Abstract: Described herein are systems and methods for training first and second neural network models. A system comprises a memory comprising instruction data representing a set of instructions and a processor configured to communicate with the memory and to execute the set of instructions. The set of instructions, when executed by the processor, cause the processor to set a weight in the second model based on a corresponding weight in the first model, train the second model on a first dataset, wherein the training comprises updating the weight in the second model and adjust the corresponding weight in the first model based on the updated weight in the second model.

Abstract: The present invention relates to an apparatus and method for determining blood pressure of a subject. To automatically trigger calibration the apparatus comprises a sensor signal input configured to obtain an arterial pulse wave sensor signal of the subject, a feature extraction unit configured to extract multiple features from the obtained arterial pulse wave sensor signal, an estimation unit configured to determine multiple blood pressure estimation values for individual extracted features and/or groups of extracted features and to determine the subject's blood pressure from said multiple blood pressure estimation values, a calibration unit configured to calibrate the estimation unit based on blood pressure reference measurements, and a calibration trigger unit configured to trigger calibration by the calibration unit if the multiple blood pressure estimation values diverge more than a divergence limit.

Abstract: A control unit (12) and method for deriving a measure of arterial compliance based on an acquired arterial volume variation signal and measured diastolic and systolic blood pressure measurements. An oscillometric blood pressure measurement device is used to obtain a first signal representative of arterial volume variations and to obtain blood pressure measurements. Both are measured as an applied pressure to an artery is varied by the oscillometric blood pressure measurement device. The first signal is processed to compile a dataset of values, ?V, representative of the change in the arterial volume for set step changes, ?P, in applied pressure, at different transmural pressure values. This set of values is numerically integrated to derive a function of arterial volume with transmural pressure. This function is differentiated to thereby derive a function of arterial compliance with transmural pressure.

Abstract: A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

Abstract: According to an aspect, there is provided a method of operating a non-invasive blood pressure, NIBP, monitor to measure the blood pressure of a subject, the NIBP monitor comprising a cuff, a pressure sensor for measuring the pressure in the cuff and for outputting a pressure signal representing the pressure in the cuff and a physiological parameter sensor, the method comprising obtaining a first measurement of a physiological parameter for the subject during inflation of the cuff, the first measurement being obtained from the pressure signal; obtaining a second measurement of the physiological parameter for the subject during inflation of the cuff, the second measurement being obtained from the physiological parameter sensor; comparing the first measurement and the second measurement; and estimating the reliability of a blood pressure measurement obtained by the NIBP monitor during inflation of the cuff based on the result of the step of comparing.

Abstract: The invention provides a control unit (12) and method for deriving a measure of arterial compliance based on an acquired arterial volume variation signal and an acquired pulse arrival time signal. An oscillometric blood pressure measurement device is used to acquire the arterial volume variation signal. Arterial volume and variation in pulse arrival time are both measured as an applied pressure to an artery are varied by the oscillometric blood pressure measurement device. The arterial volume signal is transformed into a corresponding signal representative of variation in peak-to-peak amplitude of the arterial volume. A first model fitting procedure is used to transform this peak-to-peak amplitude signal into a signal indicative of arterial volume as a function of transmural pressure. A second model fitting procedure is used to generate from the derived arterial volume vs. transmural pressure signal, and the derived pulse arrival time variation signal a final output measure of arterial compliance.

Abstract: In a system and method for determining vital sign information of a subject the subject is illuminated with radiation, and radiation reflected from the subject is received. A region of interest is located in a first phase. Said illumination is controlled to locally illuminate, in a second phase, the located region of interest with radiation allowing determination of vital sign information. Finally, vital sign information of the subject is determined from the radiation reflected from said region of interest and detected in said second phase.

