{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T01:11:59Z","timestamp":1794359519157,"version":"4.9.0"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Previous studies evaluating imputation methods on clinical time series do not jointly account for spatial (e.g., across features) and temporal (across time) structures in missingness. We present a simulation model that induces realistic spatio-temporal missingness in three real-world clinical datasets by sampling from Markov chains. A variety of imputation methods including last observation carried forward (LOCF), linear interpolation, and spatio-temporal autoencoder (STAE) are applied to fill these missingness patterns. Finally, we evaluate the influence of time series imputations on a downstream prediction task. Here we show that deep STAEs outperform simpler baseline methods when missingness patterns lack spatio-temporal structure. In contrast, linear interpolations perform best on spatio-temporal patterns, contributing to sufficient downstream performances. This study demonstrates that simple linear imputations attain robust performances for clinical real-world data with spatio-temporal missingness. We provide an open benchmark to evaluate the effect of missingness on clinical studies and prediction tasks.<\/jats:p>","DOI":"10.1038\/s41467-026-77303-8","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T12:14:18Z","timestamp":1791202458000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmarking imputation methods on real-world clinical time series with simulated spatio-temporal missingness"],"prefix":"10.1038","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0808-3966","authenticated-orcid":false,"given":"Niklas","family":"Giesa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-4904","authenticated-orcid":false,"given":"Rustam","family":"Zhumagambetov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Sekutowicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0147-8992","authenticated-orcid":false,"given":"Sophie K.","family":"Piper","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6554-2316","authenticated-orcid":false,"given":"Victor","family":"Sikora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Balzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-9195","authenticated-orcid":false,"given":"Stefan","family":"Haufe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7993-7901","authenticated-orcid":false,"given":"Sebastian D.","family":"Boie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"77303_CR1","doi-asserted-by":"publisher","first-page":"e893","DOI":"10.1016\/S2589-7500(22)00154-6","volume":"4","author":"CM Sauer","year":"2022","unstructured":"Sauer, C. M. et al. Leveraging electronic health records for data science: common pitfalls and how to avoid them. Lancet Digit. Health 4, e893\u2013e898 (2022).","journal-title":"Lancet Digit. Health"},{"key":"77303_CR2","doi-asserted-by":"publisher","first-page":"113137","DOI":"10.1016\/j.dss.2019.113137","volume":"126","author":"G Jetley","year":"2019","unstructured":"Jetley, G. & Zhang, H. Electronic health records in IS research: quality issues, essential thresholds and remedial actions. Decis. Support Syst. 126, 113137 https:\/\/doi.org\/10.1016\/j.dss.2019.113137 (2019).","journal-title":"Decis. Support Syst."},{"key":"77303_CR3","doi-asserted-by":"publisher","first-page":"940330","DOI":"10.3389\/fdgth.2022.940330","volume":"4","author":"K Honeyford","year":"2022","unstructured":"Honeyford, K. et al. Challenges and recommendations for high quality research using electronic health records. Front. Digit. Health 4, 940330 https:\/\/doi.org\/10.3389\/fdgth.2022.940330 (2022).","journal-title":"Front. Digit. Health"},{"key":"77303_CR4","doi-asserted-by":"publisher","first-page":"607471","DOI":"10.3389\/fgene.2021.607471","volume":"12","author":"S Yang","year":"2021","unstructured":"Yang, S., Zhu, F., Ling, X., Liu, Q. & Zhao, P. Intelligent health care: applications of deep learning in computational medicine. Front. Genet. 12, 607471 https:\/\/doi.org\/10.3389\/fgene.2021.607471 (2021).","journal-title":"Front. Genet."},{"key":"77303_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-59801-x","volume":"10","author":"X Chai","year":"2020","unstructured":"Chai, X. et al. Deep learning for irregularly and regularly missing data reconstruction. Sci. Rep. 10, 3302 https:\/\/doi.org\/10.1038\/s41598-020-59801-x (2020).","journal-title":"Sci. Rep."