General Electric Company

Ge Medical Systems Information Technologies Gmbh

Brian Joseph Young

Matthew Lane Pemberton

David E Albert

Donald Brodnick

James M Gray

David G Hernke

Paul S Schluter

Robert T Wolfe

David Wayne Duckert

James Russel Peterson

Chiranjiv Singh

Kjell Kristoffersen

Joel Qiuzhen Xue

Gordon Ian Rowlandson

Joel Quizhen Xue

Mark Robert Kohls

John Edward Lorbiecki

Lawrence Elwood Murphy

Willi Kaiser

Martin Findeis

Long Yu

Richard Andrew Valiga

Sarah Alme

Alfred Lojewski

Rajeev Mandwal

Computer-implemented techniques for managing transactions of machine learning algorithm updates are described. In one embodiment, a computer-implemented is provided that comprises receiving, by a system operatively coupled to a processor, a request for an update to a machine learning model associated with a software program, wherein the request is received in accordance with a defined blockchain protocol, and wherein the request comprises model development data used in association with optimization of an instance of the machine learning model. The method further comprises, employing, by the system, a blockchain network to facilitate managing fulfillment of the request.

Transaction management of machine learning algorithm updates

A method of obtaining and analyzing ECG data from a patient or group of patients is disclosed. The ECG data is obtained from the patient at an acquisition device. Once the ECG data is obtained, the ECG data is transmitted to an analysis server that is operated by an analysis provider and is located remote from the location of the acquisition device. Along with the ECG data, acquisition parameters are transmitted to the analysis server. At the analysis server, one of a plurality of algorithms is selected to analyze the ECG data. If an abnormality is detected, the patient information is directed to a healthcare provider who can then contact the patient to schedule an appointment. Based upon the referral, a referral fee can be transferred from the healthcare provider to the analysis provider. The patient can be prompted to provide additional information and selections that dictate the level of analysis generated.

System and methods for qualification of ECG data for remote analysis

In one embodiment, an ECG monitoring system includes two or more electrodes configured to record cardiac potentials from a patient, at least one processor, and a rapid acquisition module executable on the at least one processor to: determine that an impedance of each electrode is less than an impedance threshold; record initial ECG lead data based on the cardiac potentials; determine that a noise level in each ECG lead of the initial ECG data is less than a noise threshold; start a recording timer once the noise level is below the noise threshold; record an ECG dataset while the noise level is maintained below the noise threshold until the recording timer reaches a predetermined test duration; store the ECG dataset and provide a completion alert.

System and method for rapid ECG acquisition

An electrocardiograph system including a monitoring device capable of receiving cardiac signals from electrodes attached to a patient in an alternative electrode configuration, wherein the alternative electrode configuration is one of a predetermined set of known electrode configurations that differs from a default configuration. The system further includes an analysis module configured to analyze the cardiac signals to detect that the electrodes are attached to the patient in an electrode configuration that differs from the default configuration, and then request information from the user identifying the alternative electrode configuration from the predetermined set of known electrode configurations. The analysis module retrieves a set of criteria for assessing the cardiac signals based on the alternative electrode configuration, and automatically analyzes the cardiac signals based on the set of criteria for the alternative electrode configuration.

Method for ECG lead placement changes to be accurately accounted for

A method for processing ECG records from multiple patients for clinician overreading includes identifying an unread group of current ECG records from multiple patients awaiting clinician overreading. Each ECG record in the ungroup includes at least a current ECG data, a current waveform measurement, a current interpretative statement, and a serial comparison statement. A set of prioritization rules is applied with a processor to prioritize the current ECG records in the unread group into a prioritized order for clinician overreading based on at least one of the current waveform measurements, the current interpretive statements, and the serial comparison statements. The current ECG records are then presented in the prioritized order for clinician overreading.

System and method for processing ECG recordings from multiple patients for clinician overreading

A system for clinical decision support includes a database of previously-recorded waveform data from comparator-patients and a comparator module. The comparator module receives physiological waveform data for a patient and identifies a pattern in the patient's physiological waveform data, wherein the pattern accounts for a morphology and a rhythm of the patient's physiological waveform. The comparator module then compares the patient's physiological waveform data to the previously-recorded waveform data using a pattern recognition algorithm to detect the pattern in the previously-recorded waveform data to identify one or more matches. The comparator module further generates a result set based on the one or more matches.

