CoChat
Sign Up
Cited by 8Artificial Intelligence in HealthcareECG Monitoring and AnalysisPulmonary Hypertension Research and Treatments

An ensemble learning model for detection of pulmonary hypertension using electrocardiogram, chest X-ray, and brain natriuretic peptide

Open access
Kishikawa, Risa, Kodera, Satoshi, Setoguchi, Naoto, Tanabe, Kengo, Kushida, Shunichi, Nanasato, Mamoru, Maki, Hisataka, Fujita, Hideo +15 more·2025·European Heart Journal - Digital Health
DOI 10.1093/ehjdh/ztae097PMC PMC11914732
Open this paper in CoChat — free accountOpen PDF

Abstract

Aims: Delayed diagnosis of pulmonary hypertension (PH) is a known cause of poor patient prognosis. We aimed to develop an artificial intelligence (AI) model, using ensemble learning method to detect PH using electrocardiography (ECG), chest X-ray (CXR), and brain natriuretic peptide (BNP), facilitating accurate detection and prompting further examinations. Methods and results: We developed a convolutional neural network model using ECG data to predict PH, labelled by ECG from seven institutions. Logistic regression was used for the BNP prediction model. We referenced a CXR deep learning model using ResNet18. Outputs from each of the three models were integrated into a three-layer fully connected multimodal model. Ten cardiologists participated in an interpretation test, detecting PH from patients’ ECG, CXR, and BNP data both with and without the ensemble learning model. The area under the receiver operating characteristic curves of the ECG, CXR, BNP, and ensemble learning model were 0.818 [95% confidence interval (CI), 0.808–0.828], 0.823 (95% CI, 0.780–0.866), 0.724 (95% CI, 0.668–0.780), and 0.872 (95% CI, 0.829–0.915). Cardiologists’ average accuracy rates were 65.0 ± 4.7% for test without AI model and 74.0 ± 2.7% for test with AI model, a statistically significant improvement (P < 0.01). Conclusion: Our ensemble learning model improved doctors’ accuracy in detecting PH from ECG, CXR, and BNP examinations. This suggests that earlier and more accurate PH diagnosis is possible, potentially improving patient prognosis.

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 · 10.1093/ehjdh/ztae097

Cites

2 of 2 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?

  • Convincing prospective evidence that ECG-centred multimodal approaches can safely support gatekeeper-type decision making is still sparse.

    “At present, however, direct SHD-specific evidence for ECG-centred multimodal screening remains limited, and convincing prospective evidence that such approaches can safely support gatekeeper-type decision making is still sparse.69,70”

    From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [70]

    The Methods’ interpretation-test section (page not listed) describes decisions on selected test-set cases, while the Discussion’s Limitations section says the test differed from clinical practice and that the model cannot be directly applied to screening asymptomatic people. These passages support caution about using this approach for real-world gatekeeper decisions, but the paper studies pulmonary hypertension and does not establish how sparse prospective evidence is across ECG-centred multimodal screening for structural heart disease. (LLM, conf=0.81)

    Experimental — accuracy not yet measured

  • Direct SHD-specific evidence for ECG-centred multimodal screening remains limited.

    “At present, however, direct SHD-specific evidence for ECG-centred multimodal screening remains limited, and convincing prospective evidence that such approaches can safely support gatekeeper-type decision making is still sparse.69,70”

    From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [70]

    The Introduction (page unavailable) says that no multimodal AI models for detecting pulmonary hypertension had previously been reported. The paper studies pulmonary hypertension, not the availability of direct SHD-specific evidence for ECG-centred multimodal screening; a search for structural heart disease and SHD did not establish that claim. (LLM, conf=0.76)

