{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:37:42Z","timestamp":1758587862552,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060037","type":"print"},{"value":"9783032060044","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-06004-4_33","type":"book-chapter","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:22:18Z","timestamp":1758561738000},"page":"331-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aligning Multimodal Large Language Models with\u00a0Patient-Physician Dialogues for\u00a0AI-Assisted Clinical Support"],"prefix":"10.1007","author":[{"given":"Junyong","family":"Lee","sequence":"first","affiliation":[]},{"given":"Jeihee","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Jiwon","family":"Ryu","sequence":"additional","affiliation":[]},{"given":"Shiho","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"33_CR1","doi-asserted-by":"publisher","first-page":"e59505","DOI":"10.2196\/59505","volume":"26","author":"R AlSaad","year":"2024","unstructured":"AlSaad, R., et al.: Multimodal large language models in health care: applications, challenges, and future outlook. J. Med. Internet Res. 26, e59505 (2024)","journal-title":"J. Med. Internet Res."},{"key":"33_CR2","unstructured":"Ben Abacha, A., Sarrouti, M., Demner-Fushman, D., Hasan, S.A., M\u00fcller, H.: Overview of the vqa-med task at imageclef 2021: visual question answering and generation in the medical domain. In: CLEF 2021 Working Notes. CEUR Workshop Proceedings, CEUR-WS.org, Bucharest, Romania, 21\u201324 September 2021"},{"key":"33_CR3","first-page":"12546","volume":"33","author":"K Chaitanya","year":"2020","unstructured":"Chaitanya, K., Erdil, E., Karani, N., Konukoglu, E.: Contrastive learning of global and local features for medical image segmentation with limited annotations. Adv. Neural. Inf. Process. Syst. 33, 12546\u201312558 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Clunie, D., et\u00a0al.: Summary of the national cancer institute 2023 virtual workshop on medical image de-identification-part 2: pathology whole slide image de-identification, de-facing, the role of ai in image de-identification, and the nci midi datasets and pipeline. J. Imaging Inf. Med. 1\u201315 (2024)","DOI":"10.1007\/s10278-024-01183-x"},{"key":"33_CR5","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning. In: Thirty-seventh Conference on Neural Information Processing Systems (2023), https:\/\/openreview.net\/forum?id=vvoWPYqZJA"},{"key":"33_CR6","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Front. Artif. Intell. 7, 1430984 (2024)","journal-title":"Front. Artif. Intell."},{"key":"33_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/978-3-030-85251-1_23","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"B Ionescu","year":"2021","unstructured":"Ionescu, B., et al.: Overview of the ImageCLEF 2021: multimedia retrieval in medical, nature, internet and social media applications. In: Candan, K.S., et al. (eds.) CLEF 2021. LNCS, vol. 12880, pp. 345\u2013370. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85251-1_23"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Leong, H.Y., Gao, Y.F., Shuai, J., Zhang, Y., Pamuksuz, U.: Efficient fine-tuning of large language models for automated medical documentation. arXiv preprint arXiv:2409.09324 (2024)","DOI":"10.1109\/DSInS64146.2024.10992195"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Z., Zhang, K., Dan, R., Jiang, S., Zhang, Y.: Chatdoctor: a medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge. Cureus 15(6) (2023)","DOI":"10.7759\/cureus.40895"},{"issue":"7","key":"33_CR12","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TMI.2022.3149344","volume":"41","author":"Z Liao","year":"2022","unstructured":"Liao, Z., Xie, Y., Hu, S., Xia, Y.: Learning from ambiguous labels for lung nodule malignancy prediction. IEEE Trans. Med. Imaging 41(7), 1874\u20131884 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"5","key":"33_CR13","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1109\/TMI.2022.3232411","volume":"42","author":"B Liu","year":"2022","unstructured":"Liu, B., Zhan, L.M., Xu, L., Wu, X.M.: Medical visual question answering via conditional reasoning and contrastive learning. IEEE Trans. Med. Imaging 42(5), 1532\u20131545 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"33_CR14","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"33_CR15","doi-asserted-by":"publisher","first-page":"e52865","DOI":"10.2196\/52865","volume":"25","author":"B Mesk\u00f3","year":"2023","unstructured":"Mesk\u00f3, B.: The impact of multimodal large language models on health care\u2019s future. J. Med. Internet Res. 25, e52865 (2023)","journal-title":"J. Med. Internet Res."