Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Mar 13;5(3):288-294.
doi: 10.1093/ehjdh/ztae021. eCollection 2024 May.

Machine learning-based analysis of non-invasive measurements for predicting intracardiac pressures

Annemiek E van Ravensberg  1 , Niels T B Scholte  1 , Aaram Omar Khader  1 , Jasper J Brugts  1 , Nico Bruining  1 , Robert M A van der Boon  1
Affiliations

Machine learning-based analysis of non-invasive measurements for predicting intracardiac pressures

Annemiek E van Ravensberg et al. Eur Heart J Digit Health. .

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.

PubMed Disclaimer

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

Graphical Abstract
Graphical Abstract
Figure 1
Figure 1
Receiver operator characteristics plots of the classification models. (A) A linear discriminant analysis classifier; (B) a quadratic discriminant analysis classifier; (C) a random forest; (D) k-nearest neighbour; (E) gradient boosting; (F) a multi-layer perceptron.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Bui AL, Horwich TB, Fonarow GC. Epidemiology and risk profile of heart failure. Nat Rev Cardiol 2011;8:30–41. - PMC - PubMed
    1. 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
    1. Savarese G, Lund LH. Global public health burden of heart failure. Card Fail Rev 2017;3:7–11. - PMC - PubMed
    1. 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
    1. Dharmarajan K, Hsieh AF, Lin Z, Bueno H, Ross JS, Horwitz LI, et al. . Diagnoses and timing of 30-day readmissions after hospitalization for heart failure, acute myocardial infarction, or pneumonia. JAMA 2013;309:355–363. - PMC - PubMed

LinkOut - more resources