Papers › HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data

HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data

16 Nov 2021NeurIPS Datasets and Benchmarks 2021arXiv:2111.08536archive 2025-07-28

Hugo Yèche, Rita Kuznetsova, Marc Zimmermann, Matthias Hüser, Xinrui Lyu, Martin Faltys, Gunnar Rätsch

The recent success of machine learning methods applied to time series collected from Intensive Care Units (ICU) exposes the lack of standardized machine learning benchmarks for developing and comparing such methods. While raw datasets, such as MIMIC-IV or eICU, can be freely accessed on Physionet, the choice of tasks and pre-processing is often chosen ad-hoc for each publication, limiting comparability across publications. In this work, we aim to improve this situation by providing a benchmark covering a large spectrum of ICU-related tasks. Using the HiRID dataset, we define multiple clinically relevant tasks in collaboration with clinicians. In addition, we provide a reproducible end-to-end pipeline to construct both data and labels. Finally, we provide an in-depth analysis of current state-of-the-art sequence modeling methods, highlighting some limitations of deep learning approaches for this type of data. With this benchmark, we hope to give the research community the possibility of a fair comparison of their work.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 8 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ratschlab/HIRID-ICU-Benchmark officialmentioned in papermentioned on GitHubpytorchMITSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran
3unverified

Licence: 6 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ratschlab/HIRID-ICU-Benchmark. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ratschlab/HIRID-ICU-Benchmark official repository 8 samples, 5 ran (0 instrument-failed) · 3 unverified
balanced_accuracy_compute_fn icu_benchmarks/models/metrics.py ran MIT (permissive) here; the stored copy is pointer only · 8c712712d170d6fa · report fixture: signature y_preds:Tensor/2/float, y_targets:Tensor/1/int · returned float · level recorded 2026-09-24
convert_to_days icu_benchmarks/common/reference_data.py ran MIT (permissive) here; the stored copy is pointer only · 98ad0404a78f5d45 · report fixture: signature x:str/0/str · returned float · level recorded 2026-09-24
ece_curve_compute_fn icu_benchmarks/models/metrics.py ran MIT (permissive) here; the stored copy is pointer only · 1bdf730ebc38566a · report fixture: signature y_preds:Tensor/1/float, y_targets:Tensor/1/int · returned tuple · level recorded 2026-09-24
is_df_sorted icu_benchmarks/labels/label_benchmark.py ran MIT (permissive) · 7bad4865010364c1 · report fixture: signature df:DataFrame/0/?, colname:str/0/str · returned bool · level recorded 2026-09-24
read_var_ref_table icu_benchmarks/common/lookups.py ran MIT (permissive) here; the stored copy is pointer only · 1ecd73f1856cbb81 · report fixture: signature var_ref_path:str/0/str · returned DataFrame · level recorded 2026-09-24
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
icu_benchmarks/models/metrics.py unverified MIT (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
get_bindings_and_params icu_benchmarks/models/utils.py unverified MIT (permissive) · 0af839c625fc0b73 · report
read_reference_table icu_benchmarks/common/lookups.py unverified MIT (permissive) here; the stored copy is pointer only · b37afd4624d8fae8 · report

