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: In some examples, a device includes processing circuitry configured to determine a set of correlation coefficient values for first and second physiological parameters. The processing circuitry is further configured to determine a metric of the correlation coefficient values for a first plurality of bins and for a second plurality of bins, wherein each bin of the first plurality has a first bin parameter and each bin of the second plurality of bins has a second bin parameter different than the first bin parameter. The processing circuitry is also configured to determine a composite estimate of a limit of autoregulation of the patient based on the metric for the first plurality of bins and the metric for the second plurality of bins. The processing circuitry is configured to determine an autoregulation status based on the composite estimate and output, for display via the display, an indication of the autoregulation status.

Abstract: A system for continuous non-invasive blood pressure monitoring may include processing circuitry configured to determine calibration data for a continuous non-invasive blood pressure model at a calibration point, receive, from an oxygen saturation sensing device, a PPG signal at a particular time subsequent to the calibration point, derive values of the set of metrics for the patient from the PPG signal, and determine, using the continuous non-invasive blood pressure model and based at least in part on inputting the calibration data determined at the calibration point, the values of the set of metrics, and an elapsed time at the particular time since the calibration point into the continuous non-invasive blood pressure model, a blood pressure of the patient at the particular time.

Abstract: Methods and systems for monitoring a patient's position using non-contact patient monitoring systems are described. In some embodiments, depth sensing cameras are used to obtain depth images of a patient, wherein data can be extracted from the depth images and processed in various ways to make a determination as to the patient's position, including monitoring when and how often a patient changes position. Various alarms systems can also be integrated into the systems and methods described herein in order to alert clinicians regarding, for example, patients moving too infrequently, patients moving too frequently, or patients moving into undesirable positions in view of the condition being treated. AI-based patient monitoring systems used for determining patient position are also described.

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: In some examples, a device includes processing circuitry configured to determine a set of correlation coefficient values for first and second physiological parameters. The processing circuitry is further configured to determine a metric of the correlation coefficient values for a first plurality of bins and for a second plurality of bins, wherein each bin of the first plurality has a first bin parameter and each bin of the second plurality of bins has a second bin parameter different than the first bin parameter. The processing circuitry is also configured to determine a composite estimate of a limit of autoregulation of the patient based on the metric for the first plurality of bins and the metric for the second plurality of bins. The processing circuitry is configured to determine an autoregulation status based on the composite estimate and output, for display via the display, an indication of the autoregulation status.

Abstract: In some examples, a system includes an oxygen saturation sensing device configured to sense an oxygen saturation level of a patient and processing circuitry. The processing circuitry may be configured to receive a signal indicative of the oxygen saturation level of the patient, determine that the signal indicates the oxygen saturation level is at or below a desaturation threshold, and in response to determining the oxygen saturation level of the patient is at or below the desaturation threshold, predict, using an oxygen saturation prediction model, whether the oxygen saturation level of the patient will increase above the desaturation threshold by the end of a predefined time period. In response to predicting that the oxygen saturation level of the patient will increase above the desaturation threshold by the end of the predefined time period, the processing circuitry refrains from outputting an indication of the patient experiencing an oxygen desaturation event.

Abstract: Processing circuitry may receive one or more signals of a patient. The processing circuitry may determine an autoregulation status of the patient based at least in part on the one or more signals. The processing circuitry may output, for display at an output device, a graphical user interface (GUI) that includes an indication of the autoregulation status of the patient and an indication of a lower limit of autoregulation (LLA) value, wherein the GUI does not include an indication of an upper limit of autoregulation (LLA) value.

Abstract: The present technology relates to the field of medical monitoring systems. Systems, methods, and computer readable media are described. In some embodiments, a truth data set and a sensor data set are accessed. The truth data set is associated with a plurality of test data acquired through a series of tests. The sensor data set is associated with a plurality of sensor data acquired from a medical monitoring device. A machine learning network associated with a medical monitoring system is trained based on the truth data set and the sensor data set.

