Noninvasive iPhone Measurement of Left Ventricular Ejection Fraction Using Intrinsic Frequency Methodology.

OBJECTIVE: The study is based on previously reported mathematical analysis of arterial waveform that extracts hidden oscillations in the waveform that we called intrinsic frequencies. The goal of this clinical study was to compare the accuracy of left ventricular ejection fraction derived from intrinsic frequencies noninvasively versus left ventricular ejection fraction obtained with cardiac MRI, the most accurate method for left ventricular ejection fraction measurement. DESIGN: After informed consent, in one visit, subjects underwent cardiac MRI examination and noninvasive capture of a carotid waveform using an iPhone camera (The waveform is captured using a custom app that constructs the waveform from skin displacement images during the cardiac cycle.). The waveform was analyzed using intrinsic frequency algorithm. SETTING: Outpatient MRI facility. SUBJECTS: Adults able to undergo MRI were referred by local physicians or self-referred in response to local advertisement and included patients with heart failure with reduced ejection fraction diagnosed by a cardiologist. INTERVENTIONS: Standard cardiac MRI sequences were used, with periodic breath holding for image stabilization. To minimize motion artifact, the iPhone camera was held in a cradle over the carotid artery during iPhone measurements. MEASUREMENTS AND MAIN RESULTS: Regardless of neck morphology, carotid waveforms were captured in all subjects, within seconds to minutes. Seventy-two patients were studied, ranging in age from 20 to 92 years old. The main endpoint of analysis was left ventricular ejection fraction; overall, the correlation between ejection fraction-iPhone and ejection fraction-MRI was 0.74 (r = 0.74; p < 0.0001; ejection fraction-MRI = 0.93 × [ejection fraction-iPhone] + 1.9). CONCLUSIONS: Analysis of carotid waveforms using intrinsic frequency methods can be used to document left ventricular ejection fraction with accuracy comparable with that of MRI. The measurements require no training to perform or interpret, no calibration, and can be repeated at the bedside to generate almost continuous analysis of left ventricular ejection fraction without arterial cannulation.

Intrinsic Frequency Analysis and Fast Algorithms.

Intrinsic Frequency (IF) has recently been introduced as an ample signal processing method for analyzing carotid and aortic pulse pressure tracings. The IF method has also been introduced as an effective approach for the analysis of cardiovascular system dynamics. The physiological significance, convergence and accuracy of the IF algorithm has been established in prior works. In this paper, we show that the IF method could be derived by appropriate mathematical approximations from the Navier-Stokes and elasticity equations. We further introduce a fast algorithm for the IF method based on the mathematical analysis of this method. In particular, we demonstrate that the IF algorithm can be made faster, by a factor or more than 100 times, using a proper set of initial guesses based on the topology of the problem, fast analytical solution at each point iteration, and substituting the brute force algorithm with a pattern search method. Statistically, we observe that the algorithm presented in this article complies well with its brute-force counterpart. Furthermore, we will show that on a real dataset, the fast IF method can draw correlations between the extracted intrinsic frequency features and the infusion of certain drugs.

Artificial Intelligence Estimation of Carotid-Femoral Pulse Wave Velocity using Carotid Waveform.

In this article, we offer an artificial intelligence method to estimate the carotid-femoral Pulse Wave Velocity (PWV) non-invasively from one uncalibrated carotid waveform measured by tonometry and few routine clinical variables. Since the signal processing inputs to this machine learning algorithm are sensor agnostic, the presented method can accompany any medical instrument that provides a calibrated or uncalibrated carotid pressure waveform. Our results show that, for an unseen hold back test set population in the age range of 20 to 69, our model can estimate PWV with a Root-Mean-Square Error (RMSE) of 1.12 m/sec compared to the reference method. The results convey the fact that this model is a reliable surrogate of PWV. Our study also showed that estimated PWV was significantly associated with an increased risk of CVDs.

Accuracy of a Novel Handheld Wireless Platform for Detection of Cardiac Dysfunction in Anthracycline-Exposed Survivors of Childhood Cancer.

