University of Pittsburgh

Ervin Sejdic

Clifton W Callaway

Michael A Rothfuss

Michael L Gimbel

Salah Al-Zaiti

Marlin H Mickle

Mingui Sun

Amro El-Jaroudi

Joshua R Stachel

Zhi-Hong Mao

Justin H Hawks

James Coyle

Kara Nicole-Simms Bocan

Joshua Dudik

Murat Akcakaya

Disclosed herein are methods, systems, and devices for identifying increased likelihood of non-ST elevation myocardial infarction (NSTEMI) in a patient based on ECG data. The methods can include determining based on the ECG data that the patient lacks ST elevation (STE) and that the patient exhibits a ventricular repolarization dispersion (VRD) score that exceeds a predetermined threshold value. The VRD score can be based in part on a T wave complexity ratio that serves as a temporal marker of VRD for the patient. Other markers of spatial and time qualities of repolarization can also be included in the VRD score. An elevated VRD score in the absence of STE can indicate a likelihood of NSTEMI in the patient and a potential major adverse cardiac event.

Electrocardiographic identification of non-ST elevation ischemic events

A system and method for wirelessly and passively powering and/or interrogating an implanted stent using a touch probe assembly through a near-field electrical connection not over an air interface. The stent apparatus includes at least one stent member functioning as an antenna and an electronics module coupled to the at least one stent member. Also, a wirelessly and passively powered power meter for use with implanted stents. The power meter includes an electronics module coupled to a stent member, wherein the electronics module includes a programmable oscillator structured to generate an oscillating signal that is proportional to an amount of AC power received by the implantable stent apparatus power meter through the stent member.

Touch probe passively powered wireless stent antenna for implanted sensor powering and interrogation

A system for monitoring free flap patency includes transmit and receive transducers structured to be coupled to a blood vessel, and a plurality of circuitry modules structured to insonify a blood flow volume within the blood vessel and receive a scattered signal from the receive transducer, extract a baseband Doppler blood flow signal, V, from the scattered signal, extract a plurality of features from V, and classify the plurality of features and generate a binary signal based on the classification of the plurality of features, wherein the binary signal will have a first state responsive to the classification of the plurality of features indicating that a flow rate within the blood vessel is less than a predetermined level and a second state responsive to the classification of the plurality of features indicating the flow rate within the blood vessel is greater than or equal to the predetermined level.

System for automatic and early detection flap failure

A method of decoding a barcode includes capturing an image of the barcode, dividing the image of the barcode into a plurality of rows and columns, each column corresponding to one encoded character of the barcode, using a number of trained image classifiers on each row to determine a predicted character for each column of the row, for each column, determining an output character for the column based on each of the predicted characters associated with the column, and for each column, outputting the output character. Also, a system for decoding a barcode that implements the method.

System and method of decoding a barcode using machine learning

A method of classifying a swallow of a subject includes obtaining vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and using a computer implemented deep learning classifier to classify the swallow based on the vibration data. Also, a system for classifying a swallow of a subject includes a computing device implementing a deep learning classifier. The computing device includes a processor apparatus structured and configured to receive vibration data that is based on and indicative of a number of vibrations resulting from the swallow, and use the deep learning classifier to classify the swallow based on the vibration data. The deep learning classifier may comprise a single layer or a multi-layer Deep Belief network.

Deep learning for classification of swallows

A method of providing RF energy to a wireless transponder device includes outputting primary RF energy in a form wherein the primary RF energy comprises a plurality of RF bursts, with each consecutive pair of the RF bursts being separated by an associated time interval, and outputting secondary continuous wave RF energy in between each of the RF bursts of the primary RF energy during at least a portion of each of the associated time intervals. Also, a reader device implementing this method.

Growing community of inventors

Pittsburgh, PA, United States of America

Ervin Sejdic