},{"key":"77303_CR6","doi-asserted-by":"publisher","first-page":"102696","DOI":"10.1016\/j.artmed.2023.102696","volume":"146","author":"X Ruan","year":"2023","unstructured":"Ruan, X., Wang, L., Thongprayoon, C., Cheungpasitporn, W. & Liu, H. GRU-D-Weibull: a novel real-time individualized endpoint prediction. Artif. Intell. Med. 146, 102696 https:\/\/doi.org\/10.1016\/j.artmed.2023.102696 (2023).","journal-title":"Artif. Intell. Med."},{"key":"77303_CR7","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1093\/biomet\/63.3.581","volume":"63","author":"DB Rubin","year":"1976","unstructured":"Rubin, D. B. Inference and missing data. Biometrika 63, 581\u2013592 https:\/\/doi.org\/10.1093\/biomet\/63.3.581 (1976).","journal-title":"Biometrika"},{"key":"77303_CR8","doi-asserted-by":"publisher","first-page":"ooab057","DOI":"10.1093\/jamiaopen\/ooab057","volume":"4","author":"AS Afshar","year":"2021","unstructured":"Afshar, A. S. et al. An exploratory data quality analysis of time series physiologic signals using a large-scale intensive care unit database. JAMIA Open 4, ooab057 https:\/\/doi.org\/10.1093\/jamiaopen\/ooab057 (2021).","journal-title":"JAMIA Open"},{"key":"77303_CR9","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.bspc.2015.12.006","volume":"26","author":"M Khan","year":"2016","unstructured":"Khan, M. et al. Analysing the effects of cold, normal, and warm digits on transmittance pulse oximetry. Biomed. Signal Process. Control 26, 34\u201341 https:\/\/doi.org\/10.1016\/j.bspc.2015.12.006 (2016).","journal-title":"Biomed. Signal Process. Control"},{"key":"77303_CR10","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.jclinepi.2022.08.016","volume":"151","author":"MW Heymans","year":"2022","unstructured":"Heymans, M. W. & Twisk, J. W. Handling missing data in clinical research. J. Clin. Epidemiol. 151, 185\u2013188 https:\/\/doi.org\/10.1016\/j.jclinepi.2022.08.016 (2022).","journal-title":"J. Clin. Epidemiol."},{"key":"77303_CR11","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1002\/mpr.329","volume":"20","author":"MJ Azur","year":"2011","unstructured":"Azur, M. J., Stuart, E. A., Frangakis, C. & Leaf, P. J. Multiple imputation by chained equations: what is it and how does it work? Int. J. Methods Psychiatr. Res. 20, 40\u201349 https:\/\/doi.org\/10.1002\/mpr.329 (2011).","journal-title":"Int. J. Methods Psychiatr. Res."},{"key":"77303_CR12","doi-asserted-by":"publisher","unstructured":"van Buuren, S. & Groothuis-Oudshoorn, K. mice: multivariate imputation by chained equations in R. J. Stat. Softw.45 https:\/\/doi.org\/10.18637\/jss.v045.i03 (2011).","DOI":"10.18637\/jss.v045.i03"},{"key":"77303_CR13","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1093\/jamia\/ocx133","volume":"25","author":"Y Luo","year":"2018","unstructured":"Luo, Y., Szolovits, P., Dighe, A. S. & Baron, J. M. 3D-MICE: integration of cross-sectional and longitudinal imputation for multi-analyte longitudinal clinical data. J. Am. Med. Inform. Assoc. 25, 645\u2013653 https:\/\/doi.org\/10.1093\/jamia\/ocx133 (2018).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"77303_CR14","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/s10994-020-05923-2","volume":"110","author":"D Bertsimas","year":"2021","unstructured":"Bertsimas, D., Orfanoudaki, A. & Pawlowski, C. Imputation of clinical covariates in time series. Mach. Learn. 110, 185\u2013248 https:\/\/doi.org\/10.1007\/s10994-020-05923-2 (2021).","journal-title":"Mach. Learn."},{"key":"77303_CR15","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1007\/s10618-020-00706-8","volume":"34","author":"Q Ma","year":"2020","unstructured":"Ma, Q., Lee, W.-C., Fu, T.-Y., Gu, Y. & Yu, G. MIDIA: exploring denoising autoencoders for missing data imputation. Data Min. Knowl. Discov. 34, 1859\u20131897 https:\/\/doi.org\/10.1007\/s10618-020-00706-8 (2020).","journal-title":"Data Min. Knowl. Discov."},{"key":"77303_CR16","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1038\/s43856-024-00681-x","volume":"4","author":"N Giesa","year":"2024","unstructured":"Giesa, N. et al. Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium. Commun. Med. 4, 251 https:\/\/doi.org\/10.1038\/s43856-024-00681-x (2024).","journal-title":"Commun. Med."},{"key":"77303_CR17","doi-asserted-by":"publisher","first-page":"bbab489","DOI":"10.1093\/bib\/bbab489","volume":"23","author":"Y Luo","year":"2022","unstructured":"Luo, Y. Evaluating the state of the art in missing data imputation for clinical data. Brief. Bioinform. 