CoChat
Sign Up
Cited by 21Machine Learning in HealthcareArtificial Intelligence in HealthcareECG Monitoring and Analysis

Enhancing clinical decision support with physiological waveforms - A multimodal benchmark in emergency care

Open access
Alcaraz, Juan Miguel Lopez, Bouma, Hjalmar, Strodthoff, Nils·2025·Computers in Biology and Medicine
DOI 10.1016/j.compbiomed.2025.110196
Open this paper in CoChat — free account

Abstract

BACKGROUND: AI-driven prediction algorithms have the potential to enhance emergency medicine by enabling rapid and accurate decision-making regarding patient status and potential deterioration. However, the integration of multimodal data, including raw waveform signals, remains underexplored in clinical decision support. METHODS: We present a dataset and benchmarking protocol designed to advance multimodal decision support in emergency care. Our models utilize demographics, biometrics, vital signs, laboratory values, and electrocardiogram (ECG) waveforms as inputs to predict both discharge diagnoses and patient deterioration. RESULTS: The diagnostic model achieves area under the receiver operating curve (AUROC) scores above 0.8 for 609 out of 1,428 conditions, covering both cardiac (e.g., myocardial infarction) and non-cardiac (e.g., renal disease, diabetes) diagnoses. The deterioration model attains AUROC scores above 0.8 for 14 out of 15 targets, accurately predicting critical events such as cardiac arrest, mechanical ventilation, ICU admission, and mortality. CONCLUSIONS: Our study highlights the positive impact of incorporating raw waveform data into decision support models, improving predictive performance. By introducing a unique, publicly available dataset and baseline models, we provide a foundation for measurable progress in AI-driven decision support for emergency care.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.compbiomed.2025.110196

Cites

33 of 35 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Continuous physiological waveforms such as ECGs are often excluded from existing ICU models, despite evidence that they can outperform traditional clinical variables across prognostic and non-cardiovascular tasks.

    “In particular, continuous physiological waveforms such as electrocardiograms (ECGs) are often excluded [7, 8], despite evidence that they can outperform traditional clinical variables across prognostic and non-cardiovascular tasks [3].”

    From A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking (2026) · cites this paper as [3]

    Section 4.1 (page unavailable) reports that ECG-waveform-only models outperform clinical-routine-data models for diagnoses, which include non-cardiac conditions discussed in Section 4.2. But for deterioration prediction, the clinical-routine-data model outperforms the waveform-only model; superior performance there comes from multimodal models that combine waveforms with clinical data. The claim therefore overstates the evidence that waveforms outperform traditional clinical variables across prognostic tasks. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • ECG waveforms are included due to prior evidence demonstrating their statistically significant added value for related clinical prediction tasks [3].

    “ECG waveforms are included due to prior evidence demonstrating their statistically significant added value for related clinical prediction tasks [3].”

    From A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking (2026) · cites this paper as [3]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 3

  1. [19][19] S. A. Lee, S. Jain, A. Chen, A. Biswas, J. Fang, A. Rudas, J. N. Chiang, Multimodal clinical pseudo-notes for emergency department prediction tasks using multiple embedding model for ehr (meme), ArXiv Preprint arXiv:2402.00160 (2024). - · arXiv
  2. [22][22] J. M. Lopez Alcaraz, N. Strodthoff, Mimic-iv-ext-mds-ed: Multimodal decision support in the emergency department - a benchmark dataset for diagnoses and deterioration prediction in emergency medicine (version 1.0.0), doi: https://doi.org/10.13026/p90d-vd84 (2024). doi:10.13026/p90d-vd84 . - · DOI
  3. [33][33] J. M. L. Alcaraz, N. Strodthoff, Causalconceptts: Causal attributions for time series classification using high fidelity diffusion models, ArXiv Preprint arXiv:2405.15871 (2024). - · arXiv

Cited by

Sorted by citations

Related

Authors
Alcaraz, J. M. L., Bouma, H., & Strodthoff, N.
Affiliations
  • Carl von Ossietzky Universität Oldenburg (DE)
  • University Medical Center Groningen (NL)
Corresponding author
Strodthoff, Nils
ORCID
Venue
Computers in Biology and Medicine
Publisher
Elsevier BV
Published
2025-06
Volume
192
Issue
Pt A
Pages
110196
ISSN
0010-4825 (ISSN-L)
DOI
10.1016/j.compbiomed.2025.110196
OpenAlex
W4409978917
Cited by
13
References
33
Citations by year
2026: 7 · 2025: 6
FWCI
5.21
Type
journal article
Language
en
Open access
Licence
Locations
  • Computers in Biology and Medicine (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Carl von Ossiezky University of Oldenburg (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
Keywords
clinical decision support, physiological waveforms, electrocardiogram, multimodal data, emergency medicine, clinical deterioration prediction, benchmark dataset, vital signs, laboratory parameters, cardiac arrest prediction, ICU admission prediction, mortality prediction
MeSH terms
Clinical Decision-Making, Machine Learning, Deep Learning, Aged, Algorithms, Artificial Intelligence, Electrocardiography, Emergency Medical Services, Female, Humans, Male, Middle Aged, Models, Statistical, Benchmarking, Decision Support Systems, Clinical, Workflow, Datasets as Topic

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review