{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T08:03:31Z","timestamp":1789632211192,"version":"build-2803163510"},"reference-count":50,"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":[[2026,10,1]],"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3807501"],"award-info":[{"award-number":["2023YFC3807501"]}],"id":[{"id":"10.13039\/501100012166","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.2026.105094","type":"journal-article","created":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T06:30:10Z","timestamp":1787985010000},"page":"105094","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TriFuse: A multi-signal three-stage data distillation framework for efficient medical model training"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4258-9789","authenticated-orcid":false,"given":"Ruilong","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7807-2117","authenticated-orcid":false,"given":"Huan","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jbi.2026.105094_b1","first-page":"1","article-title":"Application of large language models in medicine","author":"Liu","year":"2025","journal-title":"Nat. Rev. Bioeng."},{"key":"10.1016\/j.jbi.2026.105094_b2","series-title":"Informatics","first-page":"57","article-title":"Large language models in healthcare and medical domain: A review","volume":"11","author":"Nazi","year":"2024"},{"key":"10.1016\/j.jbi.2026.105094_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2024.104734","article-title":"Learning to match patients to clinical trials using large language models","volume":"159","author":"Rybinski","year":"2024","journal-title":"J. Biomed. Inform."},{"issue":"9","key":"10.1016\/j.jbi.2026.105094_b4","doi-asserted-by":"crossref","first-page":"2093","DOI":"10.1109\/TMM.2017.2729400","article-title":"Retrieval from and understanding of large-scale multi-modal medical datasets: a review","volume":"19","author":"M\u00fcller","year":"2017","journal-title":"IEEE Trans. Multimed."},{"issue":"2","key":"10.1016\/j.jbi.2026.105094_b5","doi-asserted-by":"crossref","first-page":"224","DOI":"10.7763\/IJMLC.2013.V3.307","article-title":"Addressing the class imbalance problem in medical datasets","volume":"3","author":"Rahman","year":"2013","journal-title":"Int. J. Mach. Learn. Comput."},{"issue":"10","key":"10.1016\/j.jbi.2026.105094_b6","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s10462-024-10884-2","article-title":"Handling imbalanced medical datasets: review of a decade of research","volume":"57","author":"Salmi","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.jbi.2026.105094_b7","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"2112","article-title":"Medicat: A dataset of medical images, captions, and textual references","author":"Subramanian","year":"2020"},{"issue":"5","key":"10.1016\/j.jbi.2026.105094_b8","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.compbiomed.2010.03.005","article-title":"A learning method for the class imbalance problem with medical data sets","volume":"40","author":"Li","year":"2010","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b9","first-page":"11","article-title":"Evaluation of perplexity and syntactic handling capabilities of clueai models on Japanese medical texts","volume":"12","author":"Haga","year":"2025","journal-title":"Int. J. Artif. Intell."},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b10","doi-asserted-by":"crossref","first-page":"e47","DOI":"10.1016\/j.lanogw.2025.100005","article-title":"Measuring large language model uncertainty in women\u2019s health using semantic entropy and perplexity: a comparative study","volume":"1","author":"Penny-Dimri","year":"2025","journal-title":"Lancet Obs. Gynaecol., & Women\u2019s Health"},{"issue":"8","key":"10.1016\/j.jbi.2026.105094_b11","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nature Med."},{"issue":"3","key":"10.1016\/j.jbi.2026.105094_b12","doi-asserted-by":"crossref","first-page":"3161","DOI":"10.30534\/ijatcse\/2020\/104932020","article-title":"Improving classification performance for a novel imbalanced medical dataset using SMOTE method","volume":"9","author":"Mohammed","year":"2020","journal-title":"Int. J. Adv. Trends Comput. Sci. Eng."},{"key":"10.1016\/j.jbi.2026.105094_b13","doi-asserted-by":"crossref","unstructured":"I. Radosavovic, P. Doll\u00e1r, R. Girshick, G. Gkioxari, K. He, Data distillation: Towards omni-supervised learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4119\u20134128.","DOI":"10.1109\/CVPR.2018.00433"},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b14","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1109\/TPAMI.2023.3323376","article-title":"Dataset distillation: A comprehensive review","volume":"46","author":"Yu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jbi.2026.105094_b15","article-title":"A comprehensive survey on data distillation: Techniques, frameworks, and future directions","author":"Razi","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.jbi.2026.105094_b16","doi-asserted-by":"crossref","unstructured":"A. Sajedi, S. Khaki, E. Amjadian, L.Z. Liu, Y.A. Lawryshyn, K.N. Plataniotis, Datadam: Efficient dataset distillation with attention matching, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 17097\u201317107.","DOI":"10.1109\/ICCV51070.2023.01568"},{"key":"10.1016\/j.jbi.2026.105094_b17","unstructured":"Z. Ankner, C. Blakeney, K. Sreenivasan, M. Marion, M.L. Leavitt, M. Paul, Perplexed by perplexity: Perplexity-based pruning with small reference models, in: ICLR 2024 Workshop on Mathematical and Empirical Understanding of Foundation Models, 2024."},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b18","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1038\/s41746-024-01390-4","article-title":"Towards evaluating and building versatile large language models for medicine","volume":"8","author":"Wu","year":"2025","journal-title":"Npj Digit. Med."},{"issue":"3","key":"10.1016\/j.jbi.2026.105094_b19","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","year":"2025","journal-title":"Nature Med."},{"key":"10.1016\/j.jbi.2026.105094_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2026.104982","article-title":"Beyond fine-tuning: Leveraging domain-aware in-context learning with large language models for clinical named entity recognition","author":"Kim","year":"2026","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2026.105094_b21","first-page":"rs","article-title":"Me-llama: Foundation large language models for medical applications","author":"Xie","year":"2024","journal-title":"Res. Sq."},{"key":"10.1016\/j.jbi.2026.105094_b22","doi-asserted-by":"crossref","unstructured":"Y. Tian, R. Gan, Y. Song, J. Zhang, Y. Zhang, Chimed-gpt: A chinese medical large language model with full training regime and better alignment to human preferences, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 7156\u20137173.","DOI":"10.18653\/v1\/2024.acl-long.386"},{"key":"10.1016\/j.jbi.2026.105094_b23","series-title":"19th IEEE Symposium on Computer-Based Medical Systems","first-page":"708","article-title":"Class noise and supervised learning in medical domains: The effect of feature extraction","author":"Pechenizkiy","year":"2006"},{"issue":"6","key":"10.1016\/j.jbi.2026.105094_b24","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1080\/08839514.2016.1193719","article-title":"On the influence of class noise in medical data classification: Treatment using noise filtering methods","volume":"30","author":"S\u00e1ez","year":"2016","journal-title":"Appl. Artif. Intell."},{"issue":"6","key":"10.1016\/j.jbi.2026.105094_b25","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TMI.2022.3141425","article-title":"Improving medical images classification with label noise using dual-uncertainty estimation","volume":"41","author":"Ju","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.jbi.2026.105094_b26","doi-asserted-by":"crossref","first-page":"109960","DOI":"10.1109\/ACCESS.2021.3102399","article-title":"A comparative performance analysis of data resampling methods on imbalance medical data","volume":"9","author":"Khushi","year":"2021","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b27","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/s13755-020-00112-w","article-title":"RSMOTE: improving classification performance over imbalanced medical datasets","volume":"8","author":"Naseriparsa","year":"2020","journal-title":"Health Inf. Sci. Syst."},{"issue":"7","key":"10.1016\/j.jbi.2026.105094_b28","doi-asserted-by":"crossref","first-page":"189","DOI":"10.3390\/bdcc9070189","article-title":"State of the art and future directions of small language models: a systematic review","volume":"9","author":"Corradini","year":"2025","journal-title":"Big Data Cogn. Comput."},{"key":"10.1016\/j.jbi.2026.105094_b29","doi-asserted-by":"crossref","unstructured":"T. Gao, A. Wettig, H. Yen, D. Chen, How to train long-context language models (effectively), in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pp. 7376\u20137399.","DOI":"10.18653\/v1\/2025.acl-long.366"},{"key":"10.1016\/j.jbi.2026.105094_b30","series-title":"Dataset distillation","author":"Wang","year":"2018"},{"key":"10.1016\/j.jbi.2026.105094_b31","series-title":"Dataset meta-learning from kernel ridge-regression","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.jbi.2026.105094_b32","series-title":"Graph condensation for graph neural networks","author":"Jin","year":"2021"},{"key":"10.1016\/j.jbi.2026.105094_b33","series-title":"International Conference on Machine Learning","first-page":"5378","article-title":"Privacy for free: How does dataset condensation help privacy?","author":"Dong","year":"2022"},{"key":"10.1016\/j.jbi.2026.105094_b34","doi-asserted-by":"crossref","unstructured":"G. Cazenavette, T. Wang, A. Torralba, A.A. Efros, J.