{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:05:23Z","timestamp":1772039123481,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679962","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:11Z","timestamp":1729452851000},"page":"3974-3978","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["MEDFuse: Multimodal EHR Data Fusion with Masked Lab-Test Modeling and Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6814-9459","authenticated-orcid":false,"given":"Phan Nguyen Minh","family":"Thao","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0777-6915","authenticated-orcid":false,"given":"Cong-Tinh","family":"Dao","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7178-1377","authenticated-orcid":false,"given":"Chenwei","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9614-6815","authenticated-orcid":false,"given":"Jian-Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5240-9114","authenticated-orcid":false,"given":"Shun","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai University of Finance and Economics, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1233-138X","authenticated-orcid":false,"given":"Jun-En","family":"Ding","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology, Hoboken, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3789-1957","authenticated-orcid":false,"given":"David","family":"Restrepo","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Cambridge, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5225-8199","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"Stevens Institute of Technology, Hoboken, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3501-5459","authenticated-orcid":false,"given":"Fang-Ming","family":"Hung","sequence":"additional","affiliation":[{"name":"Far Eastern Memorial Hospital, New Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0172-7311","authenticated-orcid":false,"given":"Wen-Chih","family":"Peng","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AI@Meta. 2024. Llama 2 Model Card. (2024). https:\/\/huggingface.co\/meta-llama\/Llama-2--13b"},{"key":"e_1_3_2_1_2_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_1_3_1","volume-title":"Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data. arXiv preprint arXiv:2312.11502","author":"Bellamy David R","year":"2023","unstructured":"David R Bellamy, Bhawesh Kumar, Cindy Wang, and Andrew Beam. 2023. Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data. arXiv preprint arXiv:2312.11502 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Elliot Bolton Abhinav Venigalla Michihiro Yasunaga David Hall Betty Xiong Tony Lee Roxana Daneshjou Jonathan Frankle Percy Liang Michael Carbin et al. 2024. BioMedLM: A 2.7 B Parameter Language Model Trained On Biomedical Text. arXiv preprint arXiv:2403.18421 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Contrastive Learning on Multimodal Analysis of Electronic Health Records. arXiv preprint arXiv:2403.14926","author":"Cai Tianxi","year":"2024","unstructured":"Tianxi Cai, Feiqing Huang, Ryumei Nakada, Linjun Zhang, and Doudou Zhou. 2024. Contrastive Learning on Multimodal Analysis of Electronic Health Records. arXiv preprint arXiv:2403.14926 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016252"},{"key":"e_1_3_2_1_7_1","volume-title":"Convolutional neural network for sentence classification. Master's thesis","author":"Chen Yahui","unstructured":"Yahui Chen. 2015. Convolutional neural network for sentence classification. Master's thesis. University of Waterloo."},{"key":"e_1_3_2_1_8_1","volume-title":"TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction. arXiv preprint arXiv:2405.16847","author":"Chen Yinda","year":"2024","unstructured":"Yinda Chen, Haoyuan Shi, Xiaoyu Liu, Te Shi, Ruobing Zhang, Dong Liu, Zhiwei Xiong, and Feng Wu. 2024. TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction. arXiv preprint arXiv:2405.16847 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart.","author":"Choi Edward","year":"2016","unstructured":"Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. 2016. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","volume-title":"Wen-Chih Peng, Jian-Zhe Wang, Chun-Cheng Chug, Min-Chen Hsieh, Yun-Chien Tseng, Ling Chen, Dongsheng Luo, Chi-Te Wang, et al.","author":"Ding Jun-En","year":"2024","unstructured":"Jun-En Ding, Phan Nguyen Minh Thao, Wen-Chih Peng, Jian-Zhe Wang, Chun-Cheng Chug, Min-Chen Hsieh, Yun-Chien Tseng, Ling Chen, Dongsheng Luo, Chi-Te Wang, et al. 2024. Large Language Multimodal Models for 5-Year Chronic Disease Cohort Prediction Using EHR Data. arXiv preprint arXiv:2403.04785 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16080"},{"key":"e_1_3_2_1_13_1","volume-title":"Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems","author":"Grinsztajn L\u00e9o","year":"2022","unstructured":"L\u00e9o Grinsztajn, Edouard Oyallon, and Ga\u00ebl Varoquaux. 2022. Why do tree-based models still outperform deep learning on typical tabular data? Advances in neural information processing systems, Vol. 35 (2022), 507--520."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 5549--5581","author":"Hegselmann Stefan","year":"2023","unstructured":"Stefan Hegselmann, Alejandro Buendia, Hunter Lang, Monica Agrawal, Xiaoyi Jiang, and David Sontag. 