23, bbab489 https:\/\/doi.org\/10.1093\/bib\/bbab489 (2022).","journal-title":"Brief. Bioinform."},{"key":"77303_CR18","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1177\/1740774515602688","volume":"13","author":"JM Lachin","year":"2016","unstructured":"Lachin, J. M. Fallacies of last observation carried forward analyses. Clin. Trials 13, 161\u2013168 https:\/\/doi.org\/10.1177\/1740774515602688 (2016).","journal-title":"Clin. Trials"},{"key":"77303_CR19","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-022-05911-w","volume":"15","author":"N Cesare","year":"2022","unstructured":"Cesare, N. & Were, L. P. O. A multi-step approach to managing missing data in time and patient variant electronic health records. BMC Res. Notes 15, 64 https:\/\/doi.org\/10.1186\/s13104-022-05911-w (2022).","journal-title":"BMC Res. Notes"},{"key":"77303_CR20","doi-asserted-by":"publisher","unstructured":"Zamanzadeh, D. J. et al. Autopopulus: a novel framework for autoencoder imputation on large clinical datasets. In Proc. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)2303\u20132309 https:\/\/doi.org\/10.1109\/EMBC46164.2021.9630135 (2021).","DOI":"10.1109\/EMBC46164.2021.9630135"},{"key":"77303_CR21","unstructured":"Luo, Y., Cai, X., Zhang, Y. & Xu, J. Multivariate time series imputation with generative adversarial networks. Adv.Neural Inf. Process. Syst. 31, 130749\u2013130757 (2018)."},{"key":"77303_CR22","doi-asserted-by":"publisher","unstructured":"Jia, Y., Zhou, C. & Motani, M. Spatio-temporal autoencoder for feature learning in patient data with missing observations. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)886\u2013890 https:\/\/doi.org\/10.1109\/BIBM.2017.8217773 (2017).","DOI":"10.1109\/BIBM.2017.8217773"},{"key":"77303_CR23","doi-asserted-by":"publisher","first-page":"21562","DOI":"10.1109\/ACCESS.2023.3251919","volume":"11","author":"K Psychogyios","year":"2023","unstructured":"Psychogyios, K., Ilias, L., Ntanos, C. & Askounis, D. Missing value imputation methods for electronic health records. IEEE Access 11, 21562\u201321574 https:\/\/doi.org\/10.1109\/ACCESS.2023.3251919 (2023).","journal-title":"IEEE Access"},{"key":"77303_CR24","doi-asserted-by":"publisher","first-page":"1028978","DOI":"10.3389\/frai.2022.1028978","volume":"5","author":"M Song","year":"2022","unstructured":"Song, M. et al. An autoencoder-based deep learning method for genotype imputation. Front. Artif. Intell. 5, 1028978 https:\/\/doi.org\/10.3389\/frai.2022.1028978 (2022).","journal-title":"Front. Artif. Intell."},{"key":"77303_CR25","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.neucom.2017.03.097","volume":"276","author":"F Bashir","year":"2018","unstructured":"Bashir, F. & Wei, H.-L. Handling missing data in multivariate time series using a vector autoregressive model-imputation (VAR-IM) algorithm. Neurocomputing 276, 23\u201330 https:\/\/doi.org\/10.1016\/j.neucom.2017.03.097 (2018).","journal-title":"Neurocomputing"},{"key":"77303_CR26","doi-asserted-by":"publisher","unstructured":"Qian, L. et al. Beyond random missingness: clinically rethinking for healthcare time series imputation. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2405.17508 (2025).","DOI":"10.48550\/arXiv.2405.17508"},{"key":"77303_CR27","doi-asserted-by":"publisher","first-page":"103576","DOI":"10.1016\/j.jbi.2020.103576","volume":"111","author":"D Xu","year":"2020","unstructured":"Xu, D., Hu, P. J.-H., Huang, T.-S., Fang, X. & Hsu, C.-C. A deep learning-based, unsupervised method to impute missing values in electronic health records for improved patient management. J. Biomed. Inform. 111, 103576 https:\/\/doi.org\/10.1016\/j.jbi.2020.103576 (2020).","journal-title":"J. Biomed. Inform."},{"key":"77303_CR28","doi-asserted-by":"publisher","first-page":"122148","DOI":"10.1016\/j.eswa.2023.122148","volume":"238","author":"N Bignoumba","year":"2024","unstructured":"Bignoumba, N., Mellouli, N. & Yahia, S. B. A new efficient ALignment-driven Neural Network for Mortality Prediction from irregular multivariate time series data. Expert Syst. Appl. 238, 122148 https:\/\/doi.org\/10.1016\/j.eswa.2023.122148 (2024).","journal-title":"Expert Syst. Appl."},{"key":"77303_CR29","doi-asserted-by":"publisher","first-page":"110919","DOI":"10.1016\/j.knosys.2023.110919","volume":"279","author":"L Huang","year":"2023","unstructured":"Huang, L., Huang, J., Li, H. & Cui, J. Robust spatial temporal imputation based on spatio-temporal generative adversarial nets. Knowl.