    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

Flagged first, then by citations

Research works printed but not linked: 35

  1. [1]Humbert M, Kovacs G, Hoeper MM, Badagliacca R, Berger RMF, Brida M, et al 2022 ESC/ERS Guidelines for the diagnosis and treatment of pulmonary hypertension. Eur Heart J 2022; 43: 3618– 3731. 36017548
  2. [2]Simonneau G, Montani D, Celermajer DS, Denton CP, Gatzoulis MA, Krowka M, et al Haemodynamic definitions and updated clinical classification of pulmonary hypertension. Eur Respir J 2019; 53: 1801913. 30545968 PMC6351336
  3. [3]Ley L, Höltgen R, Bogossian H, Ghofrani HA, Bandorski D. Electrocardiogram in patients with pulmonary hypertension. J Electrocardiol 2023; 79: 24– 29. 36913785
  4. [4]Crisan S, Baghina RM, Luca SA, Cozlac AR, Negru AG, Vacarescu C, et al Comprehensive imaging in patients with suspected pulmonary arterial hypertension. Heart 2024; 110: 228– 234. 37463729
  5. [5]Miniati M, Monti S, Airò E, Pancani R, Formichi B, Bauleo C, et al Accuracy of chest radiography in predicting pulmonary hypertension: a case-control study. Thromb Res 2014; 133: 345– 351. 24393659
  6. [6]Leuchte HH, Holzapfel M, Baumgartner RA, Ding I, Neurohr C, Vogeser M, et al Clinical significance of brain natriuretic peptide in primary pulmonary hypertension. J Am Coll Cardiol 2004; 43: 764– 770. 14998614
  7. [7]Rudski LG, Lai WW, Afilalo J, Hua L, Handschumacher MD, Chandrasekaran K, et al Guidelines for the echocardiographic assessment of the right heart in adults: a report from the American Society of Echocardiography endorsed by the European Association of Echocardiography, a registered branch of the European Society of Cardiology, and the Canadian Society of Echocardiography. J Am Soc Echocardiogr 2010; 23: 685– 713. quiz 786–8. 20620859
  8. [8]Torbicki A, Kurzyna M. The diagnostic approach to pulmonary hypertension. Semin Respir Crit Care Med 2023; 44: 728– 737. 37487526
  9. [9]Strange G, Gabbay E, Kermeen F, Williams T, Carrington M, Stewart S, et al Time from symptoms to definitive diagnosis of idiopathic pulmonary arterial hypertension: the delay study. Pulm Circ 2013; 3: 89– 94. 23662179 PMC3641745
  10. [10]Small M, Perchenet L, Bennett A, Linder J. The diagnostic journey of pulmonary arterial hypertension patients: results from a multinational real-world survey. Ther Adv Respir Dis 2024; 18: 17534666231218886. 38357903 PMC10870813
  11. [12]Aras MA, Abreau S, Mills H, Radhakrishnan L, Klein L, Mantri N, et al Electrocardiogram detection of pulmonary hypertension using deep learning. J Card Fail 2023; 29: 1017– 1028. 36706977 PMC10363571
  12. [13]Liu CM, Shih ESC, Chen JY, Huang CH, Wu IC, Chen PF, et al Artificial intelligence-enabled electrocardiogram improves the diagnosis and prediction of mortality in patients with pulmonary hypertension. JACC Asia 2022; 2: 258– 270. 36338407 PMC9627911
  13. [14]Leha A, Hellenkamp K, Unsöld B, Mushemi-Blake S, Shah AM, Hasenfuß G, et al A machine learning approach for the prediction of pulmonary hypertension. PLoS One 2019; 14: e0224453. 31652290 PMC6814224
  14. [15]Imai S, Sakao S, Nagata J, Naito A, Sekine A, Sugiura T, et al Artificial intelligence-based model for predicting pulmonary arterial hypertension on chest x-ray images. BMC Pulm Med 2024; 24: 101. 38413932 PMC10898025
  15. [16]Kusunose K, Hirata Y, Tsuji T, Kotoku J, Sata M. Deep learning to predict elevated pulmonary artery pressure in patients with suspected pulmonary hypertension using standard chest X ray. Sci Rep 2020; 10: 19311. 33203947 PMC7672097
  16. [17]Amal S, Safarnejad L, Omiye JA, Ghanzouri I, Cabot JH, Ross EG. Use of multi-modal data and machine learning to improve cardiovascular disease care. Front Cardiovasc Med 2022; 9: 840262. 35571171 PMC9091962
  17. [18]Soto JT, Weston Hughes J, Sanchez PA, Perez M, Ouyang D, Ashley EA. Multimodal deep learning enhances diagnostic precision in left ventricular hypertrophy. Eur Heart J Digit Health 2022; 3: 380– 389. 36712167 PMC9707995
  18. [19]Hassan N, Slight R, Morgan G, Bates DW, Gallier S, Sapey E, et al Road map for clinicians to develop and evaluate AI predictive models to inform clinical decision-making. BMJ Health Care Inform 2023; 30: e100784. PMC10414079 37558245
  19. [20]de Hond AAH, Leeuwenberg AM, Hooft L, Kant IMJ, Nijman SWJ, van Os HJA, et al Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review. NPJ Digit Med 2022; 5: 2. 35013569 PMC8748878
  20. [21]Sato M, Kodera S, Setoguchi N, Tanabe K, Kushida S, Kanda J, et al Deep learning models for predicting left heart abnormalities from single-lead electrocardiogram for the development of wearable devices. Circ J 2023; 88: 146– 156. 37967949
  21. [22]Ueda D, Matsumoto T, Ehara S, Yamamoto A, Walston SL, Ito A, et al Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study. Lancet Digit Health 2023; 5: e525– e533. 37422342
  22. [23]Matsumoto T, Walston SL, Miki Y, Ueda D. Nervus: a comprehensive deep learning classification, regression, and prognostication tool for both medical image and clinical data analysis 2022. arXiv e-prints. December 12, 2022:arXiv:2212.11113v1. 10.48550/arXiv.2212.11113. · DOI
  23. [24]Manasrah A, Alkayem A, Qasaimeh M, Nofal S. Assessment of machine learning security: the case of healthcare data. In: International Conference on Data Science, E-Learning and Information Systems 2021, p. 91–98. Association for Computing Machinery, Ma'an, Jordan. 2021.
  24. [25]Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. JAIR 2002; 16: 321– 357.
  25. [26]Youden WJ. Index for rating diagnostic tests. Cancer 1950; 3: 32– 35. 15405679
  26. [27]Fluss R, Faraggi D, Reiser B. Estimation of the Youden Index and its associated cutoff point. Biom J 2005; 47: 458– 472. 16161804
  27. [28]Azpiri-Lopez JR, Galarza-Delgado DA, Colunga-Pedraza IJ, Arvizu-Rivera RI, Cardenas-de la Garza JA, Vera-Pineda R, et al Echocardiographic evaluation of pulmonary hypertension, right ventricular function, and right ventricular-pulmonary arterial coupling in patients with rheumatoid arthritis. Clin Rheumatol 2021; 40: 2651– 2656. 33443606
  28. [29]McLaughlin VV, Archer SL, Badesch DB, Barst RJ, Farber HW, Lindner JR, et al ACCF/AHA 2009 expert consensus document on pulmonary hypertension a report of the American College of Cardiology Foundation Task Force on Expert Consensus Documents and the American Heart Association developed in collaboration with the American College of Chest Physicians; American Thoracic Society, Inc.; and the Pulmonary Hypertension Association. J Am Coll Cardiol 2009; 53: 1573– 1619. 19389575
  29. [30]Greiner S, Jud A, Aurich M, Hess A, Hilbel T, Hardt S, et al Reliability of noninvasive assessment of systolic pulmonary artery pressure by Doppler echocardiography compared to right heart catheterization: analysis in a large patient population. J Am Heart Assoc 2014; 3: e001103. 25146706 PMC4310406
  30. [31]Bossone E, D’Andrea A, D’Alto M, Citro R, Argiento P, Ferrara F, et al Echocardiography in pulmonary arterial hypertension: from diagnosis to prognosis. J Am Soc Echocardiogr 2013; 26: 1– 14. 23140849
  31. [32]DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988; 44: 837– 845. 3203132
  32. [33]Sun X, Xu W. Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Signal Process Lett 2014; 21: 1389– 1393.
  33. [35]Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med 2019; 112: 103375. 31382212
  34. [36]O'Leary JM, Assad TR, Xu M, Farber-Eger E, Wells QS, Hemnes AR, et al Lack of a tricuspid regurgitation Doppler signal and pulmonary hypertension by invasive measurement. J Am Heart Assoc 2018; 7: e009362. 29960993 PMC6064901
  35. [37]Castro DC, Walker I, Glocker B. Causality matters in medical imaging. Nat Commun 2020; 11: 3673. 32699250 PMC7376027

