Abstract: The present invention provides a deep learning-based wearable electro-tonoarteriography method and apparatus for the estimation of continuous arterial blood pressure, which relates to the technical fields of medical detection and artificial intelligence, and is applicable to, such as, tonoarteriogram (TAG, which is continuous arterial blood pressure) signal estimation and cardiac diseases detection. The method comprises: acquiring at least one lead ECG signal collected from a clothing and/or a wearable device worn by a subject of detection; processing the ECG signal based on a deep learning network, determining a signal processing result related to a tonoarteriogram information and/or related to a cardiac disease information. The present invention is advantageous in realizing the acquisition of continuous arterial blood pressure signal and/or the automatic diagnosis of cardiac disease on the basis of ensuring accuracy.

Abstract: The present invention relates to an AI-enhanced wearable photo-electro-tonoarteriography (PETAG) method and apparatus. The invention relates to the technical fields of medical detection and artificial intelligence, and is applicable to, such as, tonoarteriogram (TAG) signal estimation, which is continuous blood pressure and cardiac diseases detection. The method comprises: acquiring at least one lead electrocardiogram (ECG) signal and multi-wavelength photoplethysmogram signals (MWPPG signals); processing the ECG signal and the MWPPG signals by a multimodal model-based multi-task learning network, determining a signal processing result related to a TAG information and/or related to a cardiac disease information. The present invention is advantageous in reducing computational cost involved in signal processing on the basis of ensuring accuracy.

Abstract: Concepts for acquiring information for identifying a security configuration for an application are proposed. In particular, the information is obtained by running the application in a development environment, detecting security requests made on behalf of the application, and then storing security information associated with the security requests in a security log. Using this concept, a security log may be obtained from which an appropriate security configuration may be determined.

Abstract: Concepts for acquiring information for identifying a security configuration for an application are proposed. In particular, the information is obtained by running the application in a development environment, detecting security requests made on behalf of the application, and then storing security information associated with the security requests in a security log. Using this concept, a security log may be obtained from which an appropriate security configuration may be determined.

Abstract: A method, system, and computer-readable medium, for detecting whether an eye blink or non-blink is captured in the image. The method includes filtering, from the image, one or more objects that are predicted to be unsuitable for determining whether an eye blink or no-blink is captured in the image, to provide a filtered image. The method also includes correlating the filtered image with a reference image, and determining, based on the correlating, whether the eye blink or non-blink is captured in the image. The eye blink is a full eye blink or a partial eye blink, and the images may be sequentially captured IR SLO images, in one example embodiment herein. Images determined to include an eye blink can be omitted from inclusion in a final (e.g., OCT) image.

Abstract: A method of processing a sequence of images of a retina acquired by an ophthalmic device to generate retinal position tracking information indicative of retina movement during acquisition. The method includes (i) receiving one or more images of the retina; (ii) calculating a cross-correlation between a reference image and an image based on the received image(s) to acquire an offset between the image and reference image; and repeating processes (i) and (ii) to acquire, as the tracking information, respective offsets for images that are based on the respective received image(s). Another step includes modifying the reference image during the repeating, by determining a measure of similarity between correspondingly located regions of pixels in two or more received images and accentuating features in the reference image representing structures of the imaged retina in relation to other features in the reference image based on the determined measure of similarity.

Abstract: There is disclosed a computer-implemented method of classifying electrocardiogram data of a patient, comprising the steps of receiving input data from each of a plurality of electrocardiogram leads, arranging the input data into a single combined image, and applying a machine-learning algorithm to the combined image to classify the electrocardiogram data.

Abstract: This disclosure relates to methods and apparatus for generating real-time alerts about a patient. In one arrangement, vital sign data representing vital sign information obtained from the patient at one or more input times within an assessment time window is received. A Gaussian process model of at least a portion of the vital sign information is used to generate a time series of synthetic vital sign data based on the received vital sign data, the synthetic vital sign data comprising at least a posterior mean for each of one or more components of the vital sign information at each of a plurality of regularly spaced time points in the assessment time window. The generated synthetic vital sign data is used as input to a trained recurrent neural network to generate an early warning score, the early warning score representing a probability of an adverse event occurring during a prediction time window of predetermined length after the assessment time window.

Abstract: This disclosure relates to methods and apparatus for monitoring a remote system. In one arrangement, a plurality of measurement data units are obtained. Each measurement data unit represents a time series of measurements made by a sensor system at the remote system. A first trained machine learning model is used to identify a subset of the measurement data units that have a higher average probability of corresponding to an abnormal state of the remote system than the other measurement data units. Data representing the identified measurement data units is sent over a communications network to a central data processing system. An abnormal state of the remote system is detected by using a second trained machine learning model at the central data processing system to process the data representing the identified measurement data units.

Abstract: Methods and apparatus for monitoring a patient are provided. In one arrangement, a multi- dimensional patient data set is received at each of a plurality of different reference times. Each dimension of the patient data set stores a value representing a different type of information about the patient. A plurality of predictions of a health trajectory of the patient are generated. Each prediction is generated using a trained machine learning model receiving as input a different one of the patient data sets. The trained machine learning model may be dimensionally adaptive, such that predictions of the patient trajectories are provided using patient data sets having different respective dimensionalities for at least a sub-set of the reference times. The trained machine learning model may use machine learned predictions of accuracy to select trained machine learning units from an ensemble of trained machine learning units.