},{"key":"33_CR16","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"key":"33_CR17","unstructured":"MTSamples: Mtsamples: medical transcription samples and example reports (2025), https:\/\/mtsamples.com, Accessed 19 Feb 2025"},{"key":"33_CR18","unstructured":"M\u00fcller, R., Kornblith, S., Hinton, G.E.: When does label smoothing help? In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"4","key":"33_CR19","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1109\/JBHI.2022.3163751","volume":"27","author":"U Naseem","year":"2022","unstructured":"Naseem, U., Khushi, M., Kim, J.: Vision-language transformer for interpretable pathology visual question answering. IEEE J. Biomed. Health Inform. 27(4), 1681\u20131690 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"1","key":"33_CR20","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41746-020-0258-y","volume":"3","author":"B Norgeot","year":"2020","unstructured":"Norgeot, B., et al.: Protected health information filter (philter): accurately and securely de-identifying free-text clinical notes. NPJ Digit. Med. 3(1), 57 (2020)","journal-title":"NPJ Digit. Med."},{"issue":"6","key":"33_CR21","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1089\/big.2021.0169","volume":"12","author":"IE Olatunji","year":"2024","unstructured":"Olatunji, I.E., Rauch, J., Katzensteiner, M., Khosla, M.: A review of anonymization for healthcare data. Big Data 12(6), 538\u2013555 (2024)","journal-title":"Big Data"},{"key":"33_CR22","doi-asserted-by":"publisher","first-page":"108111","DOI":"10.1016\/j.patcog.2021.108111","volume":"120","author":"R Singh","year":"2021","unstructured":"Singh, R., Bharti, V., Purohit, V., Kumar, A., Singh, A.K., Singh, S.K.: Metamed: few-shot medical image classification using gradient-based meta-learning. Pattern Recogn. 120, 108111 (2021)","journal-title":"Pattern Recogn."},{"key":"33_CR23","unstructured":"Singhal, K., et\u00a0al.: Toward expert-level medical question answering with large language models. Nat. Med. 1\u20138 (2025)"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Subramanian, S., et al.: Medicat: a dataset of medical images, captions, and textual references. arXiv preprint arXiv:2010.06000 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Thawkar, O., et al.: Xraygpt: chest radiographs summarization using medical vision-language models. arXiv preprint arXiv:2306.07971 (2023)","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Notechat: a dataset of synthetic doctor-patient conversations conditioned on clinical notes. arXiv preprint arXiv:2310.15959 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.901"},{"key":"33_CR27","unstructured":"Yang, X., et\u00a0al.: Gatortron: a large clinical language model to unlock patient information from unstructured electronic health records. arXiv preprint arXiv:2203.03540 (2022)"},{"key":"33_CR28","doi-asserted-by":"crossref","unstructured":"Yu, F., et\u00a0al.: Evaluating progress in automatic chest x-ray radiology report generation. Patterns 4(9) (2023)","DOI":"10.1016\/j.patter.2023.100802"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Zeng, G., et\u00a0al.: Meddialog: large-scale medical dialogue datasets. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 9241\u20139250 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.743"},{"key":"33_CR30","unstructured":"Zhang, S., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, X., Ding, J., Wu, M., Wong, S.T., Van\u00a0Nguyen, H., Pan, M.: Adaptive privacy preserving deep learning algorithms for medical data. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1169\u20131178 (2021)","DOI":"10.1109\/WACV48630.2021.00121"}],"container-title":["Lecture Notes in Computer Science","AI for Clinical Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06004-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:22:25Z","timestamp":1758561745000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06004-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"ISBN":["9783032060037","9783032060044"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06004-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"22 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CMLLMs","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Multimodal Large Language Models in Clinical Practice","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cmllms2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/clinicalmllms.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}