Defining Coronary Flow Patterns: Comprehensive Automation of Transthoracic Doppler Coronary Blood Flow

Establishing the longitudinal hemodynamic mapping framework for wearable-driven coronary digital twins

Understanding the evolving nature of coronary hemodynamics is crucial for early disease detection and monitoring progression. We require digital twins that mimic a patient's circulatory system by integrating continuous physiological data and computing hemodynamic patterns over months. Current models match clinical flow measurements but are limited to single heartbeats. To this end, we introduced the longitudinal hemodynamic mapping framework (LHMF), designed to tackle critical challenges: (1) computational intractability of explicit methods; (2) boundary conditions reflecting varying activity states; and (3) accessible computing resources for clinical translation. We show negligible error (0.0002-0.004%) between LHMF and explicit data of 750 heartbeats. We deployed LHMF across traditional and cloud-based platforms, demonstrating high-throughput simulations on heterogeneous systems. Additionally, we established LHMFC, where hemodynamically similar heartbeats are clustered to avoid redundant simulations, accurately reconstructing longitudinal hemodynamic maps (LHMs). This study captured 3D hemodynamics over 4.5 million heartbeats, paving the way for cardiovascular digital twins.

Computing pulsatile blood flow of coronary artery under incomplete boundary conditions

BACKGROUND

Accurate measurement of pulsatile blood flow in the coronary arteries enables coronary wave intensity analysis, which can serve as an indicator for assessing coronary artery physiology and myocardial viability. Computational fluid dynamics (CFD) methods integrating coronary angiography images and fractional flow reserve (FFR) offer a novel approach for computing mean coronary blood flow. However, previous methods neglect the inertial effect of blood flow, which may have great impact on pulsatile blood flow calculation. To improve the accuracy of pulsatile blood flow calculation, a novel CFD based method considering the inertia term is proposed.

METHODS

A flow resistance model based on Pressure-Flow vs.Time curves is proposed to model the resistance of the epicardial artery. The parameters of the flow resistance model can be fitted from the simulated pulsating flow rates and pressure drops of a specific mode. Then, pulsating blood flow can be calculated by combining the incomplete pressure boundary conditions under pulsating conditions which are easily obtained in clinic. Through simulation experiments, the effectiveness of the proposed method is validated in idealized and reconstructed 3D model of coronary artery. The impacts of key parameters for generating the simulated pulsating flow rates and pressure drops on the accuracy of pulsatile blood flow calculation are also investigated.

RESULTS

For the idealized model, the previously proposed Pressure-Flow model has a significant leading effect on the computed blood flow waveform in the moderate model, and this leading effect disappears with the increase of the degree of stenosis. The improved model proposed in this paper has no leading effect, the root mean square error (RMSE) of the proposed model is low (the left coronary mode:≤0.0160, the right coronary mode:≤0.0065) for all simulated models, and the RMSE decreases with an increase of stenosis. The RMSE is consistently small (≤0.0217) as the key parameters of the proposed method vary in a large range. It is verified in the reconstructed model that the proposed model significantly reduces the RMSE of patients with moderate stenosis (the Pressure-Flow model:≤0.0683, the Pressure-Flow vs.Time model:≤0.0297), and the obtained blood flow waveform has a higher coincidence with the simulated reference waveform.

CONCLUSIONS

This paper confirms that ignoring the effect of inertia term can significantly affect the accuracy of calculating pulsatile blood flow in moderate stenosis lesions, and the new method proposed in this paper can significantly improves the accuracy of calculating pulsatile blood flow in moderate stenosis lesions. The proposed method provides a convenient clinical method for obtaining pressure-synchronized blood flow, which is expected to facilitate the application of waveform analysis in the diagnosis of coronary artery disease.

Machine learning: a new era for cardiovascular pregnancy physiology and cardio-obstetrics research

The maternal cardiovascular system undergoes functional and structural adaptations during pregnancy and postpartum to support increased metabolic demands of offspring and placental growth, labor, and delivery, as well as recovery from childbirth. Thus, pregnancy imposes physiological stress upon the maternal cardiovascular system, and in the absence of an appropriate response it imparts potential risks for cardiovascular complications and adverse outcomes. The proportion of pregnancy-related maternal deaths from cardiovascular events has been steadily increasing, contributing to high rates of maternal mortality. Despite advances in cardiovascular physiology research, there is still no comprehensive understanding of maternal cardiovascular adaptations in healthy pregnancies. Furthermore, current approaches for the prognosis of cardiovascular complications during pregnancy are limited. Machine learning (ML) offers new and effective tools for investigating mechanisms involved in pregnancy-related cardiovascular complications as well as the development of potential therapies. The main goal of this review is to summarize existing research that uses ML to understand mechanisms of cardiovascular physiology during pregnancy and develop prediction models for clinical application in pregnant patients. We also provide an overview of ML platforms that can be used to comprehensively understand cardiovascular adaptations to pregnancy and discuss the interpretability of ML outcomes, the consequences of model bias, and the importance of ethical consideration in ML use.

