{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:22:46Z","timestamp":1782364966841,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402017, U23A20468"],"award-info":[{"award-number":["62402017, U23A20468"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Clinical Cohort Construction Program of Peking University Third Hospital","award":["BYSYDL2023004"],"award-info":[{"award-number":["BYSYDL2023004"]}]},{"name":"Xuzhou Scientific Technological Projects","award":["KC23143"],"award-info":[{"award-number":["KC23143"]}]},{"name":"Peking University Medicine plus X Pilot Program-Key Technologies R&D Project","award":["2024YXXLHGG007"],"award-info":[{"award-number":["2024YXXLHGG007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709166","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:42:22Z","timestamp":1743792142000},"page":"765-776","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Learnable Prompt as Pseudo-Imputation: Rethinking the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9682-9934","authenticated-orcid":false,"given":"Weibin","family":"Liao","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2640-6477","authenticated-orcid":false,"given":"Yinghao","family":"Zhu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5454-6764","authenticated-orcid":false,"given":"Zhongji","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software and Microelectronics, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0141-3827","authenticated-orcid":false,"given":"Yuhang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software and Microelectronics, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1257-9580","authenticated-orcid":false,"given":"Zixiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software and Microelectronics, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0520-7196","authenticated-orcid":false,"given":"Xu","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China, Center on Frontiers of Computing Studies, Peking University, Beijing, China, Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China, & Peking University Information Technology Institute (Tianjin Binhai), Peking University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8026-9688","authenticated-orcid":false,"given":"Yasha","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-0624","authenticated-orcid":false,"given":"Liantao","family":"Ma","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Software Engineering, Peking University, Beijing, China & Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Impact of missing data on bias and precision when estimating change in patient-reported outcomes from a clinical registry. Health and quality of life outcomes","author":"Ayilara Olawale F","year":"2019","unstructured":"Olawale F Ayilara, Lisa Zhang, Tolulope T Sajobi, Richard Sawatzky, Eric Bohm, and Lisa M Lix. 2019. Impact of missing data on bias and precision when estimating change in patient-reported outcomes from a clinical registry. Health and quality of life outcomes, Vol. 17 (2019), 1--9."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476300"},{"key":"e_1_3_2_2_3_1","volume-title":"Brits: Bidirectional recurrent imputation for time series. Advances in neural information processing systems","author":"Cao Wei","year":"2018","unstructured":"Wei Cao, Dong Wang, Jian Li, Hao Zhou, Lei Li, and Yitan Li. 2018. Brits: Bidirectional recurrent imputation for time series. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_2_5_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_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-srw.27"},{"key":"e_1_3_2_2_7_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_2_8_1","volume-title":"Stef Van Buuren, and Elise Dusseldorp","author":"Doove Lisa L","year":"2014","unstructured":"Lisa L Doove, Stef Van Buuren, and Elise Dusseldorp. 2014. Recursive partitioning for missing data imputation in the presence of interaction effects. Computational statistics & data analysis, Vol. 72 (2014), 92--104."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119619"},{"key":"e_1_3_2_2_10_1","volume-title":"International conference on artificial intelligence and statistics. PMLR, 1651--1661","author":"Fortuin Vincent","year":"2020","unstructured":"Vincent Fortuin, Dmitry Baranchuk, Gunnar R\u00e4tsch, and Stephan Mandt. 2020. Gp-vae: Deep probabilistic time series imputation. In International conference on artificial intelligence and statistics. PMLR, 1651--1661."