Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. Multiple template similarity functions (118) may be provided (602). Each template similarity function may compare a respective subset of features of a query entity feature vector with a corresponding subset of features of a candidate entity feature vector. A composite similarity function (120) may be provided (604) as a weighted combination of respective outputs of the template similarity functions. A plurality of labeled entity vectors may be provided (606) as context training data. An approximation function may be applied (608) to approximate a first context label for each respective labeled entity vector. A first context specific composite similarity function may be trained (610) based on the composite similarity function by learning first context weights for the template similarity functions using a first loss function based on output of application of the approximation function to the first context training data.

Abstract: A non-transitory computer-readable medium stores instructions readable and executable by at least one electronic processor (20) to perform an atrial fibrillation (AF) detection method (100). The method includes: generating a time-frequency representation of an electrocardiogram (ECG) signal acquired over a time interval; processing the time-frequency representation using a neural network (NN) (32) to output probabilities for rhythms of a set of rhythms including at least atrial fibrillation; assigning a rhythm for the ECG signal based on the probabilities for the rhythms of the set of rhythms output by the neural network; and controlling a display device (24) to display the rhythm assigned to the ECG signal.

Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. In various embodiments, a first value for a query entity may be displayed (702) on an interface. The first value may be related to a first context. A first trained similarity function may be selected (704) from a plurality of trained similarity functions. The first trained similarity function may be associated with the first context. The first selected trained similarity function may be applied (706) to a set of features associated with the query entity and respective sets of features associated with a plurality of candidate entities. A set of one or more similar candidate entities may be selected (708) from the plurality of candidate entities based on application of the first trained similarity function. Information associated with the first set of one or more similar candidate entities may be displayed (710) on the interface.

Abstract: A non-transitory computer-readable medium stores instructions readable and executable by at least one electronic processor (20) to perform an atrial fibrillation (AF) detection method (100). The method includes: generating a time-frequency representation of an electrocardiogram (ECG) signal acquired over a time interval; processing the time-frequency representation using a neural network (NN) (32) to output probabilities for rhythms of a set of rhythms including at least atrial fibrillation; assigning a rhythm for the ECG signal based on the probabilities for the rhythms of the set of rhythms output by the neural network; and controlling a display device (24) to display the rhythm assigned to the ECG signal.

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: Techniques disclosed herein relate to identifying individuals in digital images. In some embodiments, a digital image(s) that captures a scene containing one or more people may be acquired. The single digital image may be applied as input across a single machine learning model. In some implementations, the single machine learning model may be trained to perform a non-facial feature recognition task and a face-related recognition task. Output may be generated over the single machine learning model based on the input. The output may include first data indicative of non-facial features of a given person of the one or more people and second data indicative of at least a location of a face of the given person in the digital image relative to the non-facial features. In various embodiments, the given person may be identified based at least in part on the output.

Abstract: A method of determining patient subtyping from disease progression trajectories, including: extracting patient data and related time stamps from patient record data related to a disease, wherein the extracted patient data is incomplete and irregular; building a continuous-time disease progression model based upon the extracted patient data; and building a mixture model for clustering of patient disease trajectory subtypes.

Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. Multiple template similarity functions (118) may be provided (602). Each template similarity function may compare a respective subset of features of a query entity feature vector with a corresponding subset of features of a candidate entity feature vector. A composite similarity function (120) may be provided (604) as a weighted combination of respective outputs of the template similarity functions. A plurality of labeled entity vectors may be provided (606) as context training data. An approximation function may be applied (608) to approximate a first context label for each respective labeled entity vector. A first context specific composite similarity function may be trained (610) based on the composite similarity function by learning first context weights for the template similarity functions using a first loss function based on output of application of the approximation function to the first context training data.

Abstract: Various embodiments of the present disclosure are directed to a general statistical classifier (40) and a personal statistical classifier (50) for executing a patient risk prediction method. In operation, the general statistical classifier (40) may render a singular general independent vital sign risk score for a singular vital sign and/or may render plural general independent vital sign risk scores for plural vital signs.

Abstract: Techniques disclosed herein relate to identifying individuals in digital images. In some embodiments, a digital image(s) that captures a scene containing one or more people may be acquired. The single digital image may be applied as input across a single machine learning model. In some implementations, the single machine learning model may be trained to perform a non-facial feature recognition task and a face-related recognition task. Output may be generated over the single machine learning model based on the input. The output may include first data indicative of non-facial features of a given person of the one or more people and second data indicative of at least a location of a face of the given person in the digital image relative to the non-facial features. In various embodiments, the given person may be identified based at least in part on the output.

Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. Multiple template similarity functions may be provided. Each template similarity function may compare a respective subset of features of a query entity feature vector with a corresponding subset of features of a candidate entity feature vector. A composite similarity function may be provided as a weighted combination of respective outputs of the template similarity functions. A plurality of labeled entity vectors may be provided as context training data. An approximation function may be applied to approximate a first context label for each respective labeled entity vector. A first context specific composite similarity function may be trained based on the composite similarity function by learning first context weights for the template similarity functions using a first loss function based on output of application of the approximation function to the first context training data.