-Y. Zhu, Dataset distillation by matching training trajectories, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4750\u20134759.","DOI":"10.1109\/CVPR52688.2022.01045"},{"key":"10.1016\/j.jbi.2026.105094_b35","series-title":"International Conference on Machine Learning","first-page":"11102","article-title":"Dataset condensation via efficient synthetic-data parameterization","author":"Kim","year":"2022"},{"key":"10.1016\/j.jbi.2026.105094_b36","series-title":"International Conference on Machine Learning","first-page":"12352","article-title":"Dataset condensation with contrastive signals","author":"Lee","year":"2022"},{"key":"10.1016\/j.jbi.2026.105094_b37","doi-asserted-by":"crossref","first-page":"9813","DOI":"10.52202\/068431-0713","article-title":"Dataset distillation using neural feature regression","volume":"35","author":"Zhou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2026.105094_b38","doi-asserted-by":"crossref","unstructured":"K. Wang, B. Zhao, X. Peng, Z. Zhu, S. Yang, S. Wang, G. Huang, H. Bilen, X. Wang, Y. You, Cafe: Learning to condense dataset by aligning features, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12196\u201312205.","DOI":"10.1109\/CVPR52688.2022.01188"},{"key":"10.1016\/j.jbi.2026.105094_b39","doi-asserted-by":"crossref","unstructured":"B. Zhao, H. Bilen, Dataset condensation with distribution matching, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 6514\u20136523.","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"10.1016\/j.jbi.2026.105094_b40","doi-asserted-by":"crossref","first-page":"79155","DOI":"10.52202\/075280-3464","article-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data only","volume":"36","author":"Penedo","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2026.105094_b41","doi-asserted-by":"crossref","unstructured":"M. Li, Y. Zhang, Z. Li, J. Chen, L. Chen, N. Cheng, J. Wang, T. Zhou, J. Xiao, From quantity to quality: Boosting llm performance with self-guided data selection for instruction tuning, in: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 2024, pp. 7602\u20137635.","DOI":"10.18653\/v1\/2024.naacl-long.421"},{"key":"10.1016\/j.jbi.2026.105094_b42","doi-asserted-by":"crossref","unstructured":"M. Li, Y. Zhang, S. He, Z. Li, H. Zhao, J. Wang, N. Cheng, T. Zhou, Superfiltering: Weak-to-strong data filtering for fast instruction-tuning, in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024, pp. 14255\u201314273.","DOI":"10.18653\/v1\/2024.acl-long.769"},{"key":"10.1016\/j.jbi.2026.105094_b43","series-title":"Less: Selecting influential data for targeted instruction tuning","author":"Xia","year":"2024"},{"key":"10.1016\/j.jbi.2026.105094_b44","first-page":"97537","article-title":"Filter like you test: Data-driven data filtering for clip pretraining","volume":"38","author":"Shechter","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jbi.2026.105094_b45","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.2026.105094_b46","series-title":"International Conference on Machine Learning","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","author":"Yin","year":"2018"},{"issue":"1","key":"10.1016\/j.jbi.2026.105094_b47","doi-asserted-by":"crossref","first-page":"8384","DOI":"10.1038\/s41467-024-52417-z","article-title":"Towards building multilingual language model for medicine","volume":"15","author":"Qiu","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.jbi.2026.105094_b48","doi-asserted-by":"crossref","first-page":"3504","DOI":"10.1109\/TASLP.2021.3124365","article-title":"Pre-training with whole word masking for chinese bert","volume":"29","author":"Cui","year":"2021","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.jbi.2026.105094_b49","series-title":"Findings of the Association for Computational Linguistics: Acl 2024","first-page":"5848","article-title":"Biomistral: A collection of open-source pretrained large language models for medical domains","author":"Labrak","year":"2024"},{"key":"10.1016\/j.jbi.2026.105094_b50","doi-asserted-by":"crossref","unstructured":"H. Chen, G. Zuccon, T. Leelanupab, Beyond GeneGPT: A Multi-Agent Architecture with Open-Source LLMs for Enhanced Genomic Question Answering, in: Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, 2025, pp. 143\u2013152.","DOI":"10.1145\/3767695.3769488"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001188?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046426001188?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T07:16:47Z","timestamp":1789629407000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046426001188"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S1532046426001188"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105094","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":"TriFuse: A multi-signal three-stage data distillation framework for efficient medical model training","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2026.105094","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":"105094"}}