Abstract: A method of training a supervised machine-learning algorithm to determine a sleep state of a subject. The method uses training data and training labels in respect of a plurality of subjects derived from video images of the subjects. The training data comprises: at least one measure of subject movement; and at least one cardiorespiratory parameter of the subject. The method comprises training the supervised machine learning algorithm using the training data and the training labels.

Abstract: Methods, devices and systems for determining the frequency of a periodic physiological process of a subject, particularly respiration rate or heart rate, are disclosed. In one arrangement plural time windows of physiological data are obtained. Reference features corresponding to modulation modes are identified. Modulations of the reference features are extracted. Quality parameters are obtained by processing the extracted modulations. The quality parameters represent how strongly the extracted modulation exhibits a waveform of the periodic physiological process. The extracted modulations are processed to calculate the frequency of the periodic physiological process of the subject.

Abstract: A method and apparatus for measuring blood pressure by measuring a photoplethysmographic (PPG) signal of a user with the arm in a raised position and in a lowered position and measuring the difference in timing between them, which represents a change in pulse transit time. The PPG signal is measured in the wrist of the user relative to the PPG signal in the finger of the user. A camera built into a mobile telephone may form a first optical sensor for measuring the PPG signal in the finger and an attached accessory camera, such as an infrared camera, or an optical sensor in a wrist-worn device to obtain the PPG signal in the wrist. Alternatively, a head-worn device may be used as a second optical sensor. Signal averaging based on the timing of the finger-originating PPG signal is used to average the waveforms in the wrist-originating PPG signal for arm-up and arm-down, and the timing difference is measured between the arm-up averaged waveform and arm-down averaged waveform.

Abstract: A method and apparatus for estimating the frequency of a dominant periodic component in an input signal by modelling the input signal using auto-regressive models of several different orders to generate candidate frequencies for the periodic component, generating synthetic sinusoidal signals of each of the candidate frequencies, and calculating the cross-correlation of the synthetic signals with the original signal. The frequency of whichever of the synthetic signals has the highest cross-correlation with the original signal is taken as the estimate of the frequency for the dominant periodic component of the input signal. The method may be applied to any noisy signal which has a suspected periodic component, for example physiological signals such as photoplethysmogram signals, and in the estimation of heart rate and breathing rate from such physiological signals.

Abstract: A method of monitoring changes in oxygen saturation of a subject by analysing a three colour channel video image of the exposed skin of the subject. Within each colour channel a normalised signal obtained by dividing the intensity signal by its mean value, and the normalised signals are averaged across plural regions of interest within the exposed skin area image of the subject. Regions of interest are selected on the basis of the signal-to-noise ratios for the heart rate and breathing rate components. A single representative waveform for each colour channel is obtained by signal averaging and the ratio of the amplitudes of the representative waveforms from two different colour channels, e.g. blue and red, is taken. The changes in the ratio of amplitudes is output as a measure of changes in blood oxygen saturation.

Abstract: Methods and apparatus for monitoring a human or animal subject are disclosed. In one arrangement, measurement data representing a time series of measurements on a subject is received. The measurement data is represented as a mathematical expansion comprising a plurality of expansion components and expansion coefficients. First and second partial reconstructions are performed using first and second subsets of the expansion components. First and second spectral analyses are performed on the first and second partial reconstructions to determine first and second dominant frequencies. A frequency of a periodic physiological process is derived based on either or both of the first and second dominant frequencies.

Abstract: Haemodynamic parameters such as the amplitude and phase of a pulse wave passing through a region of interest can be obtained from a video image of the exposed skin of a patient by processing of the reflectance photoplethysmographic signal using signal averaging. The region of interest is defined and a reflectance photoplethysmographic signal obtained by finding the mean pixel intensity across the region of interest for each video frame. Signal averaging is performed on the resulting pulsatile waveform by detecting peaks in the waveform, selecting those parts of the waveform which lie within a window centered on the peaks, and summing the selected parts of the waveform to find an average pulse waveform. The region of interest is then divided into sub-regions and an average pulse waveform for the video sequence is found for each of the sub-regions in the same way.