-Based Syst. 279, 110919 https:\/\/doi.org\/10.1016\/j.knosys.2023.110919 (2023).","journal-title":"Knowl.-Based Syst."},{"key":"77303_CR30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/s10462-024-11039-z","volume":"58","author":"X Lai","year":"2024","unstructured":"Lai, X., Yao, Y., Mu, J., Lu, W. & Zhang, L. Ratai: recurrent autoencoder with imputation units and temporal attention for multivariate time series imputation. Artif. Intell. Rev. 58, 37 https:\/\/doi.org\/10.1007\/s10462-024-11039-z (2024).","journal-title":"Artif. Intell. Rev."},{"key":"77303_CR31","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.neucom.2020.05.033","volume":"411","author":"D Li","year":"2020","unstructured":"Li, D., Li, L., Li, X., Ke, Z. & Hu, Q. Smoothed LSTM-AE: a spatio-temporal deep model for multiple time-series missing imputation. Neurocomputing 411, 351\u2013363 https:\/\/doi.org\/10.1016\/j.neucom.2020.05.033 (2020).","journal-title":"Neurocomputing"},{"key":"77303_CR32","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.3390\/e24121798","volume":"24","author":"Y Li","year":"2022","unstructured":"Li, Y., Du, M. & He, S. Attention-based sequence-to-sequence model for time series imputation. Entropy 24, 1798 https:\/\/doi.org\/10.3390\/e24121798 (2022).","journal-title":"Entropy"},{"key":"77303_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3588730","volume":"1","author":"Y Fan","year":"2023","unstructured":"Fan, Y. et al. Spatio-temporal denoising graph autoencoders with data augmentation for photovoltaic data imputation. Proc. ACM Manag. Data 1, 1\u201319 https:\/\/doi.org\/10.1145\/3588730 (2023).","journal-title":"Proc. ACM Manag. Data"},{"key":"77303_CR34","unstructured":"Cao, W. et al. Brits: Bidirectional recurrent imputation for time series. Adv. Neural Inf. Process. Syst. 31, (2018)."},{"key":"77303_CR35","doi-asserted-by":"publisher","first-page":"119619","DOI":"10.1016\/j.eswa.2023.119619","volume":"219","author":"W Du","year":"2023","unstructured":"Du, W., C\u00f4t\u00e9, D. & Liu, Y. SAITS: self-attention-based imputation for time series. Expert Syst. Appl. 219, 119619 https:\/\/doi.org\/10.1016\/j.eswa.2023.119619 (2023).","journal-title":"Expert Syst. Appl."},{"key":"77303_CR36","unstructured":"Chen, R. T. Q., Rubanova, Y., Bettencourt, J. & Duvenaud, D. K. Neural ordinary differential equations. Adv. Neural Inf. Process. Syst. 31, (2018)."},{"key":"77303_CR37","doi-asserted-by":"publisher","unstructured":"Wi, H., Shin, Y. & Park, N. Continuous-time autoencoders for regular and irregular time series imputation. In Proc. 17th ACM International Conference on Web Search and Data Mining826\u2013835 https:\/\/doi.org\/10.1145\/3616855.3635831 (2024).","DOI":"10.1145\/3616855.3635831"},{"key":"77303_CR38","doi-asserted-by":"publisher","first-page":"693674","DOI":"10.3389\/fdata.2021.693674","volume":"4","author":"S J\u00e4ger","year":"2021","unstructured":"J\u00e4ger, S., Allhorn, A. & Bie\u00dfmann, F. A benchmark for data imputation methods. Front. Big Data 4, 693674 https:\/\/doi.org\/10.3389\/fdata.2021.693674 (2021).","journal-title":"Front. Big Data"},{"key":"77303_CR39","doi-asserted-by":"publisher","first-page":"e15510","DOI":"10.2196\/15510","volume":"8","author":"X Song","year":"2020","unstructured":"Song, X. et al. Longitudinal risk prediction of chronic kidney disease in diabetic patients using a temporal-enhanced gradient boosting machine: retrospective cohort study. JMIR Med. Inform. 8, e15510 (2020).","journal-title":"JMIR Med. Inform."},{"key":"77303_CR40","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24271-9","volume":"8","author":"Z Che","year":"2018","unstructured":"Che, Z., Purushotham, S., Cho, K., Sontag, D. & Liu, Y. Recurrent neural networks for multivariate time series with missing values. Sci. Rep. 8, 6085 https:\/\/doi.org\/10.1038\/s41598-018-24271-9 (2018).","journal-title":"Sci. Rep."},{"key":"77303_CR41","doi-asserted-by":"publisher","unstructured":"Faltys, M. et al. HiRID, a high time-resolution ICU dataset. Physionethttps:\/\/doi.org\/10.13026\/NKWC-JS72 (2021).","DOI":"10.13026\/NKWC-JS72"},{"key":"77303_CR42","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-030-01768-2_8","volume":"11191","author":"AF Costa","year":"2018","unstructured":"Costa, A. F., Santos, M. S., Soares, J. P. & Abreu, P. H. Missing data imputation via denoising autoencoders: the untold story. Adv. Intell. Data Anal. XVII 11191, 87\u201398 https:\/\/doi.org\/10.1007\/978-3-030-01768-2_8 (2018).","journal-title":"Adv. Intell. Data Anal. XVII"},{"key":"77303_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00518-0","volume":"4","author":"J Li","year":"2021","unstructured":"Li, J. et al. Imputation of missing values for electronic health record laboratory data. npj Digit. Med. 4, 147 https:\/\/doi.org\/10.1038\/s41746-021-00518-0 (2021).","journal-title":"npj Digit. Med."