Prospects for artificial intelligence-enhanced electrocardiogram as a unified screening tool for cardiac and non-cardiac conditions: an explorative study in emergency care
Open accessAbstract
Aims: Current deep learning algorithms for automatic ECG analysis have shown notable accuracy but are typically narrowly focused on singular diagnostic conditions. This exploratory study aims to investigate the capability of a single deep learning model to predict a diverse range of both cardiac and non-cardiac discharge diagnoses based on a single ECG collected in the emergency department. Methods and results: In this study, we assess the performance of a model trained to predict a broad spectrum of diagnoses. We find that the model can reliably predict 253 ICD codes (81 cardiac and 172 non-cardiac) in the sense of exceeding an AUROC score of 0.8 in a statistically significant manner. Conclusion: The model demonstrates proficiency in handling a wide array of cardiac and non-cardiac diagnostic scenarios, indicating its potential as a comprehensive screening tool for diverse medical encounters.
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.
Integrity signals
Registry
Cites
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.
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?
S4-based encoder has demonstrated superior performance over conventional deep learning architectures such as CNNs, RNNs, and transformers in physiological time-series modeling [29, 34].
“ECG waveforms are processed using an S4-based encoder built on structured state space models [33], which has demonstrated superior performance over conventional deep learning architectures such as CNNs, RNNs, and transformers in physiological time-series modeling [29, 34].”
From A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking (2026) · cites this paper as [29]
The Results (Model performance; page unavailable) report that an S4 model outperformed a state-of-the-art convolutional model on ECG classification, supporting the CNN comparison. Our copy does not report comparisons with RNNs or transformers, so it does not support the broader superiority claim. (LLM, conf=0.88)
Experimental — accuracy not yet measuredThe MDS-ICU dataset integrates data from MIMIC-IV, MIMIC-IV-ECG, and MIMIC-IV-ECG-ICD, focusing on ICU patients with at least one 10-second 12-lead ECG.
“The MDS-ICU dataset integrates data from MIMIC-IV [27], MIMIC-IV-ECG [28], and MIMIC-IV-ECG-ICD [29], focusing on ICU patients with at least one 10-second 12-lead ECG.”
From A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking (2026) · cites this paper as [29]
Median imputation based on training set statistics is applied to handle missing data, following the protocol outlined in [29], in line with best practices from the literature [36].
“We apply median imputation based on training set statistics to handle missing data and introduce binary indicator columns to flag imputed values, following the protocol outlined in [29], in line with best practices from the literature [36].”
From A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking (2026) · cites this paper as [29]
The Methods sections on dataset construction and training (page unavailable) describe ECG processing and model training, but do not address missing-data imputation. Searches for median imputation, training-set statistics, and missingness indicators found no passage in our copy establishing that this paper recommends the practice attributed to [36]. (LLM, conf=0.75)
Experimental — accuracy not yet measured
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
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401 · cited 2× · see citing works
“21 In this work, we will only work with the subset of ECGs captured in the ED and refer to it as MIMIC-IV-ECG-ICD-ED dataset.”
MethodIllusory generalizability of clinical prediction models
Chekroud, A. M., Hawrilenko, M., Loho, H., Bondar, J., Gueorguieva, R., Hasan, A., Kambeitz, J., Corlett, P. R., Koutsouleris, N., Krumholz, H. M., et al. (2024) · Science · doi:10.1126/science.adg8538 · Cited by 251 · see citing works
Explaining Deep Learning for ECG Analysis: Building Blocks for Auditing and Knowledge Discovery
Wagner, P., Mehari, T., Haverkamp, W., & Strodthoff, N. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108525 · Cited by 48 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 25
- [2]Schläpfer J, Wellens HJ. Computer-interpreted electrocardiograms: benefits and limitations. J Am Coll Cardiol 2017; 70: 1183– 1192. 28838369
- [3]Topol EJ. What’s lurking in your electrocardiogram?. Lancet 2021; 397: 785. 33640054 PMC9757893
- [4]Siontis KC, Noseworthy PA, Attia ZI, Friedman PA. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nat Rev Cardiol 2021; 18: 465– 478. 33526938 PMC7848866
- [5]Strodthoff N, Wagner P, Schaeffter T, Samek W. Deep learning for ECG analysis: benchmarks and insights from PTB-XL. IEEE J Biomed Health Inform 2020; 25: 1519– 1528. 32903191
- [6]Kashou AH, Ko W-Y, Attia ZI, Cohen MS, Friedman PA, Noseworthy PA. A comprehensive artificial intelligence–enabled electrocardiogram interpretation program. Cardiovasc Digit Health J 2020; 1: 62– 70. 35265877 PMC8890098
- [7]Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, et al Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 2019; 25: 65– 69. 30617320 PMC6784839
- [8]Attia ZI, Friedman PA, Noseworthy PA, Lopez-Jimenez F, Ladewig DJ, Satam G, et al Age and sex estimation using artificial intelligence from standard 12-lead ECGs. Circ Arrhythm Electrophysiol 2019; 12: e007284. 31450977 PMC7661045
- [9]Attia ZI, Kapa S, Lopez-Jimenez F, McKie PM, Ladewig DJ, Satam G, et al Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram. Nat Med 2019; 25: 70– 74. 30617318
- [10]Attia ZI, Noseworthy PA, Lopez-Jimenez F, Asirvatham SJ, Deshmukh AJ, Gersh BJ, et al An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet 2019; 394: 861– 867. 31378392
- [11]Kwon J-M, Cho Y, Jeon K-H, Cho S, Kim K-H, Baek SD, et al A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study. Lancet Digit Health 2020; 2: e358– e367. 33328095
- [12]Kulkarni AR, Patel AA, Pipal KV, Jaiswal SG, Jaisinghani MT, Thulkar V, et al Machine-learning algorithm to non-invasively detect diabetes and pre-diabetes from electrocardiogram. BMJ Innov 2023; 9: 32– 42.