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.100951"},{"key":"e_1_3_2_2_12_1","volume-title":"Informative missingness in electronic health record systems: the curse of knowing. Diagnostic and prognostic research","author":"Groenwold Rolf HH","year":"2020","unstructured":"Rolf HH Groenwold. 2020. Informative missingness in electronic health record systems: the curse of knowing. Diagnostic and prognostic research, Vol. 4, 1 (2020), 8."},{"key":"e_1_3_2_2_13_1","unstructured":"HM Hospitales. 2020. Covid Data Save Lives. https:\/\/www.hmhospitales.com\/prensa\/notas-de-prensa\/comunicado-covid-data-save-lives. Accessed: 2024-01--16."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"crossref","unstructured":"Alistair EW Johnson Lucas Bulgarelli Lu Shen Alvin Gayles Ayad Shammout Steven Horng Tom J Pollard Sicheng Hao Benjamin Moody Brian Gow et al. 2023. MIMIC-IV a freely accessible electronic health record dataset. Scientific data Vol. 10 1 (2023) 1.","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_2_2_16_1","first-page":"11530","article-title":"What'sa good imputation to predict with missing values","volume":"34","author":"Morvan Marine Le","year":"2021","unstructured":"Marine Le Morvan, Julie Josse, Erwan Scornet, and Ga\u00ebl Varoquaux. 2021. What'sa good imputation to predict with missing values? Advances in Neural Information Processing Systems, Vol. 34 (2021), 11530--11540.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Jiang Li Xiaowei S Yan Durgesh Chaudhary Venkatesh Avula Satish Mudiganti Hannah Husby Shima Shahjouei Ardavan Afshar Walter F Stewart Mohammed Yeasin et al. 2021. Imputation of missing values for electronic health record laboratory data. NPJ digital medicine Vol. 4 1 (2021) 147.","DOI":"10.1038\/s41746-021-00518-0"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_2_20_1","volume-title":"TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees. arXiv preprint arXiv:2410.12854","author":"Liao Weibin","year":"2024","unstructured":"Weibin Liao, Xu Chu, and Yasha Wang. 2024. TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees. arXiv preprint arXiv:2410.12854 (2024)."},{"key":"e_1_3_2_2_21_1","volume-title":"Zhengxiao Du, Zhilin Yang, and Jie Tang.","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Lam Tam, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv preprint arXiv:2110.07602 (2021)."},{"key":"e_1_3_2_2_22_1","volume-title":"Naomi: Non-autoregressive multiresolution sequence imputation. Advances in neural information processing systems","author":"Liu Yukai","year":"2019","unstructured":"Yukai Liu, Rose Yu, Stephan Zheng, Eric Zhan, and Yisong Yue. 2019. Naomi: Non-autoregressive multiresolution sequence imputation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/429"},{"key":"e_1_3_2_2_24_1","volume-title":"Patterns","volume":"4","author":"Ma Liantao","year":"2023","unstructured":"Liantao Ma, Chaohe Zhang, Junyi Gao, Xianfeng Jiao, Zhihao Yu, Yinghao Zhu, Tianlong Wang, Xinyu Ma, Yasha Wang, Wen Tang, et al. 2023a. Mortality prediction with adaptive feature importance recalibration for peritoneal dialysis patients. Patterns, Vol. 4, 12 (2023)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100892"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5428"},{"key":"e_1_3_2_2_27_1","volume-title":"Patient Health Representation Learning via Correlational Sparse Prior of Medical Features","author":"Ma Xinyu","year":"2022","unstructured":"Xinyu Ma, Yasha Wang, Xu Chu, Liantao Ma, Wen Tang, Junfeng Zhao, Ye Yuan, and Guoren Wang. 2022. Patient Health Representation Learning via Correlational Sparse Prior of Medical Features. IEEE Transactions on Knowledge and Data Engineering (2022)."},{"key":"e_1_3_2_2_28_1","unstructured":"William Gregory Madow Harold Nisselson Ingram Olkin Donald B Rubin et al. 1983. Incomplete data in sample surveys. (No Title) (1983)."},{"key":"e_1_3_2_2_29_1","volume-title":"Advanced structural equation modeling: Issues and techniques","author":"Marcoulides George A","unstructured":"George A Marcoulides and Randall E Schumacker. 2013. Advanced structural equation modeling: Issues and techniques. Psychology Press."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17086"},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Petroni Fabio","unstructured":"Fabio Petroni, Tim Rockt\u00e4schel, Sebastian Riedel, Patrick Lewis, Anton Bakhtin, Yuxiang Wu, and Alexander Miller. 2019. Language Models as Knowledge Bases?. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics."},{"key":"e_1_3_2_2_32_1","volume-title":"Jesse D Raffa, Leo A Celi, Roger G Mark, and Omar Badawi.","author":"Pollard Tom J","year":"2018","unstructured":"Tom J Pollard, Alistair EW Johnson, Jesse D Raffa, Leo A Celi, Roger G Mark, and Omar Badawi. 