},{"key":"77303_CR44","doi-asserted-by":"publisher","first-page":"104306","DOI":"10.1016\/j.jbi.2023.104306","volume":"139","author":"AL Tan","year":"2023","unstructured":"Tan, A. L. et al. Informative missingness: what can we learn from patterns in missing laboratory data in the electronic health record? J. Biomed. Inform. 139, 104306 https:\/\/doi.org\/10.1016\/j.jbi.2023.104306 (2023).","journal-title":"J. Biomed. Inform."},{"key":"77303_CR45","doi-asserted-by":"publisher","unstructured":"Restrepo, D. et al. Representation learning of lab values via masked AutoEncoder. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2501.02648 (2025).","DOI":"10.48550\/arXiv.2501.02648"},{"key":"77303_CR46","doi-asserted-by":"publisher","first-page":"105277","DOI":"10.1016\/j.istruc.2023.105277","volume":"57","author":"S Gao","year":"2023","unstructured":"Gao, S. et al. Enhanced data imputation framework for bridge health monitoring using Wasserstein generative adversarial networks with gradient penalty. Structures 57, 105277 https:\/\/doi.org\/10.1016\/j.istruc.2023.105277 (2023).","journal-title":"Structures"},{"key":"77303_CR47","doi-asserted-by":"publisher","first-page":"104440","DOI":"10.1016\/j.jbi.2023.104440","volume":"144","author":"M Kazijevs","year":"2023","unstructured":"Kazijevs, M. & Samad, M. D. Deep imputation of missing values in time series health data: a review with benchmarking. J. Biomed. Inform. 144, 104440 https:\/\/doi.org\/10.1016\/j.jbi.2023.104440 (2023).","journal-title":"J. Biomed. Inform."},{"key":"77303_CR48","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-01968-8","volume":"23","author":"M Jahangiri","year":"2023","unstructured":"Jahangiri, M. et al. A wide range of missing imputation approaches in longitudinal data: a simulation study and real data analysis. BMC Med. Res. Methodol. 23, 161 https:\/\/doi.org\/10.1186\/s12874-023-01968-8 (2023).","journal-title":"BMC Med. Res. Methodol."},{"key":"77303_CR49","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1177\/0962280212469358","volume":"25","author":"S Luo","year":"2016","unstructured":"Luo, S., Lawson, A. B., He, B., Elm, J. J. & Tilley, B. C. Bayesian multiple imputation for missing multivariate longitudinal data from a Parkinson\u2019s disease clinical trial. Stat. Methods Med. Res. 25, 821\u2013837 https:\/\/doi.org\/10.1177\/0962280212469358 (2016).","journal-title":"Stat. Methods Med. Res."},{"key":"77303_CR50","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1002\/sim.8009","volume":"38","author":"D Mavridis","year":"2019","unstructured":"Mavridis, D. et al. Allowing for uncertainty due to missing and LOCF imputed outcomes in meta-analysis. Stat. Med. 38, 720\u2013737 https:\/\/doi.org\/10.1002\/sim.8009 (2019).","journal-title":"Stat. Med."},{"key":"77303_CR51","doi-asserted-by":"publisher","unstructured":"van der Vaart, A. W. Asymptotic statistics. In Cambridge Series on Statistical and Probabilistic Mathematics https:\/\/doi.org\/10.1017\/CBO9780511802256 (2007).","DOI":"10.1017\/CBO9780511802256"},{"key":"77303_CR52","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.jspi.2008.04.017","volume":"139","author":"C Saha","year":"2009","unstructured":"Saha, C. & Jones, M. P. Bias in the last observation carried forward method under informative dropout. J. Stat. Plan. Inference 139, 246\u2013255 https:\/\/doi.org\/10.1016\/j.jspi.2008.04.017 (2009).","journal-title":"J. Stat. Plan. Inference"},{"key":"77303_CR53","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0103-9","volume":"6","author":"H Harutyunyan","year":"2019","unstructured":"Harutyunyan, H., Khachatrian, H., Kale, D. C., Ver Steeg, G. & Galstyan, A. Multitask learning and benchmarking with clinical time series data. Sci. Data 6, 96 https:\/\/doi.org\/10.1038\/s41597-019-0103-9 (2019).","journal-title":"Sci. Data"},{"key":"77303_CR54","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86674-9","volume":"15","author":"F Yao","year":"2025","unstructured":"Yao, F., Luo, J., Zhou, Q., Wang, L. & He, Z. Development and validation of a machine learning-based prediction model for hepatorenal syndrome in liver cirrhosis patients using MIMIC-IV and eICU databases. Sci. Rep. 15, 2743 https:\/\/doi.org\/10.1038\/s41598-025-86674-9 (2025).","journal-title":"Sci. Rep."