Tasks

BIG-bench Machine LearningCirculatory FailureICU MortalityKidney FunctionPatient PhenotypingRemaining Length of StayRespiratory FailureTime SeriesTime Series Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Circulatory Failure HiRID LGBM AUPRC 0.389±0.003 #2 of 8 Archive leaderboard report
Circulatory Failure HiRID LGBM ( + hand crafted features) AUPRC 0.388±0.002 #3 of 8 Archive leaderboard report
Circulatory Failure HiRID GRU AUPRC 0.368±0.005 #4 of 8 Archive leaderboard report
Circulatory Failure HiRID Transformer AUPRC 0.352±0.006 #5 of 8 Archive leaderboard report
Circulatory Failure HiRID LR AUPRC 0.305±0.000 #6 of 8 Archive leaderboard report
Circulatory Failure HiRID LSTM AUPRC 0.32.2±0.008 #7 of 8 Archive leaderboard report
Circulatory Failure HiRID TCN AUPRC 0.35.8±0.006 #8 of 8 Archive leaderboard report
ICU Mortality HiRID LGBM ( + hand crafted features) AUPRC 0.626±0.000 #1 of 7 Archive leaderboard report
ICU Mortality HiRID Transformer AUPRC 0.610±0.008 #2 of 7 Archive leaderboard report
ICU Mortality HiRID GRU AUPRC 0.603 ±0.016 #3 of 7 Archive leaderboard report
ICU Mortality HiRID TCN AUPRC 0.602±0.011 #4 of 7 Archive leaderboard report
ICU Mortality HiRID LSTM AUPRC 0.600±0.009 #5 of 7 Archive leaderboard report
ICU Mortality HiRID Logistic Regression AUPRC 0.581±0.000 #6 of 7 Archive leaderboard report
ICU Mortality HiRID LGBM AUPRC 0.546±0.008 #7 of 7 Archive leaderboard report
Kidney Function HiRID LGBM ( + hand crafted features) MAE 0.45±0.00 #1 of 6 Archive leaderboard report
Kidney Function HiRID LGBM MAE 0.45±0.00 #2 of 6 Archive leaderboard report
Kidney Function HiRID Transformer MAE 0.48±0.02 #3 of 6 Archive leaderboard report
Kidney Function HiRID GRU MAE 0.49±0.02 #4 of 6 Archive leaderboard report
Kidney Function HiRID LSTM MAE 0.50±0.01 #5 of 6 Archive leaderboard report
Kidney Function HiRID TCN MAE 0.50±0.01 #6 of 6 Archive leaderboard report
Patient Phenotyping HiRID LGBM ( + hand crafted features) Balanced Accuracy 45.8±2.0 #1 of 7 Archive leaderboard report
Patient Phenotyping HiRID Transformer Balanced Accuracy 42.7±1.4 #2 of 7 Archive leaderboard report
Patient Phenotyping HiRID TCN Balanced Accuracy 41.6±2.3 #3 of 7 Archive leaderboard report
Patient Phenotyping HiRID LGBM Balanced Accuracy 40.4±0.8 #4 of 7 Archive leaderboard report
Patient Phenotyping HiRID LSTM Balanced Accuracy 39.5±1.2 #5 of 7 Archive leaderboard report
Patient Phenotyping HiRID GRU Balanced Accuracy 39.2±2.1 #6 of 7 Archive leaderboard report
Patient Phenotyping HiRID Logistic Regression Balanced Accuracy 39.1±0.0 #7 of 7 Archive leaderboard report
Remaining Length of Stay HiRID LGBM MAE 56.9±0.4 #1 of 6 Archive leaderboard report
Remaining Length of Stay HiRID LGBM ( + hand crafted features) MAE 57.0±0.3 #2 of 6 Archive leaderboard report
Remaining Length of Stay HiRID Transformer MAE 59.5±2.8 #3 of 6 Archive leaderboard report
Remaining Length of Stay HiRID TCN MAE 59.8±2.8 #4 of 6 Archive leaderboard report
Remaining Length of Stay HiRID GRU MAE 60.6±0.9 #5 of 6 Archive leaderboard report
Remaining Length of Stay HiRID LSTM MAE 60.7±1.6 #6 of 6 Archive leaderboard report
Respiratory Failure HiRID LGBM ( + hand crafted features) AUPRC 0.604±0.002 #2 of 8 Archive leaderboard report
Respiratory Failure HiRID Transformer AUPRC 0.594±0.003 #3 of 8 Archive leaderboard report
Respiratory Failure HiRID GRU AUPRC 0.592±0.003 #4 of 8 Archive leaderboard report
Respiratory Failure HiRID TCN AUPRC 0.589±0.003 #5 of 8 Archive leaderboard report
Respiratory Failure HiRID LGBM AUPRC 0.585±0.001 #6 of 8 Archive leaderboard report
Respiratory Failure HiRID LSTM AUPRC 0.569±0.003 #7 of 8 Archive leaderboard report
Respiratory Failure HiRID Logistic Regression AUPRC 0.530±0.000 #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections