Technion Research & Development Foundation Ltd

Yael Yaniv

Noam Keidar

Alex Bronstein

Yonatan Elul

Joseph M Leichner

Aviv Rosenberg

Evgene Konyukhov

Gal Eidelsztein

A method comprising: at a training stage, training a machine learning algorithm on a training set comprising: (i) Heart Rate Variability (HRV) parameters extracted from temporal beat activity samples, wherein at least some of said samples include a representation of a Ventricular Fibrillation (VF) event, (ii) labels associated with one of: a first period of time immediately preceding a VF event in a temporal beat activity sample, a second period of time immediately preceding the first period of time in a temporal beat activity sample, and all other periods of time in a temporal beat activity sample; at an inference stage, receiving, as input, a target HRV parameters representing temporal beat activity in a subject; and applying said machine learning algorithm to said target HRV parameters, to predict an onset time of a VF event in said subject.

Predicting ventricular fibrillation

A method comprising: receiving an image stream of a mammalian cardiac muscle cell; defining or having defined a region of interest (ROI) within said cell; calculating a fast Fourier transform (FFT) of said ROI; detecting peaks in said FFT; and determining at least one of sarcomere length, mitochondrial length, and mitochondrial width, based, at least in part, in said detected peaks.

Real-time mitochondrial dimension measurements

A method comprising: receiving a plurality of data segments each representing human cardiac activity; calculating, from each of said data segments, a first value representing a distribution of a heart rate variability (HRV) parameter; acquiring a signal representing cardiac activity in a patient; deriving a second value representing distribution of an HRV parameter in said signal; and indicating an atrial fibrillation (AF) event in said patient, when a difference between said first and second values is above a predetermined threshold.

Atrial fibrillation prediction using heart rate variability

A method for evaluating heart function, comprising receiving a digitized cardiac signal, computing a power spectral density (PSD) or multiscale entropy (MSE) of the digitized cardiac signal, and evaluating heart function based on the PSD or MSE is provided. Systems and computer program products for doing same are also provided.

Growing community of inventors

Haifa, Israel

Yael Yaniv