2023. Tabllm: Few-shot classification of tabular data with large language models. In International Conference on Artificial Intelligence and Statistics. PMLR, 5549--5581."},{"key":"e_1_3_2_1_16_1","volume-title":"Improved Multimodal Fusion for Small Datasets with Auxiliary Supervision. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). IEEE, 1--5.","author":"Holste Gregory","unstructured":"Gregory Holste, Douwe van der Wal, Hans Pinckaers, Rikiya Yamashita, Akinori Mitani, and Andre Esteva. 2023. Improved Multimodal Fusion for Small Datasets with Auxiliary Supervision. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). IEEE, 1--5."},{"key":"e_1_3_2_1_17_1","volume-title":"International journal of data mining & knowledge management process","author":"Hossin Mohammad","year":"2015","unstructured":"Mohammad Hossin and Md Nasir Sulaiman. 2015. A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process, Vol. 5, 2 (2015), 1."},{"key":"e_1_3_2_1_18_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Leo Anthony Celi, and Roger G Mark","author":"Johnson Alistair EW","year":"2016","unstructured":"Alistair EW Johnson, Tom J Pollard, Lu Shen, Li-wei H Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data, Vol. 3, 1 (2016), 1--9."},{"key":"e_1_3_2_1_20_1","volume-title":"Abdelaali Hassaine, Rema Ramakrishnan, Dexter Canoy, Yajie Zhu, Kazem Rahimi, and Gholamreza Salimi-Khorshidi.","author":"Li Yikuan","year":"2020","unstructured":"Yikuan Li, Shishir Rao, Jos\u00e9 Roberto Ayala Solares, Abdelaali Hassaine, Rema Ramakrishnan, Dexter Canoy, Yajie Zhu, Kazem Rahimi, and Gholamreza Salimi-Khorshidi. 2020. BEHRT: transformer for electronic health records. Scientific reports, Vol. 10, 1 (2020), 7155."},{"key":"e_1_3_2_1_21_1","volume-title":"Suzanne Nie, Richard Chen, Zihao Deng, Faisal Mahmood, Ruslan Salakhutdinov, and Louis-Philippe Morency.","author":"Liang Paul Pu","year":"2023","unstructured":"Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Faisal Mahmood, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2023. Quantifying & modeling feature interactions: An information decomposition framework. arXiv e-prints (2023), arXiv--2302."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44851-9_15"},{"key":"e_1_3_2_1_23_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403107"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098088"},{"key":"e_1_3_2_1_26_1","volume-title":"Evaluation metrics for unsupervised learning algorithms. arXiv preprint arXiv:1905.05667","author":"Fernando Berzal Julio-Omar","year":"2019","unstructured":"Julio-Omar Palacio-Ni no and Fernando Berzal. 2019. Evaluation metrics for unsupervised learning algorithms. arXiv preprint arXiv:1905.05667 (2019)."},{"key":"e_1_3_2_1_27_1","volume-title":"Leo Anthony Celi, and Diego M L\u00f3pez.","author":"Restrepo David","year":"2024","unstructured":"David Restrepo, Chenwei Wu, Constanza V\u00e1squez-Venegas, Luis Filipe Nakayama, Leo Anthony Celi, and Diego M L\u00f3pez. 2024. DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era. arXiv preprint arXiv:2404.12278 (2024)."},{"key":"e_1_3_2_1_28_1","unstructured":"ruslanmv. 2024. Medical-Llama3--8B-16bit: Fine-Tuned Llama3 for Medical Q&A. (2024). https:\/\/huggingface.co\/ruslanmv\/Medical-Llama3--8B"},{"key":"e_1_3_2_1_29_1","volume-title":"Zeroprompt: Streaming acoustic encoders are zero-shot masked lms. arXiv preprint arXiv:2305.10649","author":"Song Xingchen","year":"2023","unstructured":"Xingchen Song, Di Wu, Binbin Zhang, Zhendong Peng, Bo Dang, Fuping Pan, and Zhiyong Wu. 2023. Zeroprompt: Streaming acoustic encoders are zero-shot masked lms. arXiv preprint arXiv:2305.10649 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Kabilan Elangovan, Laura Gutierrez, Ting Fang Tan, and Daniel Shu Wei Ting.","author":"Thirunavukarasu Arun James","year":"2023","unstructured":"Arun James Thirunavukarasu, Darren Shu Jeng Ting, Kabilan Elangovan, Laura Gutierrez, Ting Fang Tan, and Daniel Shu Wei Ting. 2023. Large language models in medicine. Nature medicine, Vol. 29, 8 (2023), 1930--1940."},{"key":"e_1_3_2_1_31_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.156"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403087"},{"key":"e_1_3_2_1_34_1","volume-title":"Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction. arXiv preprint arXiv:2401.01646","author":"Zhang Yilan","year":"2024","unstructured":"Yilan Zhang, Yingxue Xu, Jianqi Chen, Fengying Xie, and Hao Chen. 2024. Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction. arXiv preprint arXiv:2401.01646 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bea.2021.100013"}],"event":{"name":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679962","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:09Z","timestamp":1750294689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679962"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":35,"alternative-id":["10.1145\/3627673.3679962","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679962","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}