{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T04:29:49Z","timestamp":1768451389653,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1145\/3765612.3767193","type":"proceedings-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T17:45:59Z","timestamp":1765388759000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0237-6891","authenticated-orcid":false,"given":"Zerui","family":"Xu","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7240-3915","authenticated-orcid":false,"given":"Fang","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7774-6018","authenticated-orcid":false,"given":"Yingzhou","family":"Lu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0565-6813","authenticated-orcid":false,"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3401-4921","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23091165"},{"key":"e_1_3_2_2_2_1","first-page":"600","article-title":"Clinical trials in the era of artificial intelligence","volume":"20","author":"Bhatt Deepak L","year":"2021","unstructured":"Deepak L Bhatt et al. 2021. Clinical trials in the era of artificial intelligence. Nature Reviews Drug Discovery 20, 8 (2021), 600\u2013602.","journal-title":"Nature Reviews Drug Discovery"},{"key":"e_1_3_2_2_3_1","volume-title":"Trialbench: Multi-modal artificial intelligence-ready clinical trial datasets. arXiv preprint arXiv:2407.00631","author":"Chen Jintai","year":"2024","unstructured":"Jintai Chen, Yaojun Hu, Yue Wang, Yingzhou Lu, Xu Cao, Miao Lin, Hongxia Xu, Jian Wu, Cao Xiao, Jimeng Sun, et al. 2024. Trialbench: Multi-modal artificial intelligence-ready clinical trial datasets. arXiv preprint arXiv:2407.00631 (2024)."},{"key":"e_1_3_2_2_4_1","first-page":"107","article-title":"Ethical and regulatory considerations for using artificial intelligence in clinical trials","volume":"326","author":"Chen Jonathan H","year":"2021","unstructured":"Jonathan H Chen and Steven M Asch. 2021. Ethical and regulatory considerations for using artificial intelligence in clinical trials. JAMA 326, 2 (2021), 107\u2013108.","journal-title":"JAMA"},{"key":"e_1_3_2_2_5_1","volume-title":"David M Herrington, and Yue Wang.","author":"Chen Lulu","year":"2021","unstructured":"Lulu Chen, Yingzhou Lu, Chiung-Ting Wu, Robert Clarke, Guoqiang Yu, Jennifer E Van Eyk, David M Herrington, and Yue Wang. 2021. Data-driven detection of subtype-specific differentially expressed genes. Scientific reports 11, 1 (2021), 1\u201312."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-021-00751-8"},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the 2nd Machine Learning for Healthcare Conference","volume":"68","author":"Edward","unstructured":"Edward Choi et al. 2017. Generating Multi-label Discrete Patient Records using Generative Adversarial Networks. In Proceedings of the 2nd Machine Learning for Healthcare Conference, Vol. 68. PMLR."},{"key":"e_1_3_2_2_8_1","volume-title":"Guoqiang Yu, Robert Clarke, David M Herrington, et al.","author":"Du Dongping","year":"2023","unstructured":"Dongping Du, Saurabh Bhardwaj, Sarah J Parker, Zuolin Cheng, Zhen Zhang, Yingzhou Lu, Jennifer E Van Eyk, Guoqiang Yu, Robert Clarke, David M Herrington, et al. 2023. ABDS: tool suite for analyzing biologically diverse samples. bioRxiv (2023), 2023\u201307."},{"key":"e_1_3_2_2_9_1","volume-title":"Deep Generative Models for Synthetic Data. Comput. Surveys","author":"Eigenschink Peter","year":"2021","unstructured":"Peter Eigenschink, Stefan Vamosi, Ralf Vamosi, Chang Sun, Thomas Reutterer, and Klaudius Kalcher. 2021. Deep Generative Models for Synthetic Data. Comput. Surveys (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Fundamentals of clinical trials","author":"Friedman Lawrence M","unstructured":"Lawrence M Friedman, Curt D Furberg, David L DeMets, David M Reboussin, and Christopher B Granger. 2015. Fundamentals of clinical trials. Springer."},{"key":"e_1_3_2_2_11_1","volume-title":"ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. 223\u2013232","author":"Fu Tianfan","year":"2019","unstructured":"Tianfan Fu, Tian Gao, Cao Xiao, Tengfei Ma, and Jimeng Sun. 2019. Pearl: Prototype learning via rule learning. In ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. 223\u2013232."},{"key":"e_1_3_2_2_12_1","first-page":"065","article-title":"Automated prediction of clinical trial outcome","volume":"17","author":"Fu Tianfan","year":"2023","unstructured":"Tianfan Fu, Kexin Huang, and Jimeng Sun. 2023. Automated prediction of clinical trial outcome. US Patent App. 17\/749,065.","journal-title":"US Patent App."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100445"},{"key":"e_1_3_2_2_14_1","volume-title":"0: Determining significant rewiring of biological network structure with differential dependency networks. Bioinformatics","author":"Fu Yi","year":"2024","unstructured":"Yi Fu, Yingzhou Liu, Yizhi Wang, Bai Zhang, Zhen Zhang, Guoqiang Yu, Chunyu Liu, Robert Clarke, David M Herrington, and Yue Wang. 2024. DDN3. 0: Determining significant rewiring of biological network structure with differential dependency networks. Bioinformatics (2024), btae376."},{"key":"e_1_3_2_2_15_1","volume-title":"Generation and evaluation of synthetic patient data. BMC medical research methodology 20, 1","author":"Goncalves Andre","year":"2020","unstructured":"Andre Goncalves, Priyadip Ray, Braden Soper, Jennifer Stevens, Linda Coyle, and Ana Paula Sales. 