},{"key":"77303_CR55","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1002\/bimj.200410135","volume":"47","author":"R Fluss","year":"2005","unstructured":"Fluss, R., Faraggi, D. & Reiser, B. Estimation of the Youden index and its associated cutoff point. Biom. J. 47, 458\u2013472 https:\/\/doi.org\/10.1002\/bimj.200410135 (2005).","journal-title":"Biom. J."},{"key":"77303_CR56","doi-asserted-by":"publisher","first-page":"102762","DOI":"10.1016\/j.jag.2022.102762","volume":"108","author":"B Chen","year":"2022","unstructured":"Chen, B. et al. A joint learning Im-BiLSTM model for incomplete time-series Sentinel-2A data imputation and crop classification. Int. J. Appl. Earth Obs. Geoinf. 108, 102762 https:\/\/doi.org\/10.1016\/j.jag.2022.102762 (2022).","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"77303_CR57","doi-asserted-by":"publisher","unstructured":"Giesa, N. Public spatio-temporal benchmark. Zenodo https:\/\/doi.org\/10.5281\/ZENODO.21356282 (2026).","DOI":"10.5281\/ZENODO.21356282"},{"key":"77303_CR58","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson, A. E. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 https:\/\/doi.org\/10.1038\/sdata.2016.35 (2016).","journal-title":"Sci. Data"},{"key":"77303_CR59","doi-asserted-by":"publisher","unstructured":"Wang, S. et al. MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III. In Proc. ACM Conference on Health, Inference, and Learning 222\u2013235 https:\/\/doi.org\/10.1145\/3368555.3384469 (ACM, 2020).","DOI":"10.1145\/3368555.3384469"},{"key":"77303_CR60","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1038\/s41591-020-0789-4","volume":"26","author":"SL Hyland","year":"2020","unstructured":"Hyland, S. L. et al. Early prediction of circulatory failure in the intensive care unit using machine learning. Nat. Med. 26, 364\u2013373 https:\/\/doi.org\/10.1038\/s41591-020-0789-4 (2020).","journal-title":"Nat. Med."},{"key":"77303_CR61","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s00586-007-0415-x","volume":"16","author":"J Dvorak","year":"2007","unstructured":"Dvorak, J., Sutter, M., Eggspuehler, A., Szpalski, M. & Aebi, M. Multimodal intraoperative monitoring: towards a routine use in surgical treatment of severe spinal disorders. Eur. Spine J. 16, 113\u2013114 https:\/\/doi.org\/10.1007\/s00586-007-0415-x (2007).","journal-title":"Eur. Spine J."},{"key":"77303_CR62","doi-asserted-by":"publisher","first-page":"e0000414","DOI":"10.1371\/journal.pdig.0000414","volume":"3","author":"N Giesa","year":"2024","unstructured":"Giesa, N. et al. Predicting postoperative delirium assessed by the Nursing Screening Delirium Scale in the recovery room for non-cardiac surgeries without craniotomy: a retrospective study using a machine learning approach. PLoS Digit. Health 3, e0000414 https:\/\/doi.org\/10.1371\/journal.pdig.0000414 (2024).","journal-title":"PLoS Digit. Health"},{"key":"77303_CR63","doi-asserted-by":"publisher","first-page":"105611","DOI":"10.1016\/j.ijmedinf.2024.105611","volume":"192","author":"SD Boie","year":"2024","unstructured":"Daniel Boie, S. et al. A scalable approach for critical care data extraction and analysis in an academic medical center. Int. J. Med. Inform. 192, 105611 https:\/\/doi.org\/10.1016\/j.ijmedinf.2024.105611 (2024).","journal-title":"Int. J. Med. Inform."},{"key":"77303_CR64","doi-asserted-by":"publisher","first-page":"e0000598","DOI":"10.1371\/journal.pdig.0000598","volume":"3","author":"N Hinrichs","year":"2024","unstructured":"Hinrichs, N. et al. Short-term vital parameter forecasting in the intensive care unit: a benchmark study leveraging data from patients after cardiothoracic surgery. PLoS Digit. Health 3, e0000598 https:\/\/doi.org\/10.1371\/journal.pdig.0000598 (2024).","journal-title":"PLoS Digit. Health"},{"key":"77303_CR65","first-page":"333","volume":"17","author":"M Frydenberg","year":"1990","unstructured":"Frydenberg, M. The chain graph Markov property. Scand. J. Stat. 17, 333\u2013353 (1990).","journal-title":"Scand. J. Stat."},{"key":"77303_CR66","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","volume":"3","author":"L Rabiner","year":"1986","unstructured":"Rabiner, L. & Juang, B. An introduction to hidden Markov models. IEEE ASSP Mag. 3, 4\u201316 https:\/\/doi.org\/10.1109\/MASSP.1986.1165342 (1986).","journal-title":"IEEE ASSP Mag."