Abstract: A method for modifying data from a Real-Time Location System (RTLS) involving: receiving building arrangement information having two locations and one or more identifiable characteristics of the two locations; obtaining identifying information of at least one tag and at least two sensors in the RTLS; generating a mapping of the identifying information with the one or more identifiable characteristics of the two locations; receiving location information of the at least one tag based on the mapping, the location information indicating a presence of the at least one tag in the two locations at separate times; determining that the location information includes at least one gap because the at least one tag cannot proceed directly between the two locations in the building arrangement information; and updating the location information based on an interpolation of the location information to fill in the at least one gap.

Abstract: The present disclosure pertains to a system configured to facilitate prediction of a sleep stage and intervention preparation in advance of the sleep stage's occurrence. The system comprises sensors configured to be placed on a subject and to generate output signals conveying information related to brain activity of the subject; and processors configured to: determine a sample representing the output signals with respect to a first time period of a sleep session; provide the sample to a prediction model at a first time of the sleep session to predict a sleep stage of the subject occurring around a second time; determine intervention information based on the prediction of the sleep stage, the intervention information indicating one or more stimulator parameters related to periheral stimulation; and cause one or more stimulators to provide the intervention to the subject around the second time of the sleep session.

Abstract: The present disclosure pertains to a system and method for delivering sensory stimulation to a user during a sleep session. The system comprises one or more sensors, one or more sensory stimulators, and one or more hardware processors. The processor(s) are configured to: determine one or more brain activity parameters indicative of sleep depth in the user based on output signals from the sensors; cause a neural network to indicate sleep stages predicted to occur at future times for the user during the sleep session; cause the sensory stimulator(s) to provide the sensory stimulation to the user based on the predicted sleep stages over time during the sleep session, and cause the sensory stimulator(s) to modulate a timing and/or intensity of the sensory stimulation based on the one or more brain activity parameters and values output from one or more intermediate layers of the neural network.

Abstract: According to an aspect, there is provided a computer-implemented method of estimating a trend in a blood pressure surrogate, the method comprising obtaining a set of blood pressure surrogate measurement values of a blood pressure surrogate for a subject; obtaining, for each blood pressure surrogate measurement value, an error value indicating a measurement error for the blood pressure surrogate measurement value; and analysing the set of blood pressure surrogate measurement values and the respective error values using Bayesian inference to determine a trend (4) in the blood pressure surrogate over time.

Abstract: The invention provides a system for providing an audio stimulus to a sleeping user. The system includes a user sensor adapted to acquire user sleep data from the sleeping user and a processor, which is adapted to determine a sleep stage of the sleeping user based on the user sleep data. The processor is further adapted to determine a predicted influence of an audio stimulus on the sleep stage of the sleeping user and generate a control signal based on the predicted influence of the audio stimulus. The system further comprises an audio output device, adapted to receive the control signal and generate an audio stimulus based on the control signal.

Abstract: The present invention relates to an apparatus (18) for providing a control signal for a blood pressure measurement device, comprising: an input interface (24) for obtaining a health state parameter being indicative of a health state of a patient (12); a processing unit (28) for determining one or more operation settings of a blood pressure measurement device (14) based on the health state parameter, said one or more operation settings including a parameter that can be adjusted at the blood pressure measurement device (14) when conducting a blood pressure measurement with the device and that affects a precision of said blood pressure measurement and a patient comfort resulting from said blood pressure measurement; and a control interface (30) for providing a control signal for a blood pressure measurement device (14) to perform a blood pressure measurement based on said one or more operation settings. The present invention further relates to a corresponding method.

Abstract: A method, system and computer-program product for identifying neural network inputs for a neural network that may have been incorrectly processed by the neural network. A set of activation values (of a subset of neurons of a single layer) associated with a neural network input is obtained. A neural network output associated with the neural network input is also obtained. A determination is made as to whether a first and second neural network input share similar sets of activation values, but dissimilar neural network outputs or vice versa. In this way a prediction can be made as to whether one of the first and second neural network inputs has been incorrectly processed by the neural network.