2020. Generation and evaluation of synthetic patient data. BMC medical research methodology 20, 1 (2020), 1\u201340."},{"key":"e_1_3_2_2_16_1","first-page":"870","article-title":"Synthetic data for clinical research","volume":"4","author":"Jordon James","year":"2020","unstructured":"James Jordon, Jinsung Yoon, and Mihaela van der Schaar. 2020. Synthetic data for clinical research. Nature Biomedical Engineering 4, 9 (2020), 870\u2013872.","journal-title":"Nature Biomedical Engineering"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-017-0778-4"},{"key":"e_1_3_2_2_18_1","volume-title":"4 Ways to fix the clinical trial: clinical trials are crumbling under modern economic and scientific pressures. Nature looks at ways they might be saved. Nature 477, 7366","author":"Ledford Heidi","year":"2011","unstructured":"Heidi Ledford. 2011. 4 Ways to fix the clinical trial: clinical trials are crumbling under modern economic and scientific pressures. Nature looks at ways they might be saved. Nature 477, 7366 (2011), 526\u2013529."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"e_1_3_2_2_20_1","unstructured":"Yingzhou Lu. 2018. Multi-omics Data Integration for Identifying Disease Specific Biological Pathways. Ph. D. Dissertation. Virginia Tech."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.34133\/hds.0126"},{"key":"e_1_3_2_2_22_1","volume-title":"Guoqiang Yu, Robert Clarke, David M Herrington, and Yue Wang.","author":"Lu Yingzhou","year":"2022","unstructured":"Yingzhou Lu, Chiung-Ting Wu, Sarah J Parker, Zuolin Cheng, Georgia Saylor, Jennifer E Van Eyk, Guoqiang Yu, Robert Clarke, David M Herrington, and Yue Wang. 2022. COT: an efficient and accurate method for detecting marker genes among many subtypes. Bioinformatics Advances 2, 1 (2022), vbac037."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2017.70"},{"key":"e_1_3_2_2_24_1","volume-title":"Clinical trial methodology. Nature 272, 5648","author":"Peto Richard","year":"1978","unstructured":"Richard Peto. 1978. Clinical trial methodology. Nature 272, 5648 (1978), 15\u201316."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259"},{"key":"e_1_3_2_2_26_1","volume-title":"Medagentsbench: Benchmarking thinking models and agent frameworks for complex medical reasoning. arXiv preprint arXiv:2503.07459","author":"Xiangru Tang","year":"2025","unstructured":"Xiangru Tang et al. 2025. Medagentsbench: Benchmarking thinking models and agent frameworks for complex medical reasoning. arXiv preprint arXiv:2503.07459 (2025)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Allan Tucker et al. 2020. Generating high-fidelity synthetic patient data for assessing machine learning healthcare software. NPJ digital medicine 3 1 (2020) 1\u201313.","DOI":"10.1038\/s41746-020-00353-9"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-05457-0_17"},{"key":"e_1_3_2_2_29_1","volume-title":"TWIN-GPT: Digital Twins for Clinical Trials via Large Language Model. arXiv preprint arXiv:2404.01273","author":"Wang Yue","year":"2024","unstructured":"Yue Wang, Yingzhou Lu, Yinlong Xu, Zihan Ma, Hongxia Xu, Bang Du, Honghao Gao, and Jian Wu. 2024. TWIN-GPT: Digital Twins for Clinical Trials via Large Language Model. arXiv preprint arXiv:2404.01273 (2024)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539279"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Chiung-Ting Wu et al. 2022. Cosbin: cosine score-based iterative normalization of biologically diverse samples. Bioinformatics Advances 2 1 (2022) vbac076.","DOI":"10.1093\/bioadv\/vbac076"},{"key":"e_1_3_2_2_32_1","first-page":"1","article-title":"Generating synthetic data for medical research using generative adversarial networks","volume":"11","author":"Lei Xu","year":"2020","unstructured":"Lei Xu et al. 2020. Generating synthetic data for medical research using generative adversarial networks. Nature Communications 11, 1 (2020), 1\u20137.","journal-title":"Nature Communications"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698587.3701359"},{"key":"e_1_3_2_2_34_1","volume-title":"TrialDura: Hierarchical Attention Transformer for Interpretable Clinical Trial Duration Prediction. NeurIPS 2024 Workshop on AI for New Drug Modalities","author":"Yue Ling","year":"2024","unstructured":"Ling Yue, Jonathan Li, Md Zabirul Islam, Bolun Xia, Tianfan Fu, and Jintai Chen. 2024. TrialDura: Hierarchical Attention Transformer for Interpretable Clinical Trial Duration Prediction. NeurIPS 2024 Workshop on AI for New Drug Modalities (2024)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698587.3701375"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1101\/2021.04.10.439301"}],"event":{"name":"BCB '25: 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics","location":"Element Philadelphia Downtown Philadelphia PA USA","acronym":"BCB '25","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765612.3767193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T17:47:20Z","timestamp":1765388840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765612.3767193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":36,"alternative-id":["10.1145\/3765612.3767193","10.1145\/3765612"],"URL":"https:\/\/doi.org\/10.1145\/3765612.3767193","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-12-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}