Abstract: A patient status monitor for providing an estimate of the risk of an adverse health event such as death or intensive care readmission based on a first risk estimate using patient data collected over a first time period, such as a stay in an intensive care unit, and a second risk estimate based on current vitals signs measurements. The first and second risk estimates are based on different models, the first being a static logistic regression on data selected from electronic patient records, and the second being a novelty detection algorithm based on a a training data set of vital signs measurements representing normality. The two risk estimates are combined in a weighted combination, with the first risk estimate having a weight which decreases with time from the end of the first time period.

Abstract: Methods, devices and systems for determining the frequency of a periodic physiological process of a subject, particularly respiration rate or heart rate, are disclosed. In one arrangement plural time windows of physiological data are obtained. Reference features corresponding to modulation modes are identified. Modulations of the reference features are extracted. Quality parameters are obtained by processing the extracted modulations. The quality parameters represent how strongly the extracted modulation exhibits a waveform of the periodic physiological process. The extracted modulations are processed to calculate the frequency of the periodic physiological process of the subject.

Abstract: A method of monitoring changes in oxygen saturation of a subject by analysing a three colour channel video image of the exposed skin of the subject. Within each colour channel a normalised signal obtained by dividing the intensity signal by its mean value, and the normalised signals are averaged across plural regions of interest within the exposed skin area image of the subject. Regions of interest are selected on the basis of the signal-to-noise ratios for the heart rate and breathing rate components. A single representative waveform for each colour channel is obtained by signal averaging and the ratio of the amplitudes of the representative waveforms from two different colour channels, e.g. blue and red, is taken. The changes in the ratio of amplitudes is output as a measure of changes in blood oxygen saturation.

Abstract: Vibration amplitudes are recorded as a function of rotation speed and of frequency and the data is analyzed to estimate a noise floor amplitude threshold for each of a plurality of different speed and frequency sub-ranges. On the basis of training data known to be normal speed-frequency areas which contain significant spectral content in normal operation are deemed “known significant spectral content”, so that during monitoring of new data points which correspond to significant vibration energy at speeds and frequencies different from the known significant spectral content can be deemed “novel significant spectral content” and form the basis for an alert. The estimation of the noise floor is based on a probabilistic analysis of the data in each speed-frequency area and from this analysis an extreme value distribution expressing the probability that any given sample is noise is obtained.

Abstract: Haemodynamic parameters such as the amplitude and phase of a pulse wave passing through a region of interest can be obtained from a video image of the exposed skin of a patient by processing of the reflectance photoplethysmographic signal using signal averaging. The region of interest is defined and a reflectance photoplethysmographic signal obtained by finding the mean pixel intensity across the region of interest for each video frame. Signal averaging is performed on the resulting pulsatile waveform by detecting peaks in the waveform, selecting those parts of the waveform which lie within a window centred on the peaks, and summing the selected parts of the waveform to find an average pulse waveform. The region of interest is then divided into sub-regions and an average pulse waveform for the video sequence is found for each of the sub-regions in the same way.

Abstract: A method and apparatus for estimating the frequency of a dominant periodic component in an input signal by modelling the input signal using auto-regressive models of several different orders to generate candidate frequencies for the periodic component, generating synthetic sinusoidal signals of each of the candidate frequencies, and calculating the cross-correlation of the synthetic signals with the original signal. The frequency of whichever of the synthetic signals has the highest cross-correlation with the original signal is taken as the estimate of the frequency for the dominant periodic component of the input signal. The method may be applied to any noisy signal which has a suspected periodic component, for example physiological signals such as photoplethysmogram signals, and in the estimation of heart rate and breathing rate from such physiological signals.

Abstract: An image of a human, animal or machine subject, is analysed to detect regions which include strong periodic intensity variations, such as a photoplethysmogram (PPG) signal in a human or animal, or some periodic vibration in a machine. The image is divided into plural regions of fixed order is fitted to a representative intensity signal for that region. The poles of the fitted autoregressive model are thresholded by magnitude to select only the pole or poles with a magnitude greater than the threshold. The pole magnitude therefore acts as a signal quality index. The dominant pole is representative of the strongest periodic information and the frequency of that spectral component can be derived from the phase angle of the pole. The image may be redisplayed with image attributes, e.g. color-coding, according to the pole magnitude in each region of interest and/or the dominant pole phase angle in each region of interest. In the case of a PPG image signal this can give maps of heart rate and breathing rate.