},{"key":"77303_CR67","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1006\/jmps.1999.1279","volume":"44","author":"MW Browne","year":"2000","unstructured":"Browne, M. W. Cross-validation methods. J. Math. Psychol. 44, 108\u2013132 https:\/\/doi.org\/10.1006\/jmps.1999.1279 (2000).","journal-title":"J. Math. Psychol."},{"key":"77303_CR68","first-page":"1","volume":"17","author":"MA Wahab","year":"2017","unstructured":"Wahab, M. A. Interpolation and extrapolation. Proc. Top. Syst. Eng. Winter Term. 17, 1\u20136 (2017).","journal-title":"Proc. Top. Syst. Eng. Winter Term."},{"key":"77303_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-44584-3_1","volume":"12080","author":"AA Safi","year":"2020","unstructured":"Safi, A. A., Beyer, C., Unnikrishnan, V. & Spiliopoulou, M. Multivariate time series as images: imputation using convolutional denoising autoencoder. Adv. Intell. Data Anal. XVIII 12080, 1\u201313 https:\/\/doi.org\/10.1007\/978-3-030-44584-3_1 (2020).","journal-title":"Adv. Intell. Data Anal. XVIII"},{"key":"77303_CR70","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2022.06.111","volume":"503","author":"SR Dubey","year":"2022","unstructured":"Dubey, S. R., Singh, S. K. & Chaudhuri, B. B. Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing 503, 92\u2013108 https:\/\/doi.org\/10.1016\/j.neucom.2022.06.111 (2022).","journal-title":"Neurocomputing"},{"key":"77303_CR71","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3390\/informatics8040077","volume":"8","author":"A Alqahtani","year":"2021","unstructured":"Alqahtani, A., Xie, X. & Jones, M. W. Literature review of deep network compression. Informatics 8, 77 https:\/\/doi.org\/10.3390\/informatics8040077 (2021).","journal-title":"Informatics"},{"key":"77303_CR72","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1162\/neco_a_01729","volume":"37","author":"L Sun","year":"2025","unstructured":"Sun, L., Wu, C., Ching, W.-K. & Akutsu, T. On the compressive power of autoencoders with linear and ReLU activation functions. Neural Comput. 37, 235\u2013259 https:\/\/doi.org\/10.1162\/neco_a_01729 (2025).","journal-title":"Neural Comput."},{"key":"77303_CR73","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.3390\/en15031061","volume":"15","author":"S Ghimire","year":"2022","unstructured":"Ghimire, S. et al. Stacked LSTM sequence-to-sequence autoencoder with feature selection for daily solar radiation prediction: a review and new modeling results. Energies 15, 1061 https:\/\/doi.org\/10.3390\/en15031061 (2022).","journal-title":"Energies"},{"key":"77303_CR74","doi-asserted-by":"publisher","first-page":"3319","DOI":"10.3390\/math11153319","volume":"11","author":"MH Qais","year":"2023","unstructured":"Qais, M. H., Kewat, S., Loo, K. H., Lai, C.-M. & Leung, A. LSTM-based stacked autoencoders for early anomaly detection in induction heating systems. Mathematics 11, 3319 https:\/\/doi.org\/10.3390\/math11153319 (2023).","journal-title":"Mathematics"},{"key":"77303_CR75","first-page":"439","volume":"77","author":"JR Hermans","year":"2017","unstructured":"Hermans, J. R., Spanakis, G. & M\u00f6ckel, R. Accumulated Gradient Normalization. Proc. Ninth Asian Conf. Mach. Learn. 77, 439\u2013454 (2017).","journal-title":"Proc. Ninth Asian Conf. Mach. Learn."},{"key":"77303_CR76","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1287\/moor.2021.1176","volume":"48","author":"VA Nguyen","year":"2023","unstructured":"Nguyen, V. A., Shafieezadeh-Abadeh, S., Kuhn, D. & Mohajerin Esfahani, P. Bridging Bayesian and minimax mean square error estimation via Wasserstein distributionally robust optimization. Math. Oper. Res. 48, 1\u201337 https:\/\/doi.org\/10.1287\/moor.2021.1176 (2023).","journal-title":"Math. Oper. Res."},{"key":"77303_CR77","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1146\/annurev-statistics-030718-104938","volume":"6","author":"VM Panaretos","year":"2019","unstructured":"Panaretos, V. M. & Zemel, Y. Statistical aspects of Wasserstein distances. Annu. Rev. Stat. Appl. 6, 405\u2013431 https:\/\/doi.org\/10.1146\/annurev-statistics-030718-104938 (2019).","journal-title":"Annu. Rev. Stat. Appl."},{"key":"77303_CR78","unstructured":"Patrini, G. et al. Sinkhorn AutoEncoders. In Uncertainty in Artificial Intelligence, pp. 733\u2013743 (PMLR, 2020)."