Systems and methods for pacing cardiac conductive tissue are described. An embodiment of a medical system includes an electrostimulation circuit to generate His-bundle pacing (HBP) pulses to stimulate a His bundle, and a cardiac event detector to detect a His-bundle activity within a time window following an atrial activity. The cardiac event detector may use a cross-chamber blanking, or an adjustable His-bundle sensing threshold, to avoid or reduce over-sensing of far-field atrial activity and inappropriate inhibition of HBP therapy. The electrostimulation circuit may deliver HBP in the presence of the His-bundle activity. The system may further recognize the detected His-bundle activity as either a FFPW or a valid inhibitory event, and deliver or withhold HBP therapy based on the recognition of the His-bundle activity.

A medical device is configured to sense an electrical signal and determine that signal to noise criteria are met based on electrical signal segments stored in response to sensed electrophysiological events. The medical device is configured to determine an increased gain signal segment from one of the stored electrical signal segments in response to determining that the signal to noise criteria are met. The medical device determines a noise metric from the increased gain signal segment. The stored electrical signal segment associated with the increased gain signal segment may be classified as a noise segment in response to the noise metric meeting noise detection criteria.

A method of determining a fused sensor measurement is disclosed including: obtaining sensor measurements from sensors detecting a same type of physiological measurement; determining a signal quality index (SQI) of each sensor including determining an extent to which a sensor measurement differs from others among the sensor measurements obtained from each sensor; determining a weightage of each sensor based on the SQI of each sensor; and determining a fused sensor measurement from the plurality of sensors based on the weightage of each sensor and filtered sensor measurements of each sensor obtained from a Kalman filter operation. A vehicle safety system includes: a vehicle electronic control unit configured to: determine the sensor measurement extent, to determine the SQI of each sensor, determine the weightage of each sensor, determine the fused sensor measurement, determine the occupant's physiological condition, and if the physiological condition is abnormal, perform at least one vehicle operation.

A method of controlling a wearable device including a signal generator, two stimulation electrodes, and two sensing electrodes to monitor a level of edema of a subject, includes generating, by the generator, a signal that causes a current to flow between the stimulation electrodes and measuring an impedance between the sensing electrodes disposed on a skin of the subject at an interval of time during a testing period, thereby providing impedance measurements, validating each impedance measurement against a model set of impedance measurements, eliminating a measurement from the impedance measurements if the measurement fails the validating, thereby providing a validated sub-set of impedance measurements, converting each of the validated sub-set of impedance measurements to an edema index, thereby providing edema indices, averaging the edema indices and generating an average edema index for the testing period, and generating an alert depending on the average edema index.

Systems and methods for measuring vitals in accordance with embodiments of the invention are illustrated. One embodiment includes a method for measuring vital signs. The method includes steps for identifying regions of interest (ROIs) from video data of an individual, generating temporal waveforms from the ROIs, analyzing the generated temporal waveforms to extract vital sign measurements, and generating outputs based on the analyzed temporal waveforms.

A person support apparatus, such as a bed, stretcher, cot, recliner, or the like, includes an exit detection system having a plurality of force sensors that support the weight of an occupant positioned on a support surface and obstruction detection system having one or more obstruction sensors. The force sensors are part of an exit detection system that issues an alarm when the occupant exits, or is about to exit, the person support apparatus. The bed exit system can react to detection of an obstacle. The distribution of weight applied to the force sensors is used to determine if the occupant is about to exit the person support apparatus. Compensation is made to the exit detection system for changes in the weight distribution that are not caused by movement of the occupant. Such changes may be due to not only movement of the person support apparatus or components thereof, but obstacles encountered by the person support apparatus or components thereof.

A wearable device is provided. The wearable device includes a first sensor having a plurality of electrodes, and at least one processor electrically connected to the first sensor. The at least one processor may obtain a first electrocardiogram signal by using a first sensor in a state where the wearable device is worn on a user's body, obtain an electromyogram signal from the first electrocardiogram signal, obtain a second electrocardiogram signal by filtering the electromyogram signal from the first electrocardiogram signal, determine the wearing state of the wearable device on the basis of the intensity of the electromyogram signal and the quality of the second electrocardiogram signal, and output a guide on the wearing state on the basis of a determination result.

According to an aspect, there is provided a computer-implemented method for determining a heart rate of a subject, the method comprising: receiving data representing a signal generated by a pressure sensor configured to be placed on a suprasternal notch of a subject, the data representing a first component of the signal comprising respiratory information associated with the subject and/or a second component of the signal comprising cardiac information associated with the subject; determining, by applying a first algorithm to the data, a respiration parameter of the subject; applying at least one filter to the data to obtain first filtered data, the at least one filter comprising a first filter to attenuate the first component of the signal in the data based on the determined respiration parameter; and determining a heart rate of the subject by applying a second algorithm to the first filtered data.

An oximetry device sealed in a sheath directs a user to allow the oximetry device to make oximetry readings at a number of different tissue locations of a patient and average two or more of the oximetry readings by directing the lifts and placements of the oximetry device and sheath to and from the different tissue locations and detecting the lift and placements. The averages are generated and displayed on a display of the device for the oximetry readings if the lifts are made while use directions for the lifts are displayed on a display of the oximetry device. The averages are not generated if the lifts are not made while the user directions for the lifts are not displayed. The averages are simultaneously displayed with the oximetry readings which are instantaneous measurement for patient tissue.

A non-contact facial blood pressure measurement method based on 3D CNN is disclosed, which belongs to the technical field of computer vision. The method includes the following steps. S110: collecting an actual face video sample and training a blood pressure prediction model based on face images using 3D CNN neural network. S120: obtaining a face video in real time through a HD camera. S130: recognizing face key points in the face video obtained in S120 through dlib face recognition model, selecting a face region of interest, and extracting face images from the region. S140: performing a wavelet transform operation on the face images extracted in S130 to remove noise. S150: inputting seven consecutive frames of the face images into the 3D CNN blood pressure prediction model trained in S110 to obtain a blood pressure value of the measured person. The disclosure realizes non-contact facial blood pressure measurement.