System and method for clinical decision support

A method of directing positioning of ECG electrodes on a patient includes receiving at a processor an image of a patient from a camera of an augmented reality device. The processor analyzes the image for anatomical landmarks on the patient and generates an overlay image. The overlay image is shown over the real time image of the patient on the augmented reality device. The overlay image includes visual indicators of the desired electrode placement. The method further includes determining whether the actual location of each of the electrodes is correct and provides information on the augmented reality device as to whether the electrodes and lead placement is correct. An image of the electrode placement is stored with the ECG measurements, which can be used to verify correct electrode placement and to confirm consistent electrode placement over serial measurements. The augmented reality device allows for gesture control by the clinician.

Method and system using augmentated reality for positioning of ECG electrodes

A method of analyzing electrocardiograph (ECG) data includes receiving a first representative ECG of a patient and isolating a first principal component, a second principal component, and a third principal component of the first representative ECG. The principal components are isolated by selecting a portion of the first representative ECG relating to depolarization, calculating a covariance matrix based on the portion of the first representative ECG, conducting a principal component analysis of the covariance matrix, and selecting a first component of the principal component analysis as the first principal component, the second component of the principal component analysis as the second principal component, and the third component of the principal component analysis as the third principal component. A depolarization subspace is then formed based on the first principal component, second principal component, and the third principal component of the first representative ECG.

Method and apparatus for comparing and visualizing serial ECG data

A method and system for electrocardiographic monitoring includes receiving cardiac signals recorded from electrodes attached to a patient according to a known electrode configuration and determining the known electrode configuration. The cardiac signal is then automatically analyzed based on the alternative electrode configuration. In one embodiment, the method includes acquiring a cardiac signal through electrodes connected to the patient according to a known electrode configuration and analyzing the cardiac signal to detect whether the known electrode configuration deviates from a standard 12 lead ECG configuration. If a deviation is detected, then an estimated electrode configuration is determined for the electrodes connected to the patient and the estimated electrode configuration is presented to a user. Confirmation information is received from the user regarding whether the estimated electrode configuration is the known electrode configuration, and the physiological data is automatically analyzed based on the confirmation information.

A system for generating a diagnosis is disclosed herein. The system includes a controller, an electrocardiograph connected to the controller, and an ultrasound device connected to the controller. The electrocardiograph is configured to generate a diagnostic electrocardiogram. The controller is configured to generate a diagnosis based on data from the electrocardiograph or the ultrasound device.

System and method for generating a patient diagnosis

Devices and methods comprise or provide an ECG recording device containing a mailable base and electrode assembly and/or other means engageable with the base to receive ECG signals from a subject during a self-administered ECG examination. The devices and methods may also include a single-use or limited-use ECG recording device, in which the base is disposable or reusable or recyclable. In addition, the device may be self-contained, battery-operated, portable, disposable, mailable to a location remote from an ECG examination, provide feedback, indicate its method of use, including graphically depicting same, contain a finger cuff and/or sensor pad for receiving ECG signals, and/or contain a memory. Preferably, the base conforms to various body shapes and/or sizes, is made of flexible and/or semi-flexible material, and/or contains a receptor, such as sealable blood well. The device can also communicate the ECG signals to an ECG processing system, which can be remote from the ECG examinations and comprise wireless communications.

Devices and methods for self-administered ECG examinations

The system and method of the present application includes an ECG acquisition device having a USB connector for connecting the device to a host device and a patient connector for connecting the device to a patient with ECG leads. The ECG acquisition device of the present system further includes a processor and storage medium, a power management and brokering module, a USB communications control module, an ECG acquisition circuit, and a patient isolation module. Unlike prior art ECG acquisition systems, the system of the present application affords a truly portable ECG acquisition device that may be connected through the USB connector to any host device having software processing capabilities and a display. The ECG acquisition device auto-loads and runs ECG monitoring software onto the host device eliminating the need to install additional acquisition software and/or drivers to the host device, and allows the acquisition device to interface with a host device of varying platforms.

Portable USB electrocardiograph system and method

A monitoring system and method for monitoring signals from an implantable medical device are disclosed. The monitoring system and method include a monitor configured to detect a radio frequency artifact from the signals of the implantable medical device and circuitry for processing the radio frequency artifact from the signals of the implantable medical device.

Growing community of inventors

Wauwatosa, WI, United States of America

Brian Joseph Young