Machine learning-based analysis of non-invasive measurements for predicting intracardiac pressures
- PMID: 38774375
- PMCID: PMC11104465
- DOI: 10.1093/ehjdh/ztae021
Machine learning-based analysis of non-invasive measurements for predicting intracardiac pressures
Abstract
Aims: Early detection of congestion has demonstrated to improve outcomes in heart failure (HF) patients. However, there is limited access to invasively haemodynamic parameters to guide treatment. This study aims to develop a model to estimate the invasively measured pulmonary capillary wedge pressure (PCWP) using non-invasive measurements with both traditional statistics and machine learning (ML) techniques.
Methods and results: The study involved patients undergoing right-sided heart catheterization at Erasmus MC, Rotterdam, from 2017 to 2022. Invasively measured PCWP served as outcomes. Model features included non-invasive measurements of arterial blood pressure, saturation, heart rate (variability), weight, and temperature. Various traditional and ML techniques were used, and performance was assessed using R2 and area under the curve (AUC) for regression and classification models, respectively. A total of 853 procedures were included, of which 31% had HF as primary diagnosis and 49% had a PCWP of 12 mmHg or higher. The mean age of the cohort was 59 ± 14 years, and 52% were male. The heart rate variability had the highest correlation with the PCWP with a correlation of 0.16. All the regression models resulted in low R2 values of up to 0.04, and the classification models resulted in AUC values of up to 0.59.
Conclusion: In this study, non-invasive methods, both traditional and ML-based, showed limited correlation to PCWP. This highlights the weak correlation between traditional HF monitoring and haemodynamic parameters, also emphasizing the limitations of single non-invasive measurements. Future research should explore trend analysis and additional features to improve non-invasive haemodynamic monitoring, as there is a clear demand for further advancements in this field.
Keywords: Heart failure; Machine learning; Monitoring; Non-invasive; Pulmonary capillary wedge pressure.
© The Author(s) 2024. Published by Oxford University Press on behalf of the European Society of Cardiology.
Conflict of interest statement
Conflict of interest: N.T.B.S. none; A.E.v.R. none; A.O.K. none; J.J.B. reports an independent research grant for ISS from Abbott to the Institute and has had speaker engagements or advisory boards in the past 5 years with AstraZeneca, Abbott, Boehringer Ingelheim, Bayer, Danchii Sankyo, Novartis, and Vifor. N.B. reports to be Editor-in-Chief at the European Heart Journal – Digital Health, Topic Co-ordinator of Digital Health at the congress programme committee of the European Society of Cardiology (ESC), and Vice-Chair of the Digital Health Committee of the ESC. R.M.A.v.d.B. reports an independent research grant for ISS from Abbott to the Institute and has had speaker engagements or advisory boards in the past 5 years with Abbott and Boehringer Ingelheim.
Figures
Similar articles
-
Photoplethysmography and intracardiac pressures: early insights from a pilot study.Eur Heart J Digit Health. 2024 Mar 7;5(3):379-383. doi: 10.1093/ehjdh/ztae020. eCollection 2024 May. Eur Heart J Digit Health. 2024. PMID: 38774368 Free PMC article.
-
Associations of 2D speckle tracking echocardiography-based right heart deformation parameters and invasively assessed hemodynamic measurements in patients with pulmonary hypertension.Cardiovasc Ultrasound. 2020 May 14;18(1):13. doi: 10.1186/s12947-020-00197-z. Cardiovasc Ultrasound. 2020. PMID: 32410698 Free PMC article.
-
Echocardiography to estimate high filling pressure in patients with heart failure and reduced ejection fraction.ESC Heart Fail. 2020 Oct;7(5):2268-2277. doi: 10.1002/ehf2.12748. Epub 2020 Jul 21. ESC Heart Fail. 2020. PMID: 32692489 Free PMC article.
-
Non-invasive evaluation of pulmonary capillary wedge pressure using the left atrial expansion index in mitral valve stenosis, prosthesis and repair.Int J Cardiovasc Imaging. 2023 May;39(5):967-975. doi: 10.1007/s10554-023-02807-z. Epub 2023 Feb 10. Int J Cardiovasc Imaging. 2023. PMID: 36763208
-
Echocardiographic assessment of pulmonary capillary wedge pressure by E/e' ratio: A systematic review and meta-analysis.J Crit Care. 2023 Aug;76:154281. doi: 10.1016/j.jcrc.2023.154281. Epub 2023 Mar 1. J Crit Care. 2023. PMID: 36867978 Review.
References
-
- McDonagh TA, Metra M, Adamo M, Gardner RS, Baumbach A, Bohm M, et al. . 2021 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure. Eur Heart J 2021;42:3599–3726. - PubMed
-
- Krumholz HM, Merrill AR, Schone EM, Schreiner GC, Chen J, Bradley EH, et al. . Patterns of hospital performance in acute myocardial infarction and heart failure 30-day mortality and readmission. Circ Cardiovasc Qual Outcomes 2009;2:407–413. - PubMed
LinkOut - more resources
Full Text Sources
Research Materials
Miscellaneous