{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:48:35Z","timestamp":1775069315192,"version":"3.50.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100003653","name":"Korea National Institute of Health","doi-asserted-by":"publisher","award":["2024-ER0807-00"],"award-info":[{"award-number":["2024-ER0807-00"]}],"id":[{"id":"10.13039\/501100003653","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"DOI":"10.1186\/s12911-025-03262-7","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T12:02:22Z","timestamp":1764072142000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Domain and Language adaptive pre-training of BERT models for Korean-English bilingual clinical text analysis"],"prefix":"10.1186","volume":"25","author":[{"given":"Eunbeen","family":"Jo","sequence":"first","affiliation":[]},{"given":"Eunbi","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Yebin","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Sanghoun","family":"Song","sequence":"additional","affiliation":[]},{"given":"Hyung Joon","family":"Joo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"3262_CR1","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1590\/1413-81232020254.28922019","volume":"25","author":"RS Janett","year":"2020","unstructured":"Janett RS, Yeracaris PP. Electronic medical records in the American health system: challenges and lessons learned. Ciencia Saude Coletiva. 2020;25:1293\u2013304.","journal-title":"Ciencia Saude Coletiva"},{"key":"3262_CR2","doi-asserted-by":"publisher","first-page":"e12779","DOI":"10.2196\/12779","volume":"21","author":"R Dendere","year":"2019","unstructured":"Dendere R, Slade C, Burton-Jones A, Sullivan C, Staib A, Janda M. Patient portals facilitating engagement with inpatient electronic medical records: a systematic review. J Med Internet Res. 2019;21:e12779.","journal-title":"J Med Internet Res"},{"key":"3262_CR3","doi-asserted-by":"publisher","first-page":"103327","DOI":"10.1016\/j.jbi.2019.103327","volume":"100","author":"AJ King","year":"2019","unstructured":"King AJ, Cooper GF, Clermont G, Hochheiser H, Hauskrecht M, Sittig DF, et al. Using machine learning to selectively highlight patient information. J Biomed Inform. 2019;100:103327.","journal-title":"J Biomed Inform"},{"key":"3262_CR4","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1038\/s41467-021-20910-4","volume":"12","author":"KH Goh","year":"2021","unstructured":"Goh KH, Wang L, Yeow AYK, Poh H, Li K, Yeow JJL, et al. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat Commun. 2021;12:711.","journal-title":"Nat Commun"},{"key":"3262_CR5","unstructured":"Wei Q, Ji Z, Si Y, Du J, Wang J, Tiryaki F, et al. Relation extraction from clinical narratives using pre-trained language models. AMIA Annu Symp Proc. 2020;1236."},{"key":"3262_CR6","doi-asserted-by":"publisher","first-page":"e11","DOI":"10.1093\/jamia\/ocv115","volume":"23","author":"E Scheurwegs","year":"2016","unstructured":"Scheurwegs E, Luyckx K, Luyten L, Daelemans W, Van den Bulcke T. Data integration of structured and unstructured sources for assigning clinical codes to patient stays. J Am Med Inform Assoc. 2016;23:e11\u20139.","journal-title":"J Am Med Inform Assoc"},{"key":"3262_CR7","doi-asserted-by":"publisher","first-page":"e1549","DOI":"10.1002\/wics.1549","volume":"13","author":"M Tayefi","year":"2021","unstructured":"Tayefi M, Ngo P, Chomutare T, Dalianis H, Salvi E, Budrionis A, et al. Challenges and opportunities beyond structured data in analysis of electronic health records. Wiley Interdisciplinary Reviews: Comput Stat. 2021;13:e1549.","journal-title":"Wiley Interdisciplinary Reviews: Comput Stat"},{"key":"3262_CR8","doi-asserted-by":"publisher","first-page":"e12239","DOI":"10.2196\/12239","volume":"7","author":"S Sheikhalishahi","year":"2019","unstructured":"Sheikhalishahi S, Miotto R, Dudley JT, Lavelli A, Rinaldi F, Osmani V. Natural Language processing of clinical notes on chronic diseases: systematic review. JMIR Med Inf. 2019;7:e12239.","journal-title":"JMIR Med Inf"},{"key":"3262_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13326-018-0179-8","volume":"9","author":"A N\u00e9v\u00e9ol","year":"2018","unstructured":"N\u00e9v\u00e9ol A, Dalianis H, Velupillai S, Savova G, Zweigenbaum P. Clinical natural Language processing in Languages other than english: opportunities and challenges. J Biomedical Semant. 