{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:01Z","timestamp":1776885181261,"version":"3.51.2"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031476785","type":"print"},{"value":"9783031476792","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-47679-2_7","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T10:02:23Z","timestamp":1700906543000},"page":"86-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Multimodal LLMs for\u00a0Health Grounded in\u00a0Individual-Specific Data"],"prefix":"10.1007","author":[{"given":"Anastasiya","family":"Belyaeva","sequence":"first","affiliation":[]},{"given":"Justin","family":"Cosentino","sequence":"additional","affiliation":[]},{"given":"Farhad","family":"Hormozdiari","sequence":"additional","affiliation":[]},{"given":"Krish","family":"Eswaran","sequence":"additional","affiliation":[]},{"given":"Shravya","family":"Shetty","sequence":"additional","affiliation":[]},{"given":"Greg","family":"Corrado","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Carroll","sequence":"additional","affiliation":[]},{"given":"Cory Y.","family":"McLean","sequence":"additional","affiliation":[]},{"given":"Nicholas A.","family":"Furlotte","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"issue":"9","key":"7_CR1","doi-asserted-by":"publisher","first-page":"1773","DOI":"10.1038\/s41591-022-01981-2","volume":"28","author":"JN Acosta","year":"2022","unstructured":"Acosta, J.N., Falcone, G.J., Rajpurkar, P., Topol, E.J.: Multimodal biomedical AI. Nat. Med. 28(9), 1773\u20131784 (2022)","journal-title":"Nat. Med."},{"key":"7_CR2","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 23716\u201323736 (2022)"},{"issue":"7","key":"7_CR3","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1016\/j.ajhg.2021.05.004","volume":"108","author":"B Alipanahi","year":"2021","unstructured":"Alipanahi, B., et al.: Large-scale machine-learning-based phenotyping significantly improves genomic discovery for optic nerve head morphology. Am. J. Hum. Genet. 108(7), 1217\u20131230 (2021)","journal-title":"Am. J. Hum. Genet."},{"key":"7_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1877\u20131901 (2020)"},{"issue":"7726","key":"7_CR5","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","volume":"562","author":"C Bycroft","year":"2018","unstructured":"Bycroft, C., et al.: The UK Biobank resource with deep phenotyping and genomic data. Nature 562(7726), 203\u2013209 (2018)","journal-title":"Nature"},{"key":"7_CR6","doi-asserted-by":"publisher","unstructured":"Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 785\u2013794. ACM, New York (2016). https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"7_CR7","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"7_CR8","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1038\/s41588-023-01372-4","volume":"55","author":"J Cosentino","year":"2023","unstructured":"Cosentino, J., et al.: Inference of chronic obstructive pulmonary disease with deep learning on raw spirograms identifies new genetic loci and improves risk models. Nat. Genet. 55, 787\u2013795 (2023)","journal-title":"Nat. Genet."},{"issue":"11","key":"7_CR9","doi-asserted-by":"publisher","first-page":"e1008432","DOI":"10.1371\/journal.pgen.1008432","volume":"15","author":"A Diaz-Papkovich","year":"2019","unstructured":"Diaz-Papkovich, A., Anderson-Trocm\u00e9, L., Ben-Eghan, C., Gravel, S.: UMAP reveals cryptic population structure and phenotype heterogeneity in large genomic cohorts. PLoS Genet. 15(11), e1008432 (2019)","journal-title":"PLoS Genet."},{"key":"7_CR10","unstructured":"Dinh, T., et al.: LIFT: language-interfaced fine-tuning for non-language machine learning tasks. In: Advances in Neural Information Processing Systems, vol. 35, pp. 11763\u201311784 (2022)"},{"key":"7_CR11","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. arXiv preprint arXiv:2305.05665 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"7_CR13","unstructured":"Google: PaLM 2 technical report. arXiv preprint arXiv:2305.10403 (2023)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"He, T., Zhang, Z., Zhang, H., Zhang, Z., Xie, J., Li, M.: Bag of tricks for image classification with convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 558\u2013567 (2019)","DOI":"10.1109\/CVPR.2019.00065"},{"key":"7_CR16","unstructured":"Hegselmann, S., Buendia, A., Lang, H., Agrawal, M., Jiang, X., Sontag, D.: TabLLM: few-shot classification of tabular data with large language models. In: International Conference on Artificial Intelligence and Statistics, pp. 5549\u20135581. PMLR (2023)"},{"key":"7_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"7_CR18","unstructured":"Kirk, H.R., Vidgen, B., R\u00f6ttger, P., Hale, S.A.: Personalisation within bounds: a risk taxonomy and policy framework for the alignment of large language models with personalised feedback. arXiv preprint arXiv:2303.05453 (2023)"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s41746-022-00712-8","volume":"5","author":"A Kline","year":"2022","unstructured":"Kline, A., et al.: Multimodal machine learning in precision health: a scoping review. npj Digit. Med. 5(1), 171 (2022)","journal-title":"npj Digit. Med."