A method of detecting changes in blood flow in a head of a subject includes measuring a value of a parameter of a cardiac bioelectrical signal at a scalp area of the subject relative to a reference cardiac bioelectrical signal. The method also includes comparing the value of the measured parameter with a predetermined value of the parameter to determine any change in blood flow in the head of the subject. The determined change can be used to detect changes in perfusion in the brain of a subject for example, as a result of anti-coagulation medication used to dissolve a clot in a blood vessel of the brain of a subject who has experienced ischaemic stroke.

A method of detecting abnormalities in ECG signals by providing an ECG signal to a neural network, performing a first series of convolution operations to a first subset of layers and in a final layer, and determining a plurality of preliminary classification estimates, each preliminary classification estimate corresponding with a time segment of the ECG signal. Furthermore, determining input data for a second subset of layers of the neural network by concatenating the preliminary classification with the output of a layer of the first subset of layers that precedes the final layer of the first subset of layers. Within the second subset of layers of the neural network, performing a second series of convolution operations. In a final layer of the second subset, determining plurality of final classification estimates, each final classification estimate corresponding with a time segment of the ECG signal.

Described herein are methods, devices and system for determining whether an R-wave detection should be classified as a false R-wave detection due to T-wave oversensing (TWO) or P-wave oversensing (PWO). One such method includes comparing a specific morphological characteristic (e.g., peak amplitude) associated with the R-wave detection to the specific morphological characteristic associated with each R-wave detection in a first set of earlier detected R-wave detections to thereby determine whether first TWO or PWO morphological criteria are met, and in a second set of earlier detected R-wave detections to thereby determine whether second TWO or PWO morphological criteria are met, wherein the second set differs from the first set but may have some overlap with the first set. The method also includes determining whether to classify the R-wave detection as a false R-wave detection, based on whether one of the first or second TWO or PWO morphological criteria are met.

Wrist-wearable apparatuses that may be removed and used as a chest-applied cardiac device may include two chest electrodes on an inner surface of a strap (or strap regions), as well as two finger or more finger electrodes on the opposite side of the apparatus. The apparatus may be removed from the wrist and placed on a chest of a patient such that two electrodes are spaced at least five centimeters apart and in contact with the chest and held in place with two or more fingers to capture orthogonal cardiac signals that may be synthesized into a conventional 12-lead cardiac signal.

The process for classifying anesthetic depth includes: collecting of biological signals, conditioning of said signals, monitoring of activity of the central and autonomic systems, measurement of indexes and classification of patterns in anesthetic depth. The activity includes: i) Awake: Vigil—Ak. and recovery of verbal response—Rc. ii) Light Anesthesia: Light induction anesthesia—Li. Light recovery—Lr, Light dose, increase in drugs or patient movement (La), iii) General anesthesia: General anesthesia—Ga, one minute after the start of the surgery, and iv) Deep anesthesia: identification of the EEG burst-suppression pattern (BSP) associated with deep anesthesia.

Apparatuses, systems and methods are provided that may include a system for patient monitoring and defibrillation. The system may include at least two defibrillation electrodes. The system may further include a first unit for physiological monitoring of a patient, including ECG monitoring circuitry for monitoring ECG of the patient. The first unit may store CPR chest compression data. The system may further include a second unit, separate from the first unit, which may communicatively couple with the first unit, for providing defibrillation pulses to the patient. The second unit may include a processor, communicatively coupled with the at least two defibrillation electrodes, for providing defibrillation pulses to the patient via the at least two defibrillation electrodes.

Disclosed are a method and apparatus for visualizing an electrocardiogram using deep learning.

The present embodiment provides a method and apparatus for visualizing an electrocardiogram, the method and apparatus which analyze an electrocardiogram using a deep learning algorithm for accurate arrhythmia determination as a real-time operation algorithm for monitoring a bedridden patient in order to solve the manpower shortage of medical staff, and then visually output it in real time so that a visual help may be provided for medical staff.

The present invention relates to an electrocardiogram analysis matching support service system that supports timely and real-time analysis of an individual's electrocardiogram, and it is characterized in that it includes: a patient service app module that is installed and executed in a patient's mobile communication terminal, transmits an electrocardiogram measurement data received from a wearable electrocardiogram measurement device, requests for reading, and receives and displays the result of the reading; and a patient and medical staff matching server that reads the electrocardiogram measurement data transmitted from the patient service app module using a deep learning trained artificial intelligence network model, selects pre-registered medical staff according to the result of the reading, and supports reading the electrocardiogram measurement data.

A method including the steps of receiving a first signal sensed from a patient, receiving a first physiological signal sensed from the patient, and processing the first signal based at least on the first physiological signal to obtain a second signal that is a measurement of the patient's Heart Rhythm.

A method including the steps of receiving a first signal sensed from a patient, receiving a first physiological signal sensed from the patient, and processing the first signal based at least on the first physiological signal to obtain a second signal that is a measurement of the patient's Heart Rhythm.