2018;9:1\u201313.","journal-title":"J Biomedical Semant"},{"key":"3262_CR10","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3346\/jkms.2015.30.1.7","volume":"30","author":"S-Y Shin","year":"2015","unstructured":"Shin S-Y, Park YR, Shin Y, Choi HJ, Park J, Lyu Y, et al. A de-identification method for bilingual clinical texts of various note types. J Korean Med Sci. 2015;30:7\u201315.","journal-title":"J Korean Med Sci"},{"key":"3262_CR11","doi-asserted-by":"publisher","first-page":"16066","DOI":"10.1109\/ACCESS.2023.3245523","volume":"11","author":"HK Kim","year":"2023","unstructured":"Kim HK, Park Y, Park Y, Choi E, Kim S, You H, et al. Identifying alcohol-related information from unstructured bilingual clinical notes with multilingual Transformers. IEEE Access. 2023;11:16066\u201375.","journal-title":"IEEE Access"},{"key":"3262_CR12","doi-asserted-by":"crossref","unstructured":"Agrawal M, Hegselmann S, Lang H, Kim Y, Sontag D. Large language models are few-shot clinical information extractors. arXiv preprint arXiv:2205.12689. 2022.","DOI":"10.18653\/v1\/2022.emnlp-main.130"},{"key":"3262_CR13","doi-asserted-by":"publisher","first-page":"106492","DOI":"10.1016\/j.neunet.2024.106492","volume":"179","author":"A Cossu","year":"2024","unstructured":"Cossu A, Carta A, Passaro L, Lomonaco V, Tuytelaars T, Bacciu D. Continual pre-training mitigates forgetting in Language and vision. Neural Netw. 2024;179:106492.","journal-title":"Neural Netw"},{"key":"3262_CR14","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH, et al. BioBERT: a pre-trained biomedical Language representation model for biomedical text mining. Bioinformatics. 2020;36:1234\u201340.","journal-title":"Bioinformatics"},{"key":"3262_CR15","doi-asserted-by":"publisher","first-page":"8384","DOI":"10.1038\/s41467-024-52417-z","volume":"15","author":"P Qiu","year":"2024","unstructured":"Qiu P, Wu C, Zhang X, Lin W, Wang H, Zhang Y, et al. Towards Building multilingual Language model for medicine. Nat Commun. 2024;15:8384.","journal-title":"Nat Commun"},{"key":"3262_CR16","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1093\/jamia\/ocae037","volume":"31","author":"L Luo","year":"2024","unstructured":"Luo L, Ning J, Zhao Y, Wang Z, Ding Z, Chen P, et al. Taiyi: a bilingual fine-tuned large Language model for diverse biomedical tasks. J Am Med Inform Assoc. 2024;31:1865\u201374.","journal-title":"J Am Med Inform Assoc"},{"key":"3262_CR17","doi-asserted-by":"crossref","unstructured":"Brown KE, Yan C, Li Z, Zhang X, Collins BX, Chen Y et al. Large language models are less effective at clinical prediction tasks than locally trained machine learning models. J Am Med Inform Assoc. 2025:ocaf038.","DOI":"10.1093\/jamia\/ocaf038"},{"key":"3262_CR18","doi-asserted-by":"publisher","first-page":"e47814","DOI":"10.2196\/47814","volume":"8","author":"E Jo","year":"2024","unstructured":"Jo E, Yoo H, Kim J-H, Kim Y-M, Song S, Joo HJ. Fine-Tuned bidirectional encoder representations from Transformers versus ChatGPT for Text-Based outpatient department recommendation: comparative study. JMIR Formative Res. 2024;8:e47814.","journal-title":"JMIR Formative Res"},{"key":"3262_CR19","doi-asserted-by":"publisher","first-page":"e52897","DOI":"10.2196\/52897","volume":"12","author":"K Kim","year":"2024","unstructured":"Kim K, Park S, Min J, Park S, Kim JY, Eun J, et al. Multifaceted natural Language processing Task\u2013Based evaluation of bidirectional encoder representations from Transformers models for bilingual (Korean and English) clinical notes: algorithm development and validation. JMIR Med Inf. 2024;12:e52897.","journal-title":"JMIR Med Inf"},{"key":"3262_CR20","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1055\/s-0044-1800750","volume":"33","author":"A Sarker","year":"2024","unstructured":"Sarker A, Zhang R, Wang Y, Xiao Y, Das S, Schutte D, et al. Natural Language processing for digital health in the era of large Language models. Yearb Med Inform. 