Purpose: Childhood cancer survivors are at risk for anthracycline-related cardiac dysfunction, often developing at a time when they are least engaged in long-term survivorship care. New paradigms in survivorship care and chronic disease screening are needed in this population. We compared the accuracy of a novel handheld mHealth platform (Vivio) as well as echocardiography for assessment of cardiac function [left ventricular ejection fraction (EF)] in childhood cancer survivors with cardiac magnetic resonance (CMR) imaging (reference).Experimental Design: Cross-sectional study design was used. Concurrent evaluation of EF was performed using Vivio, two-dimensional (2D) echocardiography, and CMR. Differences in mean EF (2D echocardiography vs. CMR; Vivio vs. CMR) were compared using Bland-Altman plots. Linear regression was used to evaluate proportional bias.Results: A total of 191 consecutive survivors participated [50.7% female; median time from diagnosis: 15.8 years (2-44); median anthracycline dose: 225 mg/m2 (25-642)]. Echocardiography overestimated mean EF by 4.9% (P < 0.001); linear regression analysis confirmed a proportional bias, when compared with CMR (t = 3.1, P < 0.001). There was no difference between mean EF derived from Vivio and from CMR (-0.2%, P = 0.68). The detection of cardiac dysfunction via echocardiography was poor when compared with CMR [Echo EF < 45% (sensitivity 14.3%), Echo EF < 50% (sensitivity 28.6%)]. Sensitivity was substantially better for Vivio-based measurements [EF < 45% or EF < 50% (sensitivity 85.7%)].Conclusions: This accessible technology has the potential to change the day-to-day practice of clinicians caring for the large number of patients diagnosed with cardiac dysfunction and heart failure each year, allowing real-time monitoring and management of their disease without the lag-time between imaging and interpretation of results. Clin Cancer Res; 24(13); 3119-25. ©2018 AACR.

A non-linear data mining parameter selection algorithm for continuous variables.

In this article, we propose a new data mining algorithm, by which one can both capture the non-linearity in data and also find the best subset model. To produce an enhanced subset of the original variables, a preferred selection method should have the potential of adding a supplementary level of regression analysis that would capture complex relationships in the data via mathematical transformation of the predictors and exploration of synergistic effects of combined variables. The method that we present here has the potential to produce an optimal subset of variables, rendering the overall process of model selection more efficient. This algorithm introduces interpretable parameters by transforming the original inputs and also a faithful fit to the data. The core objective of this paper is to introduce a new estimation technique for the classical least square regression framework. This new automatic variable transformation and model selection method could offer an optimal and stable model that minimizes the mean square error and variability, while combining all possible subset selection methodology with the inclusion variable transformations and interactions. Moreover, this method controls multicollinearity, leading to an optimal set of explanatory variables.

On the convergence and accuracy of the cardiovascular intrinsic frequency method.

In this paper, we analyse the convergence, accuracy and stability of the intrinsic frequency (IF) method. The IF method is a descendant of the sparse time frequency representation methods. These methods are designed for analysing nonlinear and non-stationary signals. Specifically, the IF method is created to address the cardiovascular system that by nature is a nonlinear and non-stationary dynamical system. The IF method is capable of handling specific nonlinear and non-stationary signals with less mathematical regularity. In previous works, we showed the clinical importance of the IF method. There, we showed that the IF method can be used to evaluate cardiovascular performance. In this article, we will present further details of the mathematical background of the IF method by discussing the convergence and the accuracy of the method with and without noise. It will be shown that the waveform fit extracted from the signal is accurate even in the presence of noise.

Intrinsic Frequency and the Single Wave Biopsy: Implications for Insulin Resistance.

Insulin resistance is the hallmark of classical type II diabetes. In addition, insulin resistance plays a central role in metabolic syndrome, which astonishingly affects 1 out of 3 adults in North America. The insulin resistance state can precede the manifestation of diabetes and hypertension by years. Insulin resistance is correlated with a low-grade inflammatory condition, thought to be induced by obesity as well as other conditions. Currently, the methods to measure and monitor insulin resistance, such as the homeostatic model assessment and the euglycemic insulin clamp, can be impractical, expensive, and invasive. Abundant evidence exists that relates increased pulse pressure, pulse wave velocity (PWV), and vascular dysfunction with insulin resistance. We introduce a potential method of assessing insulin resistance that relies on a novel signal-processing algorithm, the intrinsic frequency method (IFM). The method requires a single pulse pressure wave, thus the term " wave biopsy."

Intrinsic frequency for a systems approach to haemodynamic waveform analysis with clinical applications.

The reductionist approach has dominated the fields of biology and medicine for nearly a century. Here, we present a systems science approach to the analysis of physiological waveforms in the context of a specific case, cardiovascular physiology. Our goal in this study is to introduce a methodology that allows for novel insight into cardiovascular physiology and to show proof of concept for a new index for the evaluation of the cardiovascular system through pressure wave analysis. This methodology uses a modified version of sparse time-frequency representation (STFR) to extract two dominant frequencies we refer to as intrinsic frequencies (IFs; ω1 and ω2). The IFs are the dominant frequencies of the instantaneous frequency of the coupled heart + aorta system before the closure of the aortic valve and the decoupled aorta after valve closure. In this study, we extract the IFs from a series of aortic pressure waves obtained from both clinical data and a computational model. Our results demonstrate that at the heart rate at which the left ventricular pulsatile workload is minimized the two IFs are equal (ω1 = ω2). Extracted IFs from clinical data indicate that at young ages the total frequency variation (Δω = ω1 - ω2) is close to zero and that Δω increases with age or disease (e.g. heart failure and hypertension). While the focus of this paper is the cardiovascular system, this approach can easily be extended to other physiological systems or any biological signal.