{"url":"/dataset/physionet-challenge-2012","name":"PhysioNet Challenge 2012","full_name":"PhysioNet Challenge 2012","description_markdown":"The **PhysioNet Challenge 2012** dataset is publicly available and contains the de-identified records of 8000 patients in Intensive Care Units (ICU). Each record consists of roughly 48 hours of multivariate time series data with up to 37 features recorded at various times from the patients during their stay such as respiratory rate, glucose etc.\n\nSource: [Multi-resolution Networks For Flexible Irregular Time Series Modeling (Multi-FIT)](https://arxiv.org/abs/1905.00125)\nImage Source: [https://physionet.org/content/challenge-2016/1.0.0/](https://physionet.org/content/challenge-2016/1.0.0/)","description_withheld":null,"homepage":"https://polyp.grand-challenge.org/CVCClinicDB/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Time Series Analysis","url":"/task/time-series","datasets_with_task":"/datasets/task/time-series"},{"name":"Time Series Classification","url":"/task/time-series-classification","datasets_with_task":"/datasets/task/time-series-classification"},{"name":"Multivariate Time Series Forecasting","url":"/task/multivariate-time-series-forecasting","datasets_with_task":"/datasets/task/multivariate-time-series-forecasting"},{"name":"Imputation","url":"/task/imputation","datasets_with_task":"/datasets/task/imputation"},{"name":"Multivariate Time Series Imputation","url":"/task/multivariate-time-series-imputation","datasets_with_task":"/datasets/task/multivariate-time-series-imputation"}],"languages":[],"variants":["PhysioNet Challenge 2012"],"data_loaders":[{"repo":"https://github.com/WenjieDu/TSDB","url":"https://github.com/WenjieDu/TSDB","frameworks":[]}],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/time-series-classification-on-physionet","task":"Time Series Classification","dataset_variant":"PhysioNet Challenge 2012","rows":28,"metrics":["AUC","AUC Stdev","AUPRC","AUROC"],"first_row_in_archive_order":{"model":"GRU-D","paper":"/paper/set-functions-for-time-series-1","metrics":{"AUC":"86.99%","AUC Stdev":"0.22%"},"code_links":[{"title":"WenjieDu/PyPOTS","url":"https://github.com/WenjieDu/PyPOTS"},{"title":"BorgwardtLab/Set_Functions_for_Time_Series","url":"https://github.com/BorgwardtLab/Set_Functions_for_Time_Series"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multivariate-time-series-imputation-on-1","task":"Multivariate Time Series Imputation","dataset_variant":"PhysioNet Challenge 2012","rows":9,"metrics":["MAE (10% of data as GT)","mse (10^-3)"],"first_row_in_archive_order":{"model":"SAITS","paper":"/paper/saits-self-attention-based-imputation-for","metrics":{"MAE (10% of data as GT)":"0.186"},"code_links":[{"title":"WenjieDu/PyPOTS","url":"https://github.com/WenjieDu/PyPOTS"},{"title":"WenjieDu/SAITS","url":"https://github.com/WenjieDu/SAITS"},{"title":"gorgen2020/LSSDM_imputation","url":"https://github.com/gorgen2020/LSSDM_imputation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/time-series-on-physionet-challenge-2012","task":"Time Series Analysis","dataset_variant":"PhysioNet Challenge 2012","rows":7,"metrics":["F1"],"first_row_in_archive_order":{"model":"naive classifier","paper":"/paper/as-easy-as-apc-leveraging-self-supervised","metrics":{"F1":"87.47"},"code_links":[{"title":"fiorella-wever/APC","url":"https://github.com/fiorella-wever/APC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multivariate-time-series-forecasting-on-2","task":"Multivariate Time Series Forecasting","dataset_variant":"PhysioNet Challenge 2012","rows":4,"metrics":["mse (10^-3)","MSE stdev"],"first_row_in_archive_order":{"model":"Latent ODE + Poisson","paper":"/paper/latent-odes-for-irregularly-sampled-time","metrics":{"MSE stdev":"0.05","mse (10^-3)":"2.208"},"code_links":[{"title":"YuliaRubanova/latent_ode","url":"https://github.com/YuliaRubanova/latent_ode"},{"title":"patrick-kidger/torchcde","url":"https://github.com/patrick-kidger/torchcde"},{"title":"jacobjinkelly/easy-neural-ode","url":"https://github.com/jacobjinkelly/easy-neural-ode"},{"title":"BorealisAI/continuous-time-flow-process","url":"https://github.com/BorealisAI/continuous-time-flow-process"},{"title":"HerreraKrachTeichmann/ControlledODERNN","url":"https://github.com/HerreraKrachTeichmann/ControlledODERNN"},{"title":"HerreraKrachTeichmann/NJODE","url":"https://github.com/HerreraKrachTeichmann/NJODE"},{"title":"ashysheya/ODE-RNN","url":"https://github.com/ashysheya/ODE-RNN"},{"title":"MeetGandhi/Reconstruction-of-Trajectory-recorded-with-Missing-Markers","url":"https://github.com/MeetGandhi/Reconstruction-of-Trajectory-recorded-with-Missing-Markers"},{"title":"westny/neural-stability","url":"https://github.com/westny/neural-stability"},{"title":"Ldhlwh/Latent-ODE","url":"https://github.com/Ldhlwh/Latent-ODE"},{"title":"gkrudah/ODEnet","url":"https://github.com/gkrudah/ODEnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/imputation-on-physionet-challenge-2012","task":"Imputation","dataset_variant":"PhysioNet Challenge 2012","rows":1,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"GP-VAE (B-NLST)","paper":"/paper/seq2tens-an-efficient-representation-of","metrics":{"AUROC":"0.743"},"code_links":[{"title":"tgcsaba/seq2tens","url":"https://github.com/tgcsaba/seq2tens"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/saits-self-attention-based-imputation-for","title":"SAITS: Self-Attention-based Imputation for Time Series","date":"2022-02-17","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":3,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-supervised-transformer-for-multivariate","title":"Self-Supervised Transformer for Sparse and Irregularly Sampled Multivariate Clinical Time-Series","date":"2021-07-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/as-easy-as-apc-leveraging-self-supervised","title":"As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning","date":"2021-06-29","rows_on_this_dataset":20,"code_links":1,"syntology":null},{"paper":"/paper/multi-time-attention-networks-for-irregularly-1","title":"Multi-Time Attention Networks for Irregularly Sampled Time Series","date":"2021-01-25","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/seq2tens-an-efficient-representation-of","title":"Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projections","date":"2020-06-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/set-functions-for-time-series-1","title":"Set Functions for Time Series","date":"2019-09-26","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/interpolation-prediction-networks-for-1","title":"Interpolation-Prediction Networks for Irregularly Sampled Time Series","date":"2019-09-13","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/latent-odes-for-irregularly-sampled-time","title":"Latent ODEs for Irregularly-Sampled Time Series","date":"2019-07-08","rows_on_this_dataset":7,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":4,"samples_unverified":4,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/neural-ordinary-differential-equations","title":"Neural Ordinary Differential Equations","date":"2018-06-19","rows_on_this_dataset":4,"code_links":56,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":89,"samples_unverified":35,"pointer_only_for_licence":41,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/brits-bidirectional-recurrent-imputation-for","title":"BRITS: Bidirectional Recurrent Imputation for Time Series","date":"2018-05-27","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/estimating-missing-data-in-temporal-data","title":"Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks","date":"2017-11-23","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/imputets-time-series-missing-value-imputation","title":"imputeTS: Time Series Missing Value Imputation in R","date":"2017-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/recurrent-neural-networks-for-multivariate","title":"Recurrent Neural Networks for Multivariate Time Series with Missing Values","date":"2016-06-06","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multiple-imputation-using-chained-equations","title":"Multiple imputation using chained equations: issues and guidance for practice","date":"2010-11-30","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":9,"samples_harvested":158,"samples_ran":104,"samples_unverified":54,"pointer_only_for_licence":46,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}