scholarly journals Wave Intensity Analysis Combined With Machine Learning can Detect Impaired Stroke Volume in Simulations of Heart Failure

2021 ◽  
Vol 9 ◽  
Author(s):  
Ryan M. Reavette ◽  
Spencer J. Sherwin ◽  
Meng-Xing Tang ◽  
Peter D. Weinberg
Keyword(s):  
Machine Learning ◽  
Heart Failure ◽  
Stroke Volume ◽  
Wave Intensity ◽  
Elderly Subjects ◽  
Support Vector ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Diagnostic Potential ◽  
Heart Performance

Heart failure is treatable, but in the United Kingdom, the 1-, 5- and 10-year mortality rates are 24.1, 54.5 and 75.5%, respectively. The poor prognosis reflects, in part, the lack of specific, simple and affordable diagnostic techniques; the disease is often advanced by the time a diagnosis is made. Previous studies have demonstrated that certain metrics derived from pressure–velocity-based wave intensity analysis are significantly altered in the presence of impaired heart performance when averaged over groups, but to date, no study has examined the diagnostic potential of wave intensity on an individual basis, and, additionally, the pressure waveform can only be obtained accurately using invasive methods, which has inhibited clinical adoption. Here, we investigate whether a new form of wave intensity based on noninvasive measurements of arterial diameter and velocity can detect impaired heart performance in an individual. To do so, we have generated a virtual population of two-thousand elderly subjects, modelling half as healthy controls and half with an impaired stroke volume. All metrics derived from the diameter–velocity-based wave intensity waveforms in the carotid, brachial and radial arteries showed significant crossover between groups—no one metric in any artery could reliably indicate whether a subject’s stroke volume was normal or impaired. However, after applying machine learning to the metrics, we found that a support vector classifier could simultaneously achieve up to 99% recall and 95% precision. We conclude that noninvasive wave intensity analysis has significant potential to improve heart failure screening and diagnosis.

scholarly journals Estimation of coronary wave intensity analysis using noninvasive techniques and its application to exercise physiology

2016 ◽  
Vol 310 (5) ◽  
pp. H619-H627 ◽  
Author(s):  
Christopher J. Broyd ◽  
Sukhjinder Nijjer ◽  
Sayan Sen ◽  
Ricardo Petraco ◽  
Siana Jones ◽  
...  
Keyword(s):  
Coronary Circulation ◽  
Exercise Physiology ◽  
Left Ventricular ◽  
Wave Intensity ◽  
Concordance Correlation Coefficient ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Concordance Correlation ◽  
Decompression Wave ◽  
Pulsed Wave Doppler

Wave intensity analysis (WIA) has found particular applicability in the coronary circulation where it can quantify traveling waves that accelerate and decelerate blood flow. The most important wave for the regulation of flow is the backward-traveling decompression wave (BDW). Coronary WIA has hitherto always been calculated from invasive measures of pressure and flow. However, recently it has become feasible to obtain estimates of these waveforms noninvasively. In this study we set out to assess the agreement between invasive and noninvasive coronary WIA at rest and measure the effect of exercise. Twenty-two patients (mean age 60) with unobstructed coronaries underwent invasive WIA in the left anterior descending artery (LAD). Immediately afterwards, noninvasive LAD flow and pressure were recorded and WIA calculated from pulsed-wave Doppler coronary flow velocity and central blood pressure waveforms measured using a cuff-based technique. Nine of these patients underwent noninvasive coronary WIA assessment during exercise. A pattern of six waves were observed in both modalities. The BDW was similar between invasive and noninvasive measures [peak: 14.9 ± 7.8 vs. −13.8 ± 7.1 × 104 W·m−2·s−2, concordance correlation coefficient (CCC): 0.73, P < 0.01; cumulative: −64.4 ± 32.8 vs. −59.4 ± 34.2 × 102 W·m−2·s−1, CCC: 0.66, P < 0.01], but smaller waves were underestimated noninvasively. Increased left ventricular mass correlated with a decreased noninvasive BDW fraction ( r = −0.48, P = 0.02). Exercise increased the BDW: at maximum exercise peak BDW was −47.0 ± 29.5 × 104 W·m−2·s−2 ( P < 0.01 vs. rest) and cumulative BDW −19.2 ± 12.6 × 103 W·m−2·s−1 ( P < 0.01 vs. rest). The BDW can be measured noninvasively with acceptable reliably potentially simplifying assessments and increasing the applicability of coronary WIA.

Wave intensity analysis of left atrial mechanics and energetics in anesthetized dogs

2007 ◽  
Vol 292 (3) ◽  
pp. H1533-H1540 ◽  
Author(s):  
Tracy N. Hobson ◽  
Jacqueline A. Flewitt ◽  
Israel Belenkie ◽  
John V. Tyberg
Keyword(s):  
Mitral Valve ◽  
Pulmonary Veins ◽  
Left Ventricular ◽  
Wave Intensity ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Volume Loading ◽  
Forward Movement ◽  
Reflected Wave ◽  
Left Atrial Mechanics