Abstract: The present invention relates to an apparatus and method for determining blood pressure of a subject. To automatically trigger calibration the apparatus comprises a sensor signal input (31) configured to obtain an arterial pulse wave sensor signal (11) of the subject, a feature extraction unit (32) configured to extract multiple features (42) from the obtained arterial pulse wave sensor signal, an estimation unit (33) configured to determine multiple blood pressure estimation values (43) for individual extracted features and/or groups of extracted features and to determine the subject's blood pressure (44) from said multiple blood pressure estimation values, a calibration unit (34) configured to calibrate the estimation unit (33) based on blood pressure reference measurements (21), and a calibration trigger unit (35) configured to trigger calibration by the calibration unit (34) if the multiple blood pressure estimation values diverge more than a divergence limit.

Abstract: A system and method are provided for enabling atlas registration in medical imaging, said atlas registration comprising matching a medical atlas 300, 302 to a medical image 320. The system and method may execute a Reinforcement Learning (RL) algorithm to learn a model for matching the medical atlas to the medical image, wherein said learning is on the basis of a reward function quantifying a degree of match between the medical atlas and the medical image. The state space of the RL algorithm may be determined on the basis of a set of features extracted from i) the atlas data and ii) the image data. As such, a model is obtained for medical atlas registration without the use, or with a reduced use, of heuristics. By using a machine learning based approach, the solution can easily be applied to different atlas matching problems, e.g., to different types of medical atlases and/or medical images.

Abstract: Method of operating a non-invasive blood pressure, NIBP, monitor to measure the blood pressure of a subject, the NIBP monitor comprising a cuff, a pressure sensor for measuring the pressure in the cuff and for outputting a pressure signal representing the pressure in the cuff and a physiological parameter sensor, the method comprising obtaining a first measurement of pulse rate or heart rate for the subject during inflation of the cuff, the first measurement being obtained from the pressure signal; obtaining a second measurement of the pulse rate or heart rate for the subject during inflation of the cuff, the second measurement being obtained from the physiological parameter sensor; comparing the first measurement and the second measurement; and estimating the reliability of a blood pressure measurement obtained by the NIBP monitor during inflation of the cuff based on the result of the step of comparing.

Abstract: The present disclosure pertains to a system and method for delivering sensory stimulation to a user during a sleep session. The system comprises one or more sensors, one or more sensory stimulators, and one or more hardware processors. The processor(s) are configured to: determine one or more brain activity parameters indicative of sleep depth in the user based on output signals from the sensors; cause a neural network to indicate sleep stages predicted to occur at future times for the user during the sleep session; cause the sensory stimulator(s) to provide the sensory stimulation to the user based on the predicted sleep stages over time during the sleep session, and cause the sensory stimulator(s) to modulate a timing and/or intensity of the sensory stimulation based on the one or more brain activity parameters and values output from one or more intermediate layers of the neural network.

Abstract: According to an aspect, there is provided a method of operating a non-invasive blood pressure, NIBP, monitor to measure the blood pressure of a subject, the NIBP monitor comprising a cuff, a pressure sensor for measuring the pressure in the cuff and for outputting a pressure signal representing the pressure in the cuff and a physiological parameter sensor, the method comprising obtaining a first measurement of a physiological parameter for the subject during inflation of the cuff, the first measurement being obtained from the pressure signal; obtaining a second measurement of the physiological parameter for the subject during inflation of the cuff, the second measurement being obtained from the physiological parameter sensor; comparing the first measurement and the second measurement; and estimating the reliability of a blood pressure measurement obtained by the NIBP monitor during inflation of the cuff based on the result of the step of comparing.

Abstract: The present disclosure pertains to a system configured to facilitate prediction of a sleep stage and intervention preparation in advance of the sleep stage's occurrence. The system comprises sensors configured to be placed on a subject and to generate output signals conveying information related to brain activity of the subject; and processors configured to: determine a sample representing the output signals with respect to a first time period of a sleep session; provide the sample to a prediction model at a first time of the sleep session to predict a sleep stage of the subject occurring around a second time; determine intervention information based on the prediction of the sleep stage, the intervention information indicating one or more stimulator parameters related to periheral stimulation; and cause one or more stimulators to provide the intervention to the subject around the second time of the sleep session.