An ECG monitoring device includes a vibration meter sensor unit including at least one vibration meter sensor attached to an instrument at which a person to be observed is positioned, and configured to acquire a vibration signal by detecting a vibration transmitted through the instrument in a non-contact or non-invasive method, a filter unit configured to extract a seismocardiography signal (“SCG signal”) generated by a heart vibration of the person to be observed by receiving the vibration signal and filtering a predetermined frequency band from the received vibration signal, and an ECG waveform acquisition unit including an artificial neural network learned in advance and configured to generate an electrocardiogram signal (“ECG signal”) corresponding to the applied SCG signal according to a learned method.

A system for achieving optimal sensor placement and enhanced signal quality for monitoring maternal and fetal activities is disclosed. The system includes a monitoring device and a computing unit. The monitoring device is configured for monitoring maternal and fetal activities and providing guidance to the user via the computing unit upon detecting a feature of interest. The monitoring device includes a plurality of sensors, a data acquisition and transmission unit, one or more reference electrodes, and a ground electrode. Based on personal data acquired using the computing unit, the system utilizes a statistical or machine learning model which incorporates one or more subsets of the personal data to determine the optimal sensor placement close to the fetal heart position. Following sensor placement, the monitoring device performs a signal quality assessment and selects the optimal sensors to ensure reliable information on maternal and fetal activities is obtained.

Systems and methods are provided for evaluating infranodal pacing is applied to a patient. Electrocardiogram (ECG) data representing the pacing is obtained from a set of electrodes as an ECG lead. A predictor value representing a frequency content a portion of the ECG lead is extracted. A fitness parameter is determined for the pacing from at least the predictor value. The fitness parameter represents a likelihood that the applied infranodal pacing will induce left ventricular dysfunction in the patient. The fitness parameter is displayed to a user at an associated display.

Systems and methods are provided for evaluating infranodal pacing is applied to a patient. Electrocardiogram (ECG) data representing the pacing is obtained from a set of electrodes as an ECG lead. A predictor value representing a frequency content a portion of the ECG lead is extracted. A fitness parameter is determined for the pacing from at least the predictor value. The fitness parameter represents a likelihood that the applied infranodal pacing will induce left ventricular dysfunction in the patient. The fitness parameter is displayed to a user at an associated display.

Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

Techniques are disclosed for using both feature delineation and machine learning to detect cardiac arrhythmia. A computing device receives cardiac electrogram data of a patient sensed by a medical device. The computing device obtains, via feature-based delineation of the cardiac electrogram data, a first classification of arrhythmia in the patient. The computing device applies a machine learning model to the received cardiac electrogram data to obtain a second classification of arrhythmia in the patient. As one example, the computing device uses the first and second classifications to determine whether an episode of arrhythmia has occurred in the patient. As another example, the computing device uses the second classification to verify the first classification of arrhythmia in the patient. The computing device outputs a report indicating that the episode of arrhythmia has occurred and one or more cardiac features that coincide with the episode of arrhythmia.

A smart ring includes a curved housing having a U-shape interior storing components including: a curved battery approximately conforming to the curved housing, a semi-flexible PCB approximately conforming to the curved housing and having mounted thereon: a motion sensor for generating motion data from physical perturbations of the smart ring, a memory for storing executable instructions, a transceiver for sending data to a client computer, a temperature sensor, and a processor for receiving motion data and performing executable instructions in response thereto, and a potting material disposed in the interior, forming an interior wall of the smart ring, wherein the potting material encapsulates the components and is substantially transparent to visible light, infrared light, and / or ultraviolet light.

A smart ring includes a curved housing having a U-shape interior storing components including: a curved battery approximately conforming to the curved housing, a semi-flexible PCB approximately conforming to the curved housing and having mounted thereon: a motion sensor for generating motion data from physical perturbations of the smart ring, a memory for storing executable instructions, a transceiver for sending data to a client computer, a temperature sensor, and a processor for receiving motion data and performing executable instructions in response thereto, and a potting material disposed in the interior, forming an interior wall of the smart ring, wherein the potting material encapsulates the components and is substantially transparent to visible light, infrared light, and / or ultraviolet light.

A system and method for non-invasively monitoring the hemodynamic state of a patient by determining on a beat-by-beat basis the ratio of lusitropic function to inotropic function as an index of myocardial well-being or pathology for use by clinicians in the hospital or by the patient at home. In one embodiment of the system a smartphone running an application program that is connected through the internet to the cloud processes electronic signals, first, from an electrocardiogram device monitoring electrical cardiac activity, and second, from a seismocardiogram device monitoring mechanical cardiac activity in order to determine such ratio as an instantaneous measurement of the hemodynamic state of the patient, including such states as sepsis, myocardial ischemia, and heart failure.

A system and method for non-invasively monitoring the hemodynamic state of a patient by determining on a beat-by-beat basis the ratio of lusitropic function to inotropic function as an index of myocardial well-being or pathology for use by clinicians in the hospital or by the patient at home. In one embodiment of the system a smartphone running an application program that is connected through the internet to the cloud processes electronic signals, first, from an electrocardiogram device monitoring electrical cardiac activity, and second, from a seismocardiogram device monitoring mechanical cardiac activity in order to determine such ratio as an instantaneous measurement of the hemodynamic state of the patient, including such states as sepsis, myocardial ischemia, and heart failure.