Abstract: A method of remote monitoring of vital signs by detecting the PPG signal in an image of a subject taken by a video camera such as a webcam. The PPG signal is identified by auto-regressive analysis of ambient light reflected from a region of interest on the subject's skin. Frequency components of the ambient light and aliasing artefacts resulting from the frame rate of the video camera are cancelled by auto-regressive analysis of ambient light reflected from a region of interest not on the subject's skin, e.g. in the background. This reveals the spectral content of the ambient light allowing identification of the subject's PPG signal. Heart rate, oxygen saturation and breathing rate are obtained from the PPG signal. The values can be combined into a wellness index based on a statistical analysis of the values.

Abstract: A method of obtaining information about the rate of a periodic physiological process from a time series of measurements obtained from a patient, comprising: obtaining the time series of measurements; fitting a model defining a probability distribution over functions to the time series of measurements, wherein the model is defined by a mean function and a periodic covariance function; and outputting the result of the fitting as information about the rate of the periodic physiological process.

Abstract: An image of a human, animal or machine subject, is analysed to detect regions which include strong periodic intensity variations, such as a photoplethysmogram (PPG) signal in a human or animal, or some periodic vibration in a machine. The image is divided into plural regions of fixed order is fitted to a representative intensity signal for that region. The poles of the fitted autoregressive model are thresholded by magnitude to select only the pole or poles with a magnitude greater than the threshold. The pole magnitude therefore acts as a signal quality index. The dominant pole is representative of the strongest periodic information and the frequency of that spectral component can be derived from the phase angle of the pole. The image may be redisplayed with image attributes, e.g. colour-coding, according to the pole magnitude in each region of interest and/or the dominant pole phase angle in each region of interest. In the case of a PPG image signal this can give maps of heart rate and breathing rate.

Abstract: A method of monitoring a system such as a machine, industrial system, or human or animal patient, to classify the system as normal or abnormal, in which a time-series of measurements of the system are regarded as a function to be compared to a model of normality for such functions. The model of normality can be constructed as a Gaussian Process and test functions compared to the model to derive the probability that they are drawn from the model of normality. A probability distribution for the expected extrema of sets of functions drawn from the model can also be derived and the probability of any extremum of a plurality of test functions being an extremum of a set derived from the model of normality can be obtained. The system can be classified as normal or abnormal based on the extreme probability distribution. Test functions with fewer data points can be compared to the model of normality by marginalisation with respect to the missing data points.

Abstract: A method of obtaining a consistent evaluation of the state of the system which has been monitored by measurement of multiple parameters of that system. The multiple parameters are used to calculate a single dimensional value based on the distance between the current state and normal states of the system using a Parzen Windows probability function. Consistent single dimensional values regardless of the dimensionality of the original data set can be obtained by finding a relationship between the single dimensional value and the probability of status of the system. Different relationships are obtained for different dimensionalities of data sets. Sensor malfunction can also be detected by testing the probability of the state implied by measuring all of the available parameters against the probability of the state implied by ignoring different individual ones of the parameters. A significant disparity in the two probabilities indicate possible sensor malfunction.

Abstract: A method of remote monitoring of vital signs by detecting the PPG signal in an image of a subject taken by a video camera such as a webcam. The PPG signal is identified by auto-regressive analysis of ambient light reflected from a region of interest on the subject's skin. Frequency components of the ambient light and aliasing artefacts resulting from the frame rate of the video camera are cancelled by auto-regressive analysis of ambient light reflected from a region of interest not on the subject's skin, e.g. in the background. This reveals the spectral content of the ambient light allowing identification of the subject's PPG signal. Heart rate, oxygen saturation and breathing rate are obtained from the PPG signal. The values can be combined into a wellness index based on a statistical analysis of the values.