Abstract: Methods and apparatus for classifying subjects based on time series phenotypic data are disclosed. In one arrangement, a data receiving unit receives a set of first subject-data-units, each first subject-data-unit in the set comprising time series data representing phenotypic information about a different respective one of a plurality of subjects to be classified. A data processing unit processes the set of first subject-data-units to reduce a dimensionality of each first subject-data-unit, thereby obtaining a corresponding set of second subject-data-units having lower dimensionality than the first subject-data-units. The set of second subject-data-units is processed to cluster the second subject-data-units into a plurality of clusters. Each of one or more of the subjects is classified by determining to which cluster a second subject-data-unit corresponding to the subject belongs.

Abstract: A method, apparatus, and computer-readable medium, for assessing image quality of an image produced by a scanning imaging system. The method comprises acquiring (S10) image data of an image produced by the scanning imaging system and calculating (S20 to S40), for each section of the image: a respective first value measuring at least one of sharpness or contrast of at least a part of the section, the measuring depending on noise, a respective second value measuring noise in at least a part of the section, and a respective third value indicating image quality, by combining the first and second values. The combining is such that calculated third values have a weaker dependency on the noise than the first values. The method further comprises determining (S50) a quality score that is indicative of image quality of the image based on a variation of the calculated third values among the sections.

Abstract: Methods and apparatus for subtyping subjects based on phenotypic information are disclosed. In one arrangement, a data receiving unit receives a subject data unit for each of a plurality of subjects. Each subject data unit represents a plurality of different phenotypic information items about the subject. A data processing unit uses a deep learning algorithm to derive a lower dimensional representation of each subject data unit and a clustering algorithm to detect clusters of the resulting lower dimensional representations. The deep learning algorithm and clustering algorithm are implemented by a single mathematical model in which the derivation of the lower dimensional representations and the detection of the clusters are performed jointly.

Abstract: A method, system, and computer-readable medium, for detecting whether an eye blink or non-blink is captured in the image. The method includes filtering, from the image, one or more objects that are predicted to be unsuitable for determining whether an eye blink or no-blink is captured in the image, to provide a filtered image. The method also includes correlating the filtered image with a reference image, and determining, based on the correlating, whether the eye blink or non-blink is captured in the image. The eye blink is a full eye blink or a partial eye blink, and the images may be sequentially captured IR SLO images, in one example embodiment herein. Images determined to include an eye blink can be omitted from inclusion in a final (e.g., OCT) image.

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: Methods and apparatus for monitoring a human or animal subject are disclosed. In one arrangement, test data representing a time-series of physiological measurements performed on a subject in a measurement session is received. A mean trajectory with error bounds is fitted to the test data. A state of the subject is determined by comparing the fitted mean trajectory with error bounds to a stored model of normality. The stored model of normality comprises a library of latent mean trajectories with error bounds. Each latent mean trajectory with error bounds is derived by fitting a hierarchical probabilistic model to a respective one of a plurality of sets of historical data. Each set of historical data comprises a plurality of session data units. Each session data unit representing a time-series of physiological measurements obtained during a different measurement session.

Abstract: A method of processing a sequence of images of a retina acquired by an ophthalmic device to generate retinal position tracking information indicative of retina movement during acquisition. The method includes (i) receiving one or more images of the retina; (ii) calculating a cross-correlation between a reference image and an image based on the received image(s) to acquire an offset between the image and reference image; and repeating processes (i) and (ii) to acquire, as the tracking information, respective offsets for images that are based on the respective received image(s). Another step includes modifying the reference image during the repeating, by determining a measure of similarity between correspondingly located regions of pixels in two or more received images and accentuating features in the reference image representing structures of the imaged retina in relation to other features in the reference image based on the determined measure of similarity.

Abstract: A method, apparatus, and computer-readable medium, for assessing image quality of an image produced by a scanning imaging system. The method comprises acquiring (S10) image data of an image produced by the scanning imaging system and calculating (S20 to S40), for each section of the image: a respective first value measuring at least one of sharpness or contrast of at least a part of the section, the measuring depending on noise, a respective second value measuring noise in at least a part of the section, and a respective third value indicating image quality, by combining the first and second values. The combining is such that calculated third values have a weaker dependency on the noise than the first values. The method further comprises determining (S50) a quality score that is indicative of image quality of the image based on a variation of the calculated third values among the sections.

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: A system for monitoring the operation of a surface pump such as a hand-operated water pump or oil pump, which uses an accelerometer mounted to a component of the pump to monitor movement of a pump component, for example the handle, and transmitted via a data connection such as a mobile data communications network to a server. The accelerometer measurements are processed by using a trained model such as a support vector machine to output an indication of the condition of the pump or the level of liquid in the well or borehole served by the pump. The model may be trained using a training data set of sensor measurements associated with liquid level in the well and condition of the pump.