Cited by

Sorted by citations

Authors
Kishikawa, R., Kodera, S., Setoguchi, N., Tanabe, K., Kushida, S., Nanasato, M., Maki, H., Fujita, H., Kato, N., Watanabe, H., Takahashi, M., Sawada, N., Ando, J., Sato, M., Sawano, S., Shinohara, H., Nakanishi, K., Minatsuki, S., Ishida, J., Fujiu, K., Akazawa, H., Morita, H., & Takeda, N.
Affiliations
  • University of Tokyo Hospital (JP)
  • Mitsui Memorial Hospital (JP)
  • Asahi General Hospital (JP)
  • Department of Cardiology, Sakakibara Heart Institute , Tokyo ,
  • Jichi Medical University (JP)
  • Tokyo Bay Urayasu Ichikawa Medical Center (JP)
  • JR Tokyo General Hospital (JP)
  • NTT (Japan) (JP)
  • Department of Cardiovascular Medicine, The University of Tokyo Hospital , 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655 ,
Corresponding author
Kodera, Satoshi
ORCID
Venue
European Heart Journal - Digital Health
Publisher
Oxford University Press (OUP)
Published
2025-01-16
Volume
6
Issue
2
Pages
209-217
ISSN
2634-3916 (ISSN-L)
DOI
10.1093/ehjdh/ztae097
PMC
PMC11914732
OpenAlex
W4406435340
Cited by
8
References
2
Citations by year
2026: 6 · 2025: 2
FWCI
2.44
Type
journal article
Language
en
Open access
Licence
Locations
  • European Heart Journal - Digital Health (publishedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
Funders
  • Cross-ministerial Strategic Innovation Promotion Program (SIP) on ‘Integrated Health Care System’ (JPJ012425)
  • Japan Agency for Medical Research and Development (JP23hk0102078h0003)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
  • Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Pulmonary Hypertension Research and Treatments
Keywords
pulmonary hypertension, early diagnosis, electrocardiogram, chest radiography, brain natriuretic peptide, ensemble learning, multimodal models, convolutional neural networks, ResNet-18, diagnostic accuracy

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