Modeling cardiac microcirculation for the simulation of coronary flow and 3D myocardial perfusion

Accurate modeling of blood dynamics in the coronary microcirculation is a crucial step toward the clinical application of in silico methods for the diagnosis of coronary artery disease. In this work, we present a new mathematical model of microcirculatory hemodynamics accounting for microvasculature compliance and cardiac contraction; we also present its application to a full simulation of hyperemic coronary blood flow and 3D myocardial perfusion in real clinical cases. Microvasculature hemodynamics is modeled with a compliant multi-compartment Darcy formulation, with the new compliance terms depending on the local intramyocardial pressure generated by cardiac contraction. Nonlinear analytical relationships for vessels distensibility are included based on experimental data, and all the parameters of the model are reformulated based on histologically relevant quantities, allowing a deeper model personalization. Phasic flow patterns of high arterial inflow in diastole and venous outflow in systole are obtained, with flow waveforms morphology and pressure distribution along the microcirculation reproduced in accordance with experimental and in vivo measures. Phasic diameter change for arterioles and capillaries is also obtained with relevant differences depending on the depth location. Coronary blood dynamics exhibits a disturbed flow at the systolic onset, while the obtained 3D perfusion maps reproduce the systolic impediment effect and show relevant regional and transmural heterogeneities in myocardial blood flow (MBF). The proposed model successfully reproduces microvasculature hemodynamics over the whole heartbeat and along the entire intramural vessels. Quantification of phasic flow patterns, diameter changes, regional and transmural heterogeneities in MBF represent key steps ahead in the direction of the predictive simulation of cardiac perfusion.

Cloud Computing to Enable Wearable-Driven Longitudinal Hemodynamic Maps

Tracking hemodynamic responses to treatment and stimuli over long periods remains a grand challenge. Moving from established single-heartbeat technology to longitudinal profiles would require continuous data describing how the patient's state evolves, new methods to extend the temporal domain over which flow is sampled, and high-throughput computing resources. While personalized digital twins can accurately measure 3D hemodynamics over several heartbeats, state-of-the-art methods would require hundreds of years of wallclock time on leadership scale systems to simulate one day of activity. To address these challenges, we propose a cloud-based, parallel-in-time framework leveraging continuous data from wearable devices to capture the first 3D patient-specific, longitudinal hemodynamic maps. We demonstrate the validity of our method by establishing ground truth data for 750 beats and comparing the results. Our cloud-based framework is based on an initial fixed set of simulations to enable the wearable-informed creation of personalized longitudinal hemodynamic maps.

Development of artificial intelligence tools for invasive Doppler-based coronary microvascular assessment

Aims

Coronary flow reserve (CFR) assessment has proven clinical utility, but Doppler-based methods are sensitive to noise and operator bias, limiting their clinical applicability. The objective of the study is to expand the adoption of invasive Doppler CFR, through the development of artificial intelligence (AI) algorithms to automatically quantify coronary Doppler quality and track flow velocity.

Methods and results

A neural network was trained on images extracted from coronary Doppler flow recordings to score signal quality and derive values for coronary flow velocity and CFR. The outputs were independently validated against expert consensus. Artificial intelligence successfully quantified Doppler signal quality, with high agreement with expert consensus (Spearman's rho: 0.94), and within individual experts. Artificial intelligence automatically tracked flow velocity with superior numerical agreement against experts, when compared with the current console algorithm [AI flow vs. expert flow bias -1.68 cm/s, 95% confidence interval (CI) -2.13 to -1.23 cm/s, P < 0.001 with limits of agreement (LOA) -4.03 to 0.68 cm/s; console flow vs. expert flow bias -2.63 cm/s, 95% CI -3.74 to -1.52, P < 0.001, 95% LOA -8.45 to -3.19 cm/s]. Artificial intelligence yielded more precise CFR values [median absolute difference (MAD) against expert CFR: 4.0% for AI and 7.4% for console]. Artificial intelligence tracked lower-quality Doppler signals with lower variability (MAD against expert CFR 8.3% for AI and 16.7% for console).