Abstract: Techniques disclosed herein relate to identifying individuals in digital images. In some embodiments, a digital image may be acquired (802) that captures an environment containing at least a first subject. A first portion of the digital image depicting the first subject may be segmented (806) into a plurality of superpixels. For each superpixel of the plurality of superpixels: a semantic label may be assigned (810) to the superpixel; features of the superpixel may be extracted (812); and a measure of similarity between the features extracted from the superpixel and features extracted from a reference superpixel identified in a reference digital image may be determined (814), wherein the reference superpixel has a reference semantic label that matches the semantic label assigned to the superpixel. Based on the measures of similarity associated with the plurality of superpixels, it may be determined (818) that the first subject is depicted in the reference image.

Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. In various embodiments, a first value for a query entity may be displayed (702) on an interface. The first value may be related to a first context. A first trained similarity function may be selected (704) from a plurality of trained similarity functions. The first trained similarity function may be associated with the first context. The first selected trained similarity function may be applied (706) to a set of features associated with the query entity and respective sets of features associated with a plurality of candidate entities. A set of one or more similar candidate entities may be selected (708) from the plurality of candidate entities based on application of the first trained similarity function. Information associated with the first set of one or more similar candidate entities may be displayed (710) on the interface.

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: A non-transitory computer-readable medium stores instructions readable and executable by at least one electronic processor (20) to perform an atrial fibrillation (AF) detection method (100). The method includes: generating a time-frequency representation of an electrocardiogram (ECG) signal acquired over a time interval; processing the time-frequency representation using a neural network (NN) (32) to output probabilities for rhythms of a set of rhythms including at least atrial fibrillation; assigning a rhythm for the ECG signal based on the probabilities for the rhythms of the set of rhythms output by the neural network; and controlling a display device (24) to display the rhythm assigned to the ECG signal.

Abstract: Methylotrophic microorganisms, particularly methylotrophic yeasts and more particularly Pichia pastoris, which exhibit the ability to oxidize methane to methanol. Methods of making such microorganisms and DNA constructs for making such microorganisms. Such methylotrophic microorganisms are genetically transformed to exhibit the oxidizing activity of a soluble methane monooxygenase of a methanotrophic bacterium. Such transformed methylotrophic microorganisms contain at least three methane monooxygenase hydroxylase (MMOH) protein subunits of a methanotrophic bacterium: MMOH alpha, MMOH beta and MMOH gamma and a methane monooxygenase reductase (MMOR) of a methanotrophic bacterium.

Abstract: A method of determining the infection risk probability for a patient, including: encoding physiological data of the patient into a first synthetic image; encoding environmental data of the patient into a second synthetic image; determining an intrinsic probability of infection for the patient based upon the first synthetic image and the second synthetic image using a machine learning model; generating a graphical model based upon the patient and other patients based upon similarity scores between the patient and the other patients; and determining the infection risk probability for the patient based upon the graphical model and the intrinsic probability of infection for the patient and the other patients.

Abstract: Various embodiments of the inventions of the present disclosure provide a combination of feature-based approach and deep learning approach for distinguishing between normal heart sounds and abnormal heart sounds. A feature-based classifier (60) is applied to a phonocardiogram (PCG) signal to obtain a feature-based abnormality classification of the heart sounds represented by the PCG signal and a deep learning classifier (70) is also applied to the PCG signal to obtain a deep learning abnormality classification of the heart sounds represented by the PCG signal. A final decision analyzer (80) is applied to the feature-based abnormality classification and the deep learning abnormality classification of the heart sounds represented by the PCG signal to determine a final abnormality classification decision of the PCG signal.

Abstract: Techniques described herein relate to training and applying predictive models using discretized physiological sensor data. In various embodiments, a continuous stream of samples measured by a physiological sensor may be discretized into a training sequence of quantized beats. A training sequence of vectors determined based on the training sequence of quantized beats and an embedding matrix may be associated with labels indicative of medical conditions, and applied as input across a neural network to generate corresponding instances of training output. Based on a comparison of each instance of training output with a respective label, the neural network and the embedding matrix may be trained and used to predict medical conditions from unlabeled continuous streams of physiological sensor samples. In some embodiments, the trained embedding matrix may be visualized to identify correlations between medical conditions and physiological signs.

Abstract: Techniques disclosed herein relate to learning and applying contextual patient similarities. Multiple template similarity functions may be provided. Each template similarity function may compare a respective subset of features of a query entity feature vector with a corresponding subset of features of a candidate entity feature vector. A composite similarity function may be provided as a weighted combination of respective outputs of the template similarity functions. A plurality of labeled entity vectors may be provided as context training data. An approximation function may be applied to approximate a first context label for each respective labeled entity vector. A first context specific composite similarity function may be trained based on the composite similarity function by learning first context weights for the template similarity functions using a first loss function based on output of application of the approximation function to the first context training data.