Abstract: Implementations described herein discloses, a method of AI based video tagging for alarm management includes receiving, using a processor, a video stream, the video stream comprising a sequence of images for at least a portion of a patient, determining, using the processor, a physiological parameter for the patient based on the sequence of images, detecting, using machine learning, presence of a noise object and setting a interaction-flag to a positive value in response to detecting the noise object, comparing a quality level of the sequence of images with a threshold quality level, and modifying an alarm level based on the value of the interaction-flag and comparison of the quality level of the sequence of depth images with the threshold quality level.

Abstract: According to an aspect, a method for determining an augmented vital sign, such as heart rate or heart rate variability, includes obtaining signals from a patient when the patient is both active and inactive. An activity signal is generated from the first signal, and a physiological signal is generated from the second signal. An activity weight factor is calculated from the activity signal, and a vital sign signal is calculated from the physiological signal. A mapping from the activity signal to the vital sign aids the determination of the vital sign through a motion period. The augmented vital sign is a result of the combination of first and second values, including the product of the activity weight factor and an activity derived vital sign, and the product of the vital sign signal and the activity weight factor less than one.

Abstract: Implementations described herein disclose a method of monitoring motion of a patient, the method includes receiving, using a processor, a video stream, the video stream comprising a sequence of images for at least a portion of a patient, dividing the video stream into a plurality of temporal video sequences, each of the temporal video sequences having a plurality of frames each being apart from each other, generating a matrix of depth difference frames, and determining a machine learning (ML) input feature matrix based on the matrix of depth difference frames.

Abstract: Use of non-contact monitoring systems to monitor a subject (e.g., neonate, baby, infant, child) to determine various physiological characteristics of the subject. Physical characteristic that can be monitored, measured, and/or determined include length, volume, weight, BMI, and head circumference. Other characteristics such as reactions to stimulus, development of motor skills, smiling, and even development of language can also be monitored.

Abstract: A system for monitoring autoregulation includes an oxygen saturation sensor configured to obtain an oxygen saturation signal indicative of an oxygen saturation of a patient. The system also includes a controller having a processor configured to receive a blood pressure signal indicative of a blood pressure of the patient and the oxygen saturation signal, determine a change in the oxygen saturation signal and a change in the blood pressure signal over a period of time, and provide an indication that the patient's autoregulation is intact if the oxygen saturation changes by more than an oxygen saturation threshold and if the blood pressure changes by less than a blood pressure threshold during the period of time.

Abstract: The present invention relates to the field of medical monitoring, and, in particular, to non-contact detecting and monitoring of patient breathing. Systems, methods, and computer readable media are described for calculating a change in depth of a region of interest (ROI) on a patient and assigning one or more visual indicators to at least a portion of a graphic based on the calculated changes in depth and/or based on a tidal volume signal generated for the patient. In some embodiments, the systems, methods, and/or computer readable media can display the visual indicators overlaid onto at least the portion in real-time and/or can display the tidal volume signal in real-time. The systems, methods, and/or computer readable media can trigger an alert and/or an alarm when a breathing abnormality is detected.

Abstract: In some examples, a computing system tracks, across a plurality of predictions, prediction performance of a first oxygen saturation prediction model used by one or more patient monitoring devices by comparing a respective prediction made by the first oxygen saturation prediction model to a corresponding ground truth. The computing system determines whether the prediction performance of the first oxygen saturation prediction model meets a performance metric, wherein the performance metric includes an accuracy level, a specificity level, a sensitivity level, or any combination thereof. The computing system may, in response to determining that the prediction performance of the first oxygen saturation prediction model does not meet the performance metric, cause the one or more patient monitoring devices to switch to a second oxygen saturation prediction model to predict future oxygen saturation levels of one or more patients.

Abstract: The present disclosure relates to the field of medical monitoring, and, in particular, to non-contact detecting and monitoring of patient breathing. Systems, methods, and computer readable media are described for calculating a change in depth of regions in one or more regions of interest (ROI's) on a patient and assigning one or more visual indicators to the regions based on the calculated changes in depth of the regions over time. In some embodiments, one or more breathing parameter signals corresponding to the regions can be generated and/or analyzed. In these and other embodiments, the one or more visual indicators can be displayed overlaid onto the regions in real-time. In these and still other embodiments, the systems, methods, and/or computer readable media (i) can display one or more generated breathing parameter signals in real-time and/or (ii) can trigger an alert and/or an alarm when a breathing abnormality is detected.

Abstract: Implementations described herein disclose a method of AI-based video tagging for alarm management including receiving, using a processor, a video stream, the video stream comprising a sequence of images for at least a portion of a patient; determining, using the processor, a physiological parameter for the patient based on the sequence of images, detecting, using machine learning, the presence of a noise object and setting an interaction-flag to a positive value in response to detecting the noise object; comparing a quality level of the sequence of images with a threshold quality level; and modifying an alarm level based on the value of the interaction-flag and comparison of the quality level of the sequence of depth images with the threshold quality level.

Abstract: In some examples, a method including receiving, from an image capture device, a sequence of images of an eye region of a patient; determining, using processing circuitry, a motion of a feature within the eye region based on the received sequence of images; and determining, using the processing circuitry, a depth of anesthesia of the patient based on the determined motion is disclosed.

Abstract: A system for monitoring autoregulation may include processing circuitry configured to receive a blood pressure signal indicative of an acquisition blood pressure of a patient at an acquisition site and an oxygen saturation signal indicative of an oxygen saturation of the patient. The processing circuitry may determine an altered blood pressure value indicative of a reference blood pressure of the patient at a reference site based on the blood pressure signal. The altered blood pressure value may enable a more accurate subsequent determination of a value indicative of the autoregulation status of the patient compared to an unaltered blood pressure value. In some examples, the processing circuitry may provide a signal indicative of the autoregulation status of the patient to an output device to enable a clinician to monitor the autoregulation status of the patient.