Abstract: A patient monitoring system may include processing circuitry configured to receive an indication of a surgical event, obtain a nociception parameter of a patient, compare the nociception parameter of the patient to a nociception threshold to detect a nociception event, determine whether the surgical event corresponds to the nociception event, and in response to determinizing whether the surgical event corresponds to the nociception event, provide an indication to adjust an amount of analgesic administered to the patient.

Abstract: In some examples, a device includes sensing circuitry configured to receive one or more signals from a patient and processing circuitry configured to determine a plurality of autoregulation state values associated with a plurality of blood pressure values based on the one or more signals. The processing circuitry is further configured to determine that a first autoregulation state value of the plurality of autoregulation state values is anomalous based on other autoregulation state values of the plurality of autoregulation state values. The processing circuitry is also configured to modify the first autoregulation state value in response to determining that the first autoregulation state value is anomalous and determine an autoregulation status of the patient based on the plurality of autoregulation state values including the modified first autoregulation state value.

Abstract: In some examples, devices, systems, and techniques are configured to compensate for changes in sensed blood pressure due to issues such as blood pressure sensor movement. For example, processing circuitry of a device may determine a difference value between a first blood pressure value representative of a blood pressure at a first time and a second blood pressure value representative of the blood pressure at a second time. Responsive to determining that the difference value is greater than or equal to a threshold value, the processing circuitry may generate updated blood pressure values by applying an offset value to the second blood pressure value and subsequently received blood pressure values that compensates for the difference value between the first blood pressure value and the second blood pressure value.

Abstract: Implementations described herein disclose an artificial intelligence (AI) based method for generating an oxygen saturation level output signal using the trained neural network. In one implementation, the method includes receiving a photoplethysmographic (PPG) signal, the PPG signal including a red PPG signal and an infrared PPG signal, generating an input feature matrix by performing time-frequency transform of the PPG signal, training a neural network using the input feature matrix and an oxygen saturation level input signal, and generating an oxygen saturation level output signal using the trained neural network.

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: 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: Implementations described herein disclose a method of determining how well predictions of an impending hypoxia are reported in real-time, so that a user has higher confidence in the reported predictions.

Abstract: A method for monitoring autoregulation includes, using a processor, receiving a blood pressure signal an oxygen saturation signal, and a regional oxygen saturation signal from a patient. The method also includes normalizing the regional oxygen saturation signal to correct for variation in the oxygen saturation signal based on a relationship between the oxygen saturation signal and the regional oxygen saturation signal. The method further includes determining a linear correlation between the blood pressure signal and the normalized regional oxygen saturation signal. The method still further includes providing a signal indicative of the patient's autoregulation status to an output device based on the linear correlation.

Abstract: A system for continuous non-invasive blood pressure monitoring may include processing circuitry configured to determine calibration data for a continuous non-invasive blood pressure model at a calibration point, receive, from an oxygen saturation sensing device, a PPG signal at a particular time subsequent to the calibration point, derive values of the set of metrics for the patient from the PPG signal, and determine, using the continuous non-invasive blood pressure model and based at least in part on inputting the calibration data determined at the calibration point, the values of the set of metrics, and an elapsed time at the particular time since the calibration point into the continuous non-invasive blood pressure model, a blood pressure of the patient at the particular time.

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 a cerebral autoregulation status value based on the blood pressure signal and the oxygen saturation signal. The processing circuitry may determine a non-cerebral autoregulation status value based on the cerebral autoregulation status value and an adjustment value. The processing circuitry provide to an output device a signal indicative of the non-cerebral autoregulation status value and a signal indicative of the cerebral autoregulation status value to enable a clinician to monitor the autoregulation status of the patient.

Abstract: In some examples, a device includes processing circuitry configured to receive first and second signals indicative of first and second physiological parameters, respectively, of a patient. The processing circuitry is also configured to determine a first estimate of a limit of autoregulation of the patient based on the first and second signals. The processing circuitry is further configured to determine a difference between the first estimate of the limit of autoregulation and one or more other estimates of the limit of autoregulation. The processing circuitry is configured to determine a weighted average of the first estimate and a previous value of the limit of autoregulation based on the difference between the first estimate and the one or more other estimates. The processing circuitry is configured to determine an autoregulation status based on the weighted average and output, for display via the display, an indication of the autoregulation status.