2024;33:229\u201340.","journal-title":"Yearb Med Inform"},{"key":"3262_CR21","doi-asserted-by":"publisher","first-page":"103003","DOI":"10.1016\/j.artmed.2024.103003","volume":"157","author":"A Bonfigli","year":"2024","unstructured":"Bonfigli A, Bacco L, Merone M, Dell\u2019Orletta F. From pre-training to fine-tuning: an in-depth analysis of large Language models in the biomedical domain. Artif Intell Med. 2024;157:103003.","journal-title":"Artif Intell Med"},{"key":"3262_CR22","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","volume":"5","author":"N Ding","year":"2023","unstructured":"Ding N, Qin Y, Yang G, Wei F, Yang Z, Su Y, et al. Parameter-efficient fine-tuning of large-scale pre-trained Language models. Nat Mach Intell. 2023;5:220\u201335.","journal-title":"Nat Mach Intell"},{"key":"3262_CR23","doi-asserted-by":"publisher","first-page":"3267","DOI":"10.1093\/bioinformatics\/btac297","volume":"38","author":"L Lange","year":"2022","unstructured":"Lange L, Adel H, Str\u00f6tgen J, Klakow D. CLIN-X: pre-trained Language models and a study on cross-task transfer for concept extraction in the clinical domain. Bioinformatics. 2022;38:3267\u201374.","journal-title":"Bioinformatics"},{"key":"3262_CR24","first-page":"1","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu Y, Tinn R, Cheng H, Lucas M, Usuyama N, Liu X, et al. Domain-specific Language model pretraining for biomedical natural Language processing. ACM Trans Comput Healthc (HEALTH). 2021;3:1\u201323.","journal-title":"ACM Trans Comput Healthc (HEALTH)"},{"key":"3262_CR25","doi-asserted-by":"crossref","unstructured":"Gururangan S, Marasovi\u0107 A, Swayamdipta S, Lo K, Beltagy I, Downey D, et al. Don't stop pretraining: adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964. 2020.","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"3262_CR26","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1055\/s-0041-1726522","volume":"30","author":"E Laparra","year":"2021","unstructured":"Laparra E, Mascio A, Velupillai S, Miller T. A review of recent work in transfer learning and domain adaptation for natural Language processing of electronic health records. Yearb Med Inform. 2021;30:239\u201344.","journal-title":"Yearb Med Inform"},{"key":"3262_CR27","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1038\/s41746-025-01626-x","volume":"8","author":"JS Bosma","year":"2025","unstructured":"Bosma JS, Dercksen K, Builtjes L, Andr\u00e9 R, Roest C, Fransen SJ, et al. The DRAGON benchmark for clinical NLP. Npj Digit Med. 2025;8:289.","journal-title":"Npj Digit Med"},{"key":"3262_CR28","doi-asserted-by":"crossref","unstructured":"Bilal M, Hamza A, Malik N. NLP for analyzing electronic health records and clinical notes in cancer research: a review. J Pain Symptom Manag. 2025.","DOI":"10.1016\/j.jpainsymman.2025.01.019"},{"key":"3262_CR29","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1093\/jamia\/ocad107","volume":"30","author":"C Peng","year":"2023","unstructured":"Peng C, Yang X, Yu Z, Bian J, Hogan WR, Wu Y. Clinical concept and relation extraction using prompt-based machine reading comprehension. J Am Med Inform Assoc. 2023;30:1486\u201393.","journal-title":"J Am Med Inform Assoc"},{"key":"3262_CR30","doi-asserted-by":"publisher","first-page":"102625","DOI":"10.1016\/j.artmed.2023.102625","volume":"143","author":"O Solarte-Pab\u00f3n","year":"2023","unstructured":"Solarte-Pab\u00f3n O, Montenegro O, Garc\u00eda-Barrag\u00e1n A, Torrente M, Provencio M, Menasalvas E, et al. Transformers for extracting breast cancer information from Spanish clinical narratives. Artif Intell Med. 2023;143:102625.","journal-title":"Artif Intell Med"},{"key":"3262_CR31","doi-asserted-by":"crossref","unstructured":"Li Y, Tao W, Li Z, Sun Z, Li F, Fenton S et al. Artificial intelligence-powered pharmacovigilance: a review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets. J Biomed Inform. 