},{"key":"77303_CR79","doi-asserted-by":"publisher","unstructured":"Shekar, B. H. & Dagnew, G. Grid search-based hyperparameter tuning and classification of microarray cancer data. In 2019 Second International Conference on Advanced Computational and Communication Paradigms (ICACCP)1\u20138 https:\/\/doi.org\/10.1109\/ICACCP.2019.8882943 (2019).","DOI":"10.1109\/ICACCP.2019.8882943"},{"key":"77303_CR80","first-page":"6765","volume":"18","author":"L Li","year":"2017","unstructured":"Li, L., Jamieson, K., DeSalvo, G., Rostamizadeh, A. & Talwalkar, A. Hyperband: a novel bandit-based approach to hyperparameter optimization. J. Mach. Learn. Res. 18, 6765\u20136816 (2017).","journal-title":"J. Mach. Learn. Res."},{"key":"77303_CR81","doi-asserted-by":"publisher","first-page":"5481","DOI":"10.5194\/gmd-15-5481-2022","volume":"15","author":"TO Hodson","year":"2022","unstructured":"Hodson, T. O. Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geosci. Model Dev. 15, 5481\u20135487 https:\/\/doi.org\/10.5194\/gmd-15-5481-2022 (2022).","journal-title":"Geosci. Model Dev."},{"key":"77303_CR82","doi-asserted-by":"crossref","unstructured":"Ramdas, A., Garcia, N. & Cuturi, M. On Wasserstein two sample testing and related families of nonparametric tests. Entropy 19, 47 (2017).","DOI":"10.3390\/e19020047"},{"key":"77303_CR83","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1002\/cphc.201100897","volume":"13","author":"S Felekyan","year":"2012","unstructured":"Felekyan, S., Kalinin, S., Sanabria, H., Valeri, A. & Seidel, C. A. M. Filtered FCS: species auto- and cross-correlation functions highlight binding and dynamics in biomolecules. ChemPhysChem 13, 1036\u20131053 https:\/\/doi.org\/10.1002\/cphc.201100897 (2012).","journal-title":"ChemPhysChem"},{"key":"77303_CR84","first-page":"480","volume":"287","author":"AA Toye","year":"2025","unstructured":"Toye, A. A., Celik, A. & Kleinberg, S. Benchmarking missing data imputation methods for time series using real-world test cases. Proc. Mach. Learn. Res. 287, 480\u2013501 (2025).","journal-title":"Proc. Mach. Learn. Res."},{"key":"77303_CR85","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1177\/019394599001200210","volume":"12","author":"D Taylor","year":"1990","unstructured":"Taylor, D. Time-series analysis: use of autocorrelation as an analytic strategy for describing pattern and change. West. J. Nurs. Res. 12, 254\u2013261 https:\/\/doi.org\/10.1177\/019394599001200210 (1990).","journal-title":"West. J. Nurs. Res."},{"key":"77303_CR86","doi-asserted-by":"publisher","first-page":"RP89947","DOI":"10.7554\/eLife.89947.3","volume":"12","author":"S Kazdaghli","year":"2024","unstructured":"Kazdaghli, S., Kerenidis, I., Kieckbusch, J. & Teare, P. Improved clinical data imputation via classical and quantum determinantal point processes. eLife 12, RP89947 https:\/\/doi.org\/10.7554\/eLife.89947.3 (2024).","journal-title":"eLife"},{"key":"77303_CR87","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145\u20131159 (1997).","journal-title":"Pattern Recognit."},{"key":"77303_CR88","doi-asserted-by":"publisher","unstructured":"Voigt, P. & von dem Bussche, A. Regulation (eu) 2016\/67. In The EU General Data Protection Regulation (GDPR): A Practical Guidehttps:\/\/doi.org\/10.1007\/978-3-031-62328-8 (2024).","DOI":"10.1007\/978-3-031-62328-8"}],"updated-by":[{"DOI":"10.1038\/s41467-026-79464-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T00:00:00Z","timestamp":1793923200000}}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77303-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77303-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77303-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T06:38:34Z","timestamp":1794033514000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-026-77303-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":88,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["77303"],"URL":"https:\/\/doi.org\/10.1038\/s41467-026-77303-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7263571\/v1","asserted-by":"object"}]},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"assertion":[{"value":"31 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 November 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41467-026-79464-y","URL":"https:\/\/doi.org\/10.1038\/s41467-026-79464-y","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"S.P. declares the following competing interests: Participation on different Data Safety Monitoring Boards, completely unrelated to this paper and co-authors. Payment for lectures on statistical planning of animal trials by Apprendis UG (\n                      \n                      ). All other authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"10491"}}