Abstract: The disclosed technology qualifies sensor alignment relative to a patient environment by determining a respiratory region of the patient, detecting, by the sensor, sensor data including a plurality of distances between a position of the sensor and the respiratory region, generating, based at least in part on the detected sensor data, an aggregate alignment metric, determining that the aggregate alignment metric satisfies a misalignment condition, classifying a characteristic of misalignment of the sensor relative to the determined respiratory region at least partially based on the satisfaction of the misalignment condition, and generating an instruction to provide a misalignment notification based at least partially on the classified characteristic of misalignment.

Abstract: The present disclosure relates to the field of medical monitoring, and, in particular, to non-contact detecting and monitoring of patient breathing. Systems, methods, and computer readable media are described for calculating a change in depth of regions in one or more regions of interest (ROI's) on a patient and assigning one or more visual indicators to the regions based on the calculated changes in depth of the regions over time. In some embodiments, one or more breathing parameter signals corresponding to the regions can be generated and/or analyzed. In these and other embodiments, the one or more visual indicators can be displayed overlaid onto the regions in real-time. In these and still other embodiments, the systems, methods, and/or computer readable media (i) can display one or more generated breathing parameter signals in real-time and/or (ii) can trigger an alert and/or an alarm when a breathing abnormality is detected.

Abstract: In some examples, a method includes receiving a signal indicative of a blood pressure of a patient and identifying at least one first portion of the signal comprising a first characteristic of the signal exceeding a first threshold. The method also includes identifying at least one first portion of the signal comprising a second characteristic of the signal exceeding a second threshold, the first characteristic being different than the second characteristic. The method further includes determining a filtered signal indicative of the blood pressure of the patient by excluding the at least one first portion and the at least one second portion from the signal. The method includes determining a set of mean arterial pressure values based on the filtered signal and determining an autoregulation status of the patient based on the set of mean arterial pressure values.

Abstract: A system for detecting and identifying sleep apnea, such as obstructive sleep apnea, that includes a non-contact patient monitoring system and a pulse oximetry system. The methods utilize respiratory parameters (e.g., respiration rate, respiration volume) from the non-contact patient monitoring system to determine a significant reduction in or absence of the patient's respiration. The methods also utilize cardiological information (e.g., pulse) from a pulse oximetry system to determine intrathoracic pressure increases from various modulations of the PPG signal during the patient's respiration cycle.

Abstract: Implementations described herein disclose a method of classifying oxygen level desaturation events. In one implementation, the method includes receiving input signal sequences, the input signals indicative of a physiological condition of a patient, generating an input sequence of oxygen saturation levels based on the input signal sequence, comparing the input sequence of oxygen saturation levels to a desaturation alarm threshold to determine a desaturation event, generating an input feature matrix based on at least one of the input signal sequences and the input sequence of oxygen saturation levels, and classifying based on the input feature matrix, using a neural network, the desaturation event being a severe desaturation event (SDE) or a non-severe desaturation event (non-SDE).

Abstract: The present invention relates to the field of medical monitoring, and in particular non-contact monitoring and communication with other medical monitoring devices. Systems and methods are described for receiving a video signal of a medical monitoring device that is outputting a light signal, identifying the light signal emitted by the medical monitoring device from the video signal, decoding information from the light signal, and determining a communication from the decoded information related to a patient being monitored or the medical monitoring device itself.

Abstract: In some examples, a device includes a memory configured to store a first relationship between a blood pressure and another physiological parameter of a patient, the first relationship being indicative of cerebral autoregulation of the patient. The device also includes processing circuitry configured to receive first and second signals indicative of the blood pressure and the physiological parameter, respectively, of a patient. The processing circuitry is also configured to determine an expected value and an actual value of the physiological parameter at a particular blood pressure value of the first physiological signal. The processing circuitry is configured to determine, based on a difference between the actual value and the expected value, and store, in the memory, a second relationship between the blood pressure and the physiological parameter, the second relationship being indicative of a change in the cerebral autoregulation of the patient from the first relationship.

Abstract: An example system includes a thermal camera, a memory, and processing circuitry coupled to the thermal camera and the memory. The processing circuitry is configured to acquire a core temperature of a patient and acquire a first thermal image associated with the patient. The processing circuitry is configured to determine, based on the first thermal image, a first sensed temperature of a location associated with the patient. The processing circuitry is configured to determine a core temperature delta between the core temperature and the first sensed temperature. The processing circuitry is configured to acquire a second thermal image associated with the patient. The processing circuitry is configured to determine, based on the second thermal image, a second sensed temperature. The processing circuitry is configured to determine, based on the second sensed temperature and the core temperature delta, a measure of the core temperature.

Abstract: Methods and systems are provided for determining fluid administration. The system may determine fluid administration based on the fluid responsiveness and regional oxygen saturation of a subject. The system may receive the fluid responsiveness and regional oxygen saturation from external sources or may determine one or both based on received physiological signals. In some embodiments, the system may determine whether to administer fluid based on the fluid responsiveness and regional oxygen saturation. In some embodiments, the system may determine the amount of fluid to administer based on the fluid responsiveness and regional oxygen saturation. In some embodiments, the system may determine the effectiveness of fluid administration. In some embodiments, the system may provide an indication of the determined fluid administration so that a care-giver can implement the appropriate fluid administration. In some embodiments, the system may control the fluid administration based on its determination.