2024:104621.","DOI":"10.1016\/j.jbi.2024.104621"},{"key":"3262_CR32","unstructured":"Ding X, Sheng Z, Yeti\u015fgen M, Pakhomov S, Cohen T. Backdoor adjustment of confounding by provenance for robust text classification of multi-institutional clinical notes. AMIA Annu Symp Proc. 2024;923."},{"key":"3262_CR33","doi-asserted-by":"publisher","first-page":"e49607","DOI":"10.2196\/49607","volume":"12","author":"C G\u00e9rardin","year":"2024","unstructured":"G\u00e9rardin C, Xiong Y, Wajsb\u00fcrt P, Carrat F, Tannier X. Impact of translation on biomedical information extraction: experiment on Real-Life clinical notes. JMIR Med Inf. 2024;12:e49607.","journal-title":"JMIR Med Inf"},{"key":"3262_CR34","doi-asserted-by":"publisher","first-page":"104657","DOI":"10.1016\/j.jbi.2024.104657","volume":"155","author":"T-Y Chen","year":"2024","unstructured":"Chen T-Y, Huang T-Y, Chang Y-C. Using a clinical narrative-aware pre-trained Language model for predicting emergency department patient disposition and unscheduled return visits. J Biomed Inform. 2024;155:104657.","journal-title":"J Biomed Inform"},{"key":"3262_CR35","doi-asserted-by":"crossref","unstructured":"Song X, Salcianu A, Song Y, Dopson D, Zhou D. Fast wordpiece tokenization. arXiv preprint arXiv:2012.15524. 2020.","DOI":"10.18653\/v1\/2021.emnlp-main.160"},{"key":"3262_CR36","doi-asserted-by":"publisher","first-page":"13847","DOI":"10.1038\/s41598-022-17806-8","volume":"12","author":"Y Kim","year":"2022","unstructured":"Kim Y, Kim J-H, Lee JM, Jang MJ, Yum YJ, Kim S, et al. A pre-trained BERT for Korean medical natural Language processing. Sci Rep. 2022;12:13847.","journal-title":"Sci Rep"},{"key":"3262_CR37","unstructured":"Devlin J, Bert. Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. 2018."},{"key":"3262_CR38","doi-asserted-by":"crossref","unstructured":"Pires T, Schlinger E, Garrette D. How multilingual is multilingual BERT? arXiv preprint arXiv:1906.01502. 2019.","DOI":"10.18653\/v1\/P19-1493"},{"key":"3262_CR39","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s10579-018-9431-1","volume":"54","author":"Y Wang","year":"2020","unstructured":"Wang Y, Afzal N, Fu S, Wang L, Shen F, Rastegar-Mojarad M, et al. MedSTS: a resource for clinical semantic textual similarity. Lang Resour Evaluation. 2020;54:57\u201372.","journal-title":"Lang Resour Evaluation"},{"key":"3262_CR40","unstructured":"AI-Hub. https:\/\/aihub.or.kr\/ (accessed 3 March 2024)."},{"key":"3262_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AE Johnson","year":"2023","unstructured":"Johnson AE, Bulgarelli L, Shen L, Gayles A, Shammout A, Horng S, et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci Data. 2023;10:1.","journal-title":"Sci Data"},{"key":"3262_CR42","doi-asserted-by":"publisher","first-page":"Article116","DOI":"10.1145\/3578707","volume":"22","author":"C Toraman","year":"2023","unstructured":"Toraman C, Yilmaz EH, \u015eahi\u0307nu\u00e7 F, Ozcelik O. Impact of tokenization on Language models: an analysis for Turkish. ACM Trans Asian Low-Resour Lang Inf Process. 2023;22:Article116.","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"3262_CR43","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s10462-024-10921-0","volume":"57","author":"D Wang","year":"2024","unstructured":"Wang D, Zhang S. Large Language models in medical and healthcare fields: applications, advances, and challenges. Artif Intell Rev. 2024;57:299.","journal-title":"Artif Intell Rev"},{"key":"3262_CR44","first-page":"267","volume-title":"ICD-10 and SNOMED CT: the role of healthcare classification systems in digital health","author":"S Gallo","year":"2025","unstructured":"Gallo S. ICD-10 and SNOMED CT: the role of healthcare classification systems in digital health. Digital Health: Elsevier; 2025. pp. 267\u201385."},{"key":"3262_CR45","doi-asserted-by":"publisher","first-page":"e2431696","DOI":"10.2214\/AJR.24.31696","volume":"223","author":"JE Lee","year":"2024","unstructured":"Lee JE, Park K-S, Kim Y-H, Song H-C, Park B, Jeong YJ. Lung cancer staging using chest CT and FDG PET\/CT free-text reports: comparison among three ChatGPT large Language models and six human readers of varying experience. Am J Roentgenol. 