Conclusion

An AI-based system, trained by experts and independently validated, could assign a quality score to Doppler traces and derive coronary flow velocity and CFR. By making Doppler CFR more automated, precise, and operator-independent, AI could expand the clinical applicability of coronary microvascular assessment.

Invasive or More Direct Measurements Can Provide an Objective Early-Stopping Ceiling for Training Deep Neural Networks on Non-invasive or Less-Direct Biomedical Data

Early stopping is an extremely common tool to minimize overfitting, which would otherwise be a cause of poor generalization of the model to novel data. However, early stopping is a heuristic that, while effective, primarily relies on ad hoc parameters and metrics. Optimizing when to stop remains a challenge. In this paper, we suggest that for some biomedical applications, a natural dichotomy of invasive/non-invasive measurements, or more generally proximal vs distal measurements of a biological system can be exploited to provide objective advice on early stopping. We discuss the conditions where invasive measurements of a biological process should provide better predictions than non-invasive measurements, or at best offer parity. Hence, if data from an invasive measurement are available locally, or from the literature, that information can be leveraged to know with high certainty whether a model of non-invasive data is overfitted. We present paired invasive/non-invasive cardiac and coronary artery measurements from two mouse strains, one of which spontaneously develops type 2 diabetes, posed as a classification problem. Examination of the various stopping rules shows that generalization is reduced with more training epochs and commonly applied stopping rules give widely different generalization error estimates. The use of an empirically derived training ceiling is demonstrated to be helpful as added information to leverage early stopping in order to reduce overfitting.

Prospective Assessment of Coronary Artery Flows Before and After Cardiopulmonary Bypass in Children With a Spectrum of Congenital Heart Disease

Background

Normative data for the effect of cardiopulmonary bypass (CPB) on coronary artery Doppler velocities by transesophageal echocardiography in paediatric patients with congenital heart disease (CHD) are lacking. The objective of the study was to prospectively examine the effects of CPB on coronary artery flow patterns by transesophageal echocardiography before and after CPB in children with CHD.

Methods

All cases undergoing CHD surgery at the Hospital for Sick Children, Toronto, were eligible. The excluded cases included Norwood operation, heart transplantation, or weight <2.5 kg. Coronary Dopplers and coronary flow reserve (CFR) for the right coronary artery (RCA) and left anterior descending (LAD) were obtained. Multivariable analyses using linear regression models were performed, adjusted for age and cross-clamp time.

Results

From May 2017 to June 2018, 69 children (median age at surgery: 0.7 years, interquartile range [IQR]: 0.4-3.7 years; median weight: 7.4 kg, IQR: 5.8-13.3 kg) were included. They were grouped into shunt lesions (N = 26), obstructive lesions (N = 26), transposition of the great arteries (N = 5), and single ventricle (N = 12). N = 39 (57%) were primary repairs, and 56 (81%) had 1 CPB run. For RCA and LAD peak velocities, there was an increase from pre- to post-CPB in RCA peak 39 cm/s (IQR: 30-54 cm/s) to 65 cm/s (IQR: 47-81 cm/s), P < 0.001, mean CFR 1.52 (IQR: 1.25-1.81), and LAD peak 49 cm/s (IQR: 39-60 cm/s) to 70 cm/s (IQR: 52-90 cm/s), P < 0.001, mean CFR 1.48 (IQR: 1.14-1.77).

Conclusions

Coronary flow velocities increase from pre- to post-CPB in congenital heart lesions. CFR is consistent across all lesions but is relatively low compared with the adult population.

Improvement of automated analysis of coronary Doppler echocardiograms

Coronary artery disease is the leading cause of heart disease, and while it can be assessed through transthoracic Doppler echocardiography (TTDE) by observing changes in coronary flow, manual analysis of TTDE is time consuming and subject to bias. In a previous study, a program was created to automatically analyze coronary flow patterns by parsing Doppler videos into a single continuous image, binarizing and separating the image into cardiac cycles, and extracting data values from each of these cycles. The program significantly reduced variability and time to complete TTDE analysis, but some obstacles such as interfering noise and varying video sizes left room to increase the program's accuracy. The goal of this current study was to refine the existing automation algorithm and heuristics by (1) moving the program to a Python environment, (2) increasing the program's ability to handle challenging cases and video variations, and (3) removing unrepresentative cardiac cycles from the final data set. With this improved analysis, examiners can use the automatic program to easily and accurately identify the early signs of serious heart diseases.