2018. The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Scientific data, Vol. 5, 1 (2018), 1--13."},{"key":"e_1_3_2_2_33_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_2_34_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3898--3906","author":"Ramchandran Siddharth","year":"2021","unstructured":"Siddharth Ramchandran, Gleb Tikhonov, Kalle Kujanp\u00e4\u00e4, Miika Koskinen, and Harri L\u00e4hdesm\u00e4ki. 2021. Longitudinal variational autoencoder. In International Conference on Artificial Intelligence and Statistics. PMLR, 3898--3906."},{"key":"e_1_3_2_2_35_1","volume-title":"Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge","author":"Reyna Matthew A","year":"2019","unstructured":"Matthew A Reyna, Christopher S Josef, Russell Jeter, Supreeth P Shashikumar, M Brandon Westover, Shamim Nemati, Gari D Clifford, and Ashish Sharma. 2020. Early prediction of sepsis from clinical data: the PhysioNet\/Computing in Cardiology Challenge 2019. Critical care medicine, Vol. 48, 2 (2020), 210--217."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095054"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3297173"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3273255"},{"key":"e_1_3_2_2_39_1","volume-title":"Azra Bihorac, and Parisa Rashidi.","author":"Shickel Benjamin","year":"2017","unstructured":"Benjamin Shickel, Patrick James Tighe, Azra Bihorac, and Parisa Rashidi. 2017. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE journal of biomedical and health informatics, Vol. 22, 5 (2017), 1589--1604."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2023.104306"},{"key":"e_1_3_2_2_42_1","first-page":"24804","article-title":"Csdi: Conditional score-based diffusion models for probabilistic time series imputation","volume":"34","author":"Tashiro Yusuke","year":"2021","unstructured":"Yusuke Tashiro, Jiaming Song, Yang Song, and Stefano Ermon. 2021. Csdi: Conditional score-based diffusion models for probabilistic time series imputation. Advances in Neural Information Processing Systems, Vol. 34 (2021), 24804--24816.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_43_1","volume-title":"Clinical prompt learning with frozen language models","author":"Taylor Niall","year":"2023","unstructured":"Niall Taylor, Yi Zhang, Dan W Joyce, Ziming Gao, Andrey Kormilitzin, and Alejo Nevado-Holgado. 2023. Clinical prompt learning with frozen language models. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1080\/00223891.2018.1530680"},{"key":"e_1_3_2_2_45_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_46_1","volume-title":"PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning. In 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP","author":"Wang Zifeng","year":"2022","unstructured":"Zifeng Wang and Jimeng Sun. 2022. PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning. In 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.13063\/2327-9214.1035"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107687"},{"key":"e_1_3_2_2_49_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Wu Haixu","year":"2022","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2022. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_50_1","volume-title":"A functional HTR1A polymorphism, rs6295, predicts short-term response to lurasidone: Confirmation with meta-analysis of other antipsychotic drugs. The pharmacogenomics journal","author":"Yoshikawa Akane","year":"2020","unstructured":"Akane Yoshikawa, Jiang Li, and Herbert Y Meltzer. 2020. A functional HTR1A polymorphism, rs6295, predicts short-term response to lurasidone: Confirmation with meta-analysis of other antipsychotic drugs. The pharmacogenomics journal, Vol. 20, 2 (2020), 260--270."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539388"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_55_1","unstructured":"Yinghao Zhu Wenqing Wang Junyi Gao and Liantao Ma. 2023a. PyEHR: A Predictive Modeling Toolkit for Electronic Health Records. https:\/\/github.com\/yhzhu99\/pyehr."},{"key":"e_1_3_2_2_56_1","unstructured":"Yinghao Zhu Zixiang Wang Long He Shiyun Xie Zixi Chen Jingkun An Liantao Ma and Chengwei Pan. 2023b. Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration to Mitigate EHR Data Sparsity. arxiv: 2309.04160 [cs.LG]"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709166","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:38:32Z","timestamp":1755358712000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":56,"alternative-id":["10.1145\/3690624.3709166","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709166","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}