2024;223:e2431696.","journal-title":"Am J Roentgenol"},{"key":"3262_CR46","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1002\/ejhf.1957","volume":"22","author":"J \u010celutkien\u0117","year":"2020","unstructured":"\u010celutkien\u0117 J, Pudil R, L\u00f3pez-Fern\u00e1ndez T, Grapsa J, Nihoyannopoulos P, Bergler\u2010Klein J, et al. Role of cardiovascular imaging in cancer patients receiving cardiotoxic therapies: a position statement on behalf of the H eart F ailure A ssociation (HFA), the E uropean A ssociation of C ardiovascular I Maging (EACVI) and the Cardio\u2010Oncology C ouncil of the E uropean S ociety of C ardiology (ESC). Eur J Heart Fail. 2020;22:1504\u201324.","journal-title":"Eur J Heart Fail"},{"key":"3262_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11886-020-01420-z","volume":"22","author":"R Bussani","year":"2020","unstructured":"Bussani R, Castrichini M, Restivo L, Fabris E, Porcari A, Ferro F, et al. Cardiac tumors: diagnosis, prognosis, and treatment. Curr Cardiol Rep. 2020;22:1\u201313.","journal-title":"Curr Cardiol Rep"},{"key":"3262_CR48","doi-asserted-by":"crossref","unstructured":"Simpson S, Kay FU, Abbara S, Bhalla S, Chung JH, Chung M, et al. Radiological Society of North America expert consensus document on reporting chest CT findings related to COVID-19: endorsed by the Society of Thoracic Radiology, the American College of Radiology, and RSNA. Radiol Cardiothorac Imaging. 2020;2:e200152.","DOI":"10.1148\/ryct.2020200152"},{"key":"3262_CR49","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1007\/s00330-020-07300-y","volume":"31","author":"I Espallargas","year":"2021","unstructured":"Espallargas I, Rodriguez Sevilla JJ, Rodriguez Chiaradia DA, Salar A, Casamayor G, Villar-Garcia J, et al. CT imaging of pulmonary embolism in patients with COVID-19 pneumonia: a retrospective analysis. Eur Radiol. 2021;31:1915\u201322.","journal-title":"Eur Radiol"},{"key":"3262_CR50","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1007\/s11547-015-0595-0","volume":"121","author":"N Sverzellati","year":"2016","unstructured":"Sverzellati N, Arcadi T, Salvolini L, Dore R, Zompatori M, Mereu M, et al. Under-reporting of cardiovascular findings on chest CT. Radiol Med. 2016;121:190\u20139.","journal-title":"Radiol Med"},{"key":"3262_CR51","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","volume":"45","author":"M Sokolova","year":"2009","unstructured":"Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inf Process Manag. 2009;45:427\u201337.","journal-title":"Inf Process Manag"},{"key":"3262_CR52","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15:1929\u201358.","journal-title":"J Mach Learn Res"},{"key":"3262_CR53","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, Sutskever I, Salakhutdinov RR. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580. 2012."},{"key":"3262_CR54","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2018.03.016","volume":"104","author":"A Poernomo","year":"2018","unstructured":"Poernomo A, Kang D-K. Biased dropout and crossmap dropout: learning towards effective dropout regularization in convolutional neural network. Neural Netw. 2018;104:60\u20137.","journal-title":"Neural Netw"},{"key":"3262_CR55","doi-asserted-by":"crossref","unstructured":"van de Ven GM, Soures N, Kudithipudi D. Continual learning and catastrophic forgetting. arXiv preprint arXiv:2403.05175. 2024.","DOI":"10.1016\/B978-0-443-15754-7.00073-0"},{"key":"3262_CR56","doi-asserted-by":"crossref","unstructured":"Chang TA, Arnett C, Tu Z, Bergen BK. When is multilinguality a curse? language modeling for 250 high-and low-resource languages. arXiv preprint arXiv:2311.09205. 2023.","DOI":"10.18653\/v1\/2024.emnlp-main.236"},{"key":"3262_CR57","doi-asserted-by":"crossref","unstructured":"Rust P, Pfeiffer J, Vuli\u0107 I, Ruder S, Gurevych I. How good is your tokenizer? on the monolingual performance of multilingual language models. arXiv preprint arXiv:2012.15613. 