The left atrium (LA) acts as a booster pump during late diastole, generating the Doppler transmitral A wave and contributing incrementally to left ventricular (LV) filling. However, after volume loading and in certain disease states, LA contraction fills the LV less effectively, and retrograde flow (i.e., the Doppler Ar wave) into the pulmonary veins increases. The purpose of this study was to provide an energetic analysis of LA contraction to clarify the mechanisms responsible for changes in forward and backward flow. Wave intensity analysis was performed at the mitral valve and a pulmonary vein orifice. As operative LV stiffness increased with progressive volume loading, the reflection coefficient (i.e., energy of reflected wave/energy of incident wave) also increased. This reflected wave decelerated the forward movement of blood through the mitral valve and was transmitted through the LA, accelerating retrograde blood flow in the pulmonary veins. Although total LA work increased with volume loading, the forward hydraulic work decreased and backward hydraulic work increased. Thus wave reflection due to increased LV stiffness accounts for the decrease in the A wave and the increase in the Ar wave measured by Doppler.

Wave intensity analysis and the development of the reservoir–wave approach

2009 ◽  
Vol 47 (2) ◽  
pp. 221-232 ◽  
Author(s):  
John V. Tyberg ◽  
Justin E. Davies ◽  
Zhibin Wang ◽  
William A. Whitelaw ◽  
Jacqueline A. Flewitt ◽  
...  
Keyword(s):  
Wave Intensity ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Wave Approach

Wave speed in human coronary arteries is not influenced by microvascular vasodilation: implications for wave intensity analysis

2014 ◽  
Vol 109 (2) ◽  
Author(s):  
M. Cristina Rolandi ◽  
Kalpa Silva ◽  
Matthew Lumley ◽  
Timothy P. E. Lockie ◽  
Brian Clapp ◽  
...  
Keyword(s):  
Coronary Arteries ◽  
Wave Speed ◽  
Wave Intensity ◽  
Intensity Analysis ◽  
Wave Intensity Analysis

scholarly journals Development and Validation of a New Adenosine-Independent Index of Stenosis Severity From Coronary Wave–Intensity Analysis

2012 ◽  
Vol 59 (15) ◽  
pp. 1392-1402 ◽  
Author(s):  
Sayan Sen ◽  
Javier Escaned ◽  
Iqbal S. Malik ◽  
Ghada W. Mikhail ◽  
Rodney A. Foale ◽  
...  
Keyword(s):  
Wave Intensity ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Stenosis Severity ◽  
Development And Validation

Abstract 16131: Novel Magnetic Resonance Wave Intensity Analysis in Pulmonary Hypertension

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Michael A Quail ◽  
Daniel S Knight ◽  
Jennifer A Steeden ◽  
Liesbeth Taelman ◽  
Shahin Moledina ◽  
...  
Keyword(s):  
Pulmonary Hypertension ◽  
Pulmonary Arteries ◽  
Wave Intensity ◽  
Healthy Controls ◽  
Intensity Analysis ◽  
Wave Intensity Analysis ◽  
Resonance Wave ◽  
Golden Angle ◽  
Significant Difference ◽  
Pressure And Velocity Measurements

Background: Pathological pulmonary wave reflections (WR) are a potential hemodynamic biomarker for pulmonary hypertension (PH). WR can be quantified using wave intensity analysis (WIA), typically utilizing simultaneous invasive pressure and velocity measurements. In this study we reformulated WIA to use CMR area and flow to measure reflections non-invasively. We hypothesized that this method could detect differences in WR in PH patients compared to healthy controls and could also differentiate certain PH subtypes. Methods: 20 patients with PH (35% CTEPH), mean age 54years (75% female) and 10 healthy controls, 47years (60% female) were recruited. Branch pulmonary artery (PA) flow volume (Q) and area curves (A) were used to measure wave intensity ( dI ), defined as, dI =[[Unable to Display Character: &#8710;]]Ax[[Unable to Display Character: &#8710;]]Q and dI ± =± c /4 [[[Unable to Display Character: &#8710;]]A± [[Unable to Display Character: &#8710;]]Q/ c ] 2 , where c =wave-speed. Data were acquired using a retrospectively gated, respiratory navigated, golden-angle, 10.5ms temporal resolution, phase-contrast MR sequence. All patients also underwent right heart cardiac catheterization for pressure and vascular resistance (PVR) measurement, median interval 6 days (IQR 2-11days). The presence of proximal clot in CTEPH patients was determined from contemporaneous CT/angiographic data. Results: A backwards-travelling compression wave (BCW) was present in both left and right PAs of all PH patients, but was absent in all controls ( p =6e -8 ). A backwards-travelling expansion/suction wave was present in the 19/20 branch PAs of controls, and only 4/40 PAs in patients ( p < 0.0001). The area under the BCW was associated with a sensitivity of 100% (95% CI 63-100%) and specificity of 91% (95% CI 75-98%) for the presence of clot in the proximal pulmonary arteries of patients with CTEPH. Conclusions: Noninvasive pulmonary WIA accurately delineates pulmonary vascular health and disease. The main findings of this study were: i) There was a significant difference in WIA metrics between patients and controls, in particular, the presence of a BCW was specifically associated with the presence of PH; and ii) The magnitude of the BCW area showed discriminatory capacity for the presence of proximal PA clot in patients with CTEPH. We believe that these results demonstrate that WIA could be used in the non-invasive assessment of PH.

Sign in / Sign up

Export Citation Format

Share Document