Characterizing the transient electrocardiographic signature of ischemic stress using Laplacian Eigenmaps for dimensionality reduction.

OBJECTIVE: Despite a long history of ECG-based monitoring of acute ischemia quantified by several widely used clinical markers, the diagnostic performance of these metrics is not yet satisfactory, motivating a data-driven approach to leverage underutilized information in the electrograms. This study introduces a novel metric for acute ischemia, created using a machine learning technique known as Laplacian eigenmaps (LE), and compares the diagnostic and temporal performance of the LE metric against traditional metrics. METHODS: The LE technique uses dimensionality reduction of simultaneously recorded time signals to map them into an abstract space in a manner that highlights the underlying signal behavior. To evaluate the performance of an electrogram-based LE metric compared to current standard approaches, we induced episodes of transient, acute ischemia in large animals and captured the electrocardiographic response using up to 600 electrodes within the intramural and epicardial domains. RESULTS: The LE metric generally detected ischemia earlier than all other approaches and with greater accuracy. Unlike other metrics derived from specific features of parts of the signals, the LE approach uses the entire signal and provides a data-driven strategy to identify features that reflect ischemia. CONCLUSION: The superior performance of the LE metric suggests there are underutilized features of electrograms that can be leveraged to detect the presence of acute myocardial ischemia earlier and more robustly than current methods. SIGNIFICANCE: The earlier detection capabilities of the LE metric on the epicardial surface provide compelling motivation to apply the same approach to ECGs recorded from the body surface.

A STATISTICAL APPROACH TO INCORPORATE MULTIPLE ECG OR EEG RECORDINGS WITH ARTIFACTUAL VARIABILITY INTO INVERSE SOLUTIONS.

Inverse methods for localization and characterization of cardiac and brain sources from ECG and EEG signals are notoriously ill-conditioned and thus sensitive to SNR in the measurements. Multiple recordings of the same underlying phenomenon are often available, but are contaminated by unmodeled correlated noise such as heart motion from respiration or superposition of atrial activation or on-going EEG in the case of inter-ictal spikes or evoked response in EEG. We address here the open question of how best to incorporate these multiple recordings, comparing standard ensemble averaging, a multichannel non-linear spline-based average designed to be less sensitive to timing variations from motion or modulation, and a probalistic inverse incorporating a data-driven model of the noise correlation and using all recordings jointly. Results are tested on localizations of clincally recorded 120 lead ECGs during ventricular pacing.

COMBINED DELAY AND GRAPH EMBEDDING OF EPILEPTIC DISCHARGES IN EEG REVEALS COMPLEX AND RECURRENT NONLINEAR DYNAMICS.

The dynamical structure of the brain's electrical signals contains valuable information about its physiology. Here we combine techniques for nonlinear dynamical analysis and manifold identification to reveal complex and recurrent dynamics in interictal epileptiform discharges (IEDs). Our results suggest that recurrent IEDs exhibit some consistent dynamics, which may only last briefly, and so individual IED dynamics may need to be considered in order to understand their genesis. This could potentially serve to constrain the dynamics of the inverse source localization problem.

TIME INVARIANT MULTI ELECTRODE AVERAGING FOR BIOMEDICAL SIGNALS.

One of the biggest challenges in averaging ECG or EEG signals is to overcome temporal misalignments and distortions, due to uncertain timing or complex non-stationary dynamics. Standard methods average individual leads over a collection of epochs on a time-sample by time-sample basis, even when multi-electrode signals are available. Here we propose a method that averages multi electrode recordings simultaneously by using spatial patterns and without relying on time or frequency.

MANIFOLD LEARNING FOR ANALYSIS OF LOW-ORDER NONLINEAR DYNAMICS IN HIGH-DIMENSIONAL ELECTROCARDIOGRAPHIC SIGNALS.

The dynamical structure of electrical recordings from the heart or torso surface is a valuable source of information about cardiac physiological behavior. In this paper, we use an existing data-driven technique for manifold identification to reveal electrophysiologically significant changes in the underlying dynamical structure of these signals. Our results suggest that this analysis tool characterizes and differentiates important parameters of cardiac bioelectric activity through their dynamic behavior, suggesting the potential to serve as an effective dynamic constraint in the context of inverse solutions.