":"K. Ethayarajh, How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, Hong Kong, China, 2019, pp. 55-65.","DOI":"10.18653\/v1\/D19-1006"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0085","doi-asserted-by":"crossref","unstructured":"A. Aghajanyan, S. Gupta, L. Zettlemoyer, Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning, 2021.","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0090","unstructured":"Z. Nie, Z. Feng, M. Li, C. Zhang, Y. Zhang, D. Long, R. Zhang, When Text Embedding Meets Large Language Model: A Comprehensive Survey, 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0095","doi-asserted-by":"crossref","unstructured":"O. Kovaleva, S. Kulshreshtha, A. Rogers, A. Rumshisky, BERT Busters: Outlier Dimensions that Disrupt Transformers, 2021.","DOI":"10.18653\/v1\/2021.findings-acl.300"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0100","doi-asserted-by":"crossref","unstructured":"S. Rajaee, M.T. Pilevar, An Isotropy Analysis in the Multilingual BERT Embedding Space, 2022.","DOI":"10.18653\/v1\/2022.findings-acl.103"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0105","doi-asserted-by":"crossref","unstructured":"T.A. Chang, Z. Tu, B.K. Bergen, The Geometry of Multilingual Language Model Representations, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, 2022, pp. 119\u2013136.","DOI":"10.18653\/v1\/2022.emnlp-main.9"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0110","doi-asserted-by":"crossref","unstructured":"K. H\u00e4mmerl, A. Fastowski, J. Libovick\u00fd, A. Fraser, Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity, 2023.","DOI":"10.18653\/v1\/2023.findings-acl.439"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0115","unstructured":"OpenAI, New embedding models and API updates, 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0120","unstructured":"OpenAI, New and improved embedding model, 2022."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0125","unstructured":"Nomic Inc, nomic-embed-text-v2-moe: Multilingual Mixture of Experts Text Embeddings, 2025."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0130","unstructured":"Z. Nussbaum, B. Duderstadt, Training Sparse Mixture Of Experts Text Embedding Models, ArXiv, abs\/2502.07972 (2025)."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0135","unstructured":"B.A.o.A.I. (BAAI), BGE (BAAI General Embeddings), 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0140","unstructured":"Y. Zhang, M. Li, D. Long, X. Zhang, H. Lin, B. Yang, P. Xie, A. Yang, D. Liu, J. Lin, F. Huang, J. Zhou, Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models, ArXiv, abs\/2506.05176 (2025)."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0145","unstructured":"Qwen Team, Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models, 2025."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0150","unstructured":"L. Wang, N. Yang, X. Huang, L. Yang, R. Majumder, F. Wei, Multilingual E5 Text Embeddings: A Technical Report, ArXiv, abs\/2402.05672 (2024)."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0155","unstructured":"L.Y. Wang, Nan; Huang, Xiaolong; Yang, Linjun; Majumder, Rangan; Wei, Furu, multilingual-e5-large, 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0160","unstructured":"Google, EmbeddingGemma model overview, 2025."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0165","unstructured":"Snowflake, Snowflake\u2019s Arctic Embed 2.0 Goes Multilingual: Empowering Global-Scale Retrieval with Inference Efficiency and High-Quality Retrieval, 2024."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0170","unstructured":"Medbench Platform."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2026.103421","article-title":"Measuring the quality of AI-generated clinical notes: a systematic review and experimental benchmark of evaluation methods","volume":"177","author":"Dahlberg","year":"2026","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0180","unstructured":"J. Cohen, Statistical Power Analysis for the Behavioral Sciences (2nd ed.), Routledge1988."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0185","unstructured":"Microsoft, What is Azure Machine Learning prompt flow?, 2025."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0190","unstructured":"Ollama Inc., Ollama, 2026."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0195","unstructured":"Hugging Face, Hugging Face, 2026."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0200","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0205","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: a 2D Graphics Environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0210","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0215","article-title":"seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"J. Open Sour. Softw."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0220","unstructured":"E. Turunen, HUS Acamedic, 2025."},{"key":"10.1016\/j.ijmedinf.2026.106563_b0225","doi-asserted-by":"crossref","unstructured":"M. Artetxe, G. Labaka, Translation Artifacts in Cross-lingual Transfer Learning, 2020.","DOI":"10.18653\/v1\/2020.emnlp-main.618"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0230","article-title":"Comparative Evaluation of Advanced Chunking for Retrieval-Augmented Generation in Large Language Models for Clinical Decision support","volume":"12","author":"Gomez-Cabello","year":"2025","journal-title":"Bioengineering (basel)"},{"key":"10.1016\/j.ijmedinf.2026.106563_b0235","unstructured":"Anthropic, Claude Sonnet 4.6 [Large Language Model], 2026."}],"container-title":["International Journal of Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626003035?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626003035?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T02:11:41Z","timestamp":1785895901000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1386505626003035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":47,"alternative-id":["S1386505626003035"],"URL":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106563","relation":{},"ISSN":["1386-5056"],"issn-type":[{"value":"1386-5056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Clinical note comparison and data retrieval via embedding vectors: model selection, metrics, and convergence","name":"articletitle","label":"Article Title"},{"value":"International Journal of Medical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106563","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"106563"}}