},{"key":"7_CR20","doi-asserted-by":"publisher","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"7_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"7_CR22","unstructured":"Lu, J., Clark, C., Zellers, R., Mottaghi, R., Kembhavi, A.: Unified-IO: a unified model for vision, language, and multi-modal tasks. arXiv preprint arXiv:2206.08916 (2022)"},{"issue":"7956","key":"7_CR23","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","volume":"616","author":"M Moor","year":"2023","unstructured":"Moor, M., et al.: Foundation models for generalist medical artificial intelligence. Nature 616(7956), 259\u2013265 (2023)","journal-title":"Nature"},{"key":"7_CR24","unstructured":"OpenAI: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR25","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"7_CR26","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do CIFAR-10 classifiers generalize to CIFAR-10? arXiv preprint arXiv:1806.00451 (2018)"},{"issue":"3","key":"7_CR27","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1038\/s41588-018-0342-2","volume":"51","author":"P Sakornsakolpat","year":"2019","unstructured":"Sakornsakolpat, P., et al.: Genetic landscape of chronic obstructive pulmonary disease identifies heterogeneous cell-type and phenotype associations. Nat. Genet. 51(3), 494\u2013505 (2019)","journal-title":"Nat. Genet."},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Salemi, A., Mysore, S., Bendersky, M., Zamani, H.: LaMP: when large language models meet personalization. arXiv preprint arXiv:2304.11406 (2023)","DOI":"10.18653\/v1\/2024.acl-long.399"},{"issue":"3","key":"7_CR29","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1038\/s41588-018-0321-7","volume":"51","author":"N Shrine","year":"2019","unstructured":"Shrine, N., et al.: New genetic signals for lung function highlight pathways and chronic obstructive pulmonary disease associations across multiple ancestries. Nat. Genet. 51(3), 481\u2013493 (2019)","journal-title":"Nat. Genet."},{"key":"7_CR30","unstructured":"Singhal, K., et al.: Large language models encode clinical knowledge. arXiv preprint arXiv:2212.13138 (2022)"},{"key":"7_CR31","unstructured":"Singhal, K., et al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2212.13138 (2022)"},{"key":"7_CR32","doi-asserted-by":"publisher","first-page":"103637","DOI":"10.1016\/j.jbi.2020.103637","volume":"113","author":"E Steinberg","year":"2021","unstructured":"Steinberg, E., Jung, K., Fries, J.A., Corbin, C.K., Pfohl, S.R., Shah, N.H.: Language models are an effective representation learning technique for electronic health record data. J. Biomed. Inform. 113, 103637 (2021)","journal-title":"J. Biomed. Inform."},{"issue":"4","key":"7_CR33","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1164\/rccm.201204-0596PP","volume":"187","author":"J Vestbo","year":"2013","unstructured":"Vestbo, J., et al.: Global strategy for the diagnosis, management, and prevention of chronic obstructive pulmonary disease. Am. J. Respir. Crit. Care Med. 187(4), 347\u2013365 (2013)","journal-title":"Am. J. Respir. Crit. Care Med."},{"issue":"1","key":"7_CR34","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1038\/s43856-021-00028-w","volume":"1","author":"KN Vokinger","year":"2021","unstructured":"Vokinger, K.N., Feuerriegel, S., Kesselheim, A.S.: Mitigating bias in machine learning for medicine. Commun. Med. 1(1), 25 (2021)","journal-title":"Commun. Med."},{"key":"7_CR35","unstructured":"Wang, Y., et al.: Preserving in-context learning ability in large language model fine-tuning. arXiv preprint arXiv:2211.00635 (2022)"},{"key":"7_CR36","unstructured":"Wei, J., et al.: Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)"},{"issue":"1","key":"7_CR37","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41467-020-20249-2","volume":"12","author":"KD Yang","year":"2021","unstructured":"Yang, K.D., et al.: Multi-domain translation between single-cell imaging and sequencing data using autoencoders. Nat. Commun. 12(1), 31 (2021)","journal-title":"Nat. Commun."},{"issue":"1","key":"7_CR38","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","volume":"5","author":"X Yang","year":"2022","unstructured":"Yang, X., et al.: A large language model for electronic health records. npj Digit. Med. 5(1), 194 (2022)","journal-title":"npj Digit. Med."},{"key":"7_CR39","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"issue":"1","key":"7_CR40","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/s42256-021-00425-9","volume":"4","author":"HY Zhou","year":"2022","unstructured":"Zhou, H.Y., Chen, X., Zhang, Y., Luo, R., Wang, L., Yu, Y.: Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports. Nat. Mach. Intell. 4(1), 32\u201340 (2022)","journal-title":"Nat. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Healthcare Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47679-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T09:32:09Z","timestamp":1730626329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47679-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"ISBN":["9783031476785","9783031476792"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47679-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ML4MHD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Machine Learning for Multimodal Healthcare Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Honolulu, HI","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2023","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":"ml4mhd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.mlhealthdata.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}