- [13]Ahn JC, Attia ZI, Rattan P, Mullan AF, Buryska S, Allen AM, et al Development of the AI-cirrhosis-ECG score: an electrocardiogram-based deep learning model in cirrhosis. Am J Gastroenterol 2021; 117: 424– 432. PMC9727935 35029163
- [14]Wagner P, Strodthoff N, Bousseljot R-D, Kreiseler D, Lunze FI, Samek W, et al PTB-XL, a large publicly available electrocardiography dataset. Sci Data 2020; 7: 154. 32451379 PMC7248071
- [15]Ribeiro AH, Ribeiro MH, Paixão GMM, Oliveira DM, Gomes PR, Canazart JA, et al Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun 2020; 11: 1760. 32273514 PMC7145824
- [16]Sun W, Kalmady SV, Salimi A, Sepehrvand N, Ly E, Hindle A, et al ECG for high-throughput screening of multiple diseases: proof-of-concept using multi-diagnosis deep learning from population-based datasets. In: Medical Imaging Meets NeurIPS Workshop 2021, Sydney, Australia. Curran Associates; 2022.
- [17]Kashou AH, Adedinsewo DA, Siontis KC, Noseworthy PA. Artificial intelligence-enabled ECG: physiologic and pathophysiologic insights and implications. Compr Physiol 2022; 12: 3417– 3424. 35766831 PMC9795459
- [18]Mehari T, Strodthoff N. Self-supervised representation learning from 12-lead ECG data. Comput Biol Med 2022; 141: 105114. 34973584
- [19]Sibbald M, Abdulla B, Keuhl A, Norman G, Monteiro S, Sherbino J. Electronic diagnostic support in emergency physician triage: qualitative study with thematic analysis of interviews. JMIR Human Factors 2022; 9: e39234. 36178728 PMC9568817
- [20]Gow B, Pollard T, Nathanson LA, Johnson A, Moody B, Fernandes C, et al MIMIC-IV-ECG: diagnostic electrocardiogram matched subset (version 1.0). PhysioNet 2023. doi: 10.13026/4nqg-sb35. · DOI · Paper page
- [22]Mehari T, Strodthoff N. Towards quantitative precision for ECG analysis: leveraging state space models, self-supervision and patient metadata. IEEE J Biomed Health Inform 2023; 27: 5326– 5334. 37656655
- [23]Gu A, Goel K, Re C. Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations 2021. ICLR; 2022.
- [25]Ahn JC, Attia ZI, Rattan P, Mullan AF, Buryska S, Allen AM, et al Development of the AI-cirrhosis-ECG (ACE) score: an electrocardiogram-based deep learning model in cirrhosis. Am J Gastroenterol 2022; 117: 424. 35029163 PMC9727935
- [26]Capecchi PL, Laghi-Pasini F, El-Sherif N, Qu Y, Boutjdir M, Lazzerini PE. Autoimmune and inflammatory K+ channelopathies in cardiac arrhythmias: clinical evidence and molecular mechanisms. Heart Rhythm 2019; 16: 1273– 1280. 30772530
- [27]Ouyang D. The uncanny and unreasonable performance of AI in medical imaging, in Causality in Medical Image Computing (MICCAI 2023 tutorial), 2023. https://sites.google.com/view/causemic (1 December 2023).
- [30]Zhou H-Y, Yu Y, Wang C, Zhang S, Gao Y, Pan J, et al A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nat Biomed Eng 2023; 7: 743– 755. 37308585
Cited by
Sorted by citations
Alcaraz, J. M. L., Bouma, H., & Strodthoff, N. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110196 · Cited by 13 · see citing works
Self-citationAlcaraz, J. M. L., Moran, X. L., Zaragoza, E. D., Händel, C., Koebe, R., Haverkamp, W., & Strodthoff, N. (2026) · arXiv · doi:10.48550/arxiv.2601.06645
“The MDS-ICU dataset integrates data from MIMIC-IV [27], MIMIC-IV-ECG [28], and MIMIC-IV-ECG-ICD [29], focusing on ICU patients with at least one 10-second 12-lead ECG. ECG waveforms are included due to prior evidence demonstrating their statistically significant added value for related clinical…”
InfluentialSelf-citation
- Authors
- Strodthoff, N., Lopez Alcaraz, J. M., & Haverkamp, W.
- Affiliations
- Carl von Ossietzky Universität Oldenburg (DE)
- Carl von Ossietzky Universität Oldenburg , School VI Medicine and Health Services, Department of Health Services Research, Ammerländer Heerstr. 114-118, 26129 Oldenburg , Germany
- Charité – Universitätsmedizin Berlin (DE)
- Corresponding author
- Strodthoff, Nils
- Venue
- European Heart Journal - Digital Health
- Publisher
- Oxford University Press (OUP)
- Published
- 2024-05-12
- Volume
- 5
- Issue
- 4
- Pages
- 454-460
- ISSN
- 2634-3916 (ISSN-L)
- PMC
- PMC11284007
- OpenAlex
- W4396848156
- Cited by
- 22
- References
- 3
- Citations by year
- 2026: 6 · 2025: 16
- FWCI
- 6.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- European Heart Journal - Digital Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- artificial intelligence, electrocardiogram, deep learning, automated ECG analysis, emergency department, ICD-10 codes, heart disease diagnosis, screening tool, model generalization
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