2020.","DOI":"10.18653\/v1\/2021.acl-long.243"},{"key":"3262_CR58","doi-asserted-by":"crossref","unstructured":"Dunn A, Inkpen D, Andonie R. Context-sensitive visualization of deep learning natural language processing models. In: 2021 25th International Conference on Information Visualisation (IV). IEEE; 2021;170\u20135.","DOI":"10.1109\/IV53921.2021.00035"},{"key":"3262_CR59","doi-asserted-by":"crossref","unstructured":"Thompson B, Gwinnup J, Khayrallah H, Duh K, Koehn P. Overcoming catastrophic forgetting during domain adaptation of neural machine translation. 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: association for computational linguistics; 2019;2062-8.","DOI":"10.18653\/v1\/N19-1209"},{"key":"3262_CR60","doi-asserted-by":"crossref","unstructured":"Bai A, Yeh C-K, Hsieh C-J, Taly A. An efficient rehearsal scheme for catastrophic forgetting mitigation during multi-stage fine-tuning. arXiv preprint arXiv:2402.08096. 2025.","DOI":"10.18653\/v1\/2025.findings-naacl.138"},{"key":"3262_CR61","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1007\/s10115-022-01736-y","volume":"64","author":"M Ryu","year":"2022","unstructured":"Ryu M, Lee G, Lee K. Knowledge distillation for Bert unsupervised domain adaptation. Knowl Inf Syst. 2022;64:3113\u201328.","journal-title":"Knowl Inf Syst"},{"key":"3262_CR62","doi-asserted-by":"crossref","unstructured":"Winata GI, Xie L, Radhakrishnan K, Wu S, Jin X, Cheng P et al. Overcoming catastrophic forgetting in massively multilingual continual learning. arXiv preprint arXiv:2305.16252. 2023.","DOI":"10.18653\/v1\/2023.findings-acl.48"},{"key":"3262_CR63","doi-asserted-by":"crossref","unstructured":"Cho S, Jeon J, Lee D, Lee C, Kim J. Dsg-kd: knowledge distillation from domain-specific to general language models. IEEE Access. 2024.","DOI":"10.1109\/ACCESS.2024.3457850"},{"key":"3262_CR64","doi-asserted-by":"publisher","first-page":"864","DOI":"10.3390\/math13050864","volume":"13","author":"HA Jeong","year":"2025","unstructured":"Jeong HA, Context-Preserving. Tokenization mismatch resolution method for Korean word sense disambiguation based on the Sejong corpus and BERT. Mathematics. 2025;13:864.","journal-title":"Mathematics"},{"key":"3262_CR65","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s12859-022-04688-w","volume":"23","author":"U Naseem","year":"2022","unstructured":"Naseem U, Dunn AG, Khushi M, Kim J. Benchmarking for biomedical natural Language processing tasks with a domain specific ALBERT. BMC Bioinformatics. 2022;23:144.","journal-title":"BMC Bioinformatics"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03262-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-025-03262-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-025-03262-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T13:05:01Z","timestamp":1764075901000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-025-03262-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["3262"],"URL":"https:\/\/doi.org\/10.1186\/s12911-025-03262-7","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,25]]},"assertion":[{"value":"1 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethics declarations"}},{"value":"The study was conducted in accordance with the Declaration of Helsinki and was approved by the Institutional Review Board of Korea University Anam Hospital (IRB No. 2024AN0261). This study utilized pseudonymized medical data in accordance with Article 28\u2009\u2212\u20092 of South Korea\u2019s Personal Information Protection Act (PIPA) and the 2024 Guideline for Healthcare Data Utilization (Ministry of Health and Welfare). The requirement for written informed consent was waived by the Institutional Review Board of Korea University Anam Hospital (IRB No. 2024AN0261) because this retrospective research involved secondary analysis of existing de-identified clinical data, posed minimal risk to participants, and complied with PIPA\u2019s exemption provisions for pseudonymized data used in scientific research.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"428"}}