Koninklijke Philips Corporation N.V.

Massachusetts Eye and Ear Infirmary

The United States Government As Represented by the Department of Veterans Affairs

Minnan Xu

Bryan Conroy

Cristhian Mauricio Potes Blandon

Larry James Eshelman

Asif Rahman

Ashequl Qadir

Conrad Wall, Iii

Joseph F Rizzo, Iii

Kathy Mi Young Lee

Eric Thomas Carlson

Srinivasan Vairavan

Cristhian Potes

Limei Cheng

Claire Yunzhu Zhao

Gary Nelson Garcia Molina

Balasundar Iyyavu Raju

Ajay Anand

Aaditya Prakash

Joseph James Frassica

Louis Nicolas Atallah

Pedro Miguel Ferreira Dos Santos Da Fonseca

Adam Jacob Seiver

Junzi Dong

Kostyantyn Volyanskyy

Attila Priplata

A system and method for training a text report identification machine learning model and an image identification machine learning model, including: initially training a text report machine learning model, using a labeled set of text reports including text pre-processing the text report and extracting features from the pre-processed text report, wherein the extracted features are input into the text report machine learning model; initially training an image machine learning model, using a labeled set of images; applying the initially trained text report machine learning model to a first set of unlabeled text reports with associated images to label the associated images; selecting a first portion of labeled associated images; re-training the image machine learning model using the selected first portion of labeled associated images; applying the initially trained image machine learning model to a first set of unlabeled images with associated text reports to label the associated text reports; selecting a first portion of labeled associated text reports; and re-training the text report machine learning model using the selected first portion of labeled associated text reports.

Co-training framework to mutually improve concept extraction from clinical notes and medical image classification

A system and method for unsupervised training of a text report identification machine learning model, including: labeling a first set of unlabeled text reports using a seed dictionary to identify concepts in the unlabeled text reports; inputting images associated with the first set of seed-labeled text reports into an auto-encoder to obtain an encoded first set of images; calculating a set of first correlation matrices as a dot product of the first encoded images with their associated text report features; determining a distance between the set of first correlation matrices and a filter bank value associated with the auto-encoder; identifying a first set of validated images as the images in the first set of images that have a distance less than a threshold value; and training the text report machine learning model using the labeled text reports associated with the set of first validated images.

Method to improve instance selection in bootstrapping framework for concept extraction from text documents

The present disclosure pertains to a system for providing client-side physiological condition estimations during a live video session. In some embodiments, the system includes a first client computer system that is caused to: (i) store a neural network on one or more computer-readable storage media of the first client computer system, (ii) obtain a live video stream of an individual via a camera of the first client computer system during a video streaming session between the first client computer system and a second client computer system, (iii) provide, during the video streaming session, video data of the live video stream as input to the neural network to obtain physiological condition information from the neural network, and (iv) provide, during the video streaming session, the physiological condition information for presentation at the second client computer system.

System and method for client-side physiological condition estimations based on a video of an individual

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.

Learning and applying contextual similiarities between entities

Techniques disclosed herein relate to learning and applying contextual patient similarities. In various embodiments, a first value for a query entity may be displayed () on an interface. The first value may be related to a first context. A first trained similarity function may be selected () 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 () 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 () 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 () on the interface.

Learning and applying contextual similarities between entities

A method of implementing a task complexity learning system, including: learning a model for predicting the value of a continuous task variable y based upon an input variable x; learning an encoder that encodes a continuous task variable y into an encoded task value; calculating a loss function based upon the predicted value of y output by the model and the encoded task value output by the encoder; calculating a distortion function based upon the input continuous task variable y and the encoded task value, wherein learning the model and learning the encoder includes minimizing an objective function based upon the loss function and the distortion function for a set of input training data including x, y pairs.

System to identify and explore relevant predictive analytics tasks of clinical value and calibrate predictive model outputs to a prescribed minimum level of predictive accuracy

In a risk level assessment method for a plurality of clinical conditions as follows, a set of laboratory test results () are stored with time stamps for a patient, including at least one hematology test result and at least one arterial blood gas (ABG) test result. For each clinical condition, a risk level is determined for the clinical condition based on a clinical condition-specific sub-set of the stored set of laboratory test results. This determination is made conditional on the stored clinical condition-specific sub-set of laboratory test results being sufficient to determine the risk level. A time stamp is assigned to each determined risk level based on the time stamps for the laboratory test results of the clinical condition-specific sub-set of laboratory test results. A display device () displays the determined risk level and the assigned time stamp for each clinical condition whose determined risk level satisfies a display criterion.

System for laboratory values automated analysis and risk notification in intensive care unit

An electronic clinical decision support (CDS) device () employs a trained CDS algorithm () that operates on values of a set of covariates to output a prediction of a medical condition. The CDS algorithm was trained on a training data set (). The CDS device includes a computer () that is programmed to provide a user interface () for completing clinical survey questions using the display and the one or more user input devices. Marginal probability distributions () for the covariates of the set of covariates are generated from the completed clinical survey questions. The trained CDS algorithm is adjusted for covariate shift using the marginal probability distributions. A prediction of the medical condition is generated for a medical subject using the trained CDS algorithm adjusted for covariate shift () operating on values for the medical subject of the covariates of the set of covariates.

Electronic clinical decision support device based on hospital demographics

A system () for monitoring an individual's sleep includes: (i) a patient monitor () configured to obtain a patient waveform, the patient waveform comprising information representative of a vital statistic of the patient; a processor () in communication with the patient monitor and configured to: (i) process the patient waveform to generate a segmented waveform; (ii) extract at least one feature from a segment of the waveform in a time domain and/or at least one feature from the segment of the waveform in the frequency domain; (iii) classify, using the at least one extracted feature, a sleep stage of the patient for the segment of the waveform; and (iv) generate, from classified sleep stages for a plurality of segments of the waveform, a sleep quality measurement; and a user interface () configured to report the generated sleep quality measurement.

Method and system for monitoring sleep quality

System () for extracting a fetal heart rate from at least one maternal signal using a computer processor (). The system includes sensors (-) attached to a patient to receive abdominal ECG signals and a recorder and digitizer () to record and digitize each at least one maternal signal in a maternal signal buffer (A-D). The system further includes a peak detector () to identify candidate peaks in the maternal signal buffer. The signal stacker () of the system stacks the divides at least one maternal signal buffer into a plurality of snippets, each snippet including one candidate peak and a spatial filter () to identify and attenuate a maternal QRS signal in the plurality of snippets of the maternal signal buffer, the spatial filter including at least one of principal component analysis and orthogonal projection, to produce a raw fetal ECG signal which is stored in a raw fetal ECG buffer. The system further includes a fetal QRS identifier () for identifying peaks in the raw fetal ECG buffer by at least one of principal component analysis and a peak-detector followed by rule based fQRS extraction and a merger () to calculate and merge the fetal heart rate from the identified peaks.

Fetal heart rate extraction from maternal abdominal ECG recordings

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.

A Doppler ultrasound instrument () includes ultrasound pulse control and data acquisition electronics () for acquiring Doppler ultrasound data, an N-channel connector port () for simultaneously operatively connecting up to N ultrasound transducer patches () where N is an integer equal to or greater than two, and an electronic processor () programmed to concurrently determine up to N blood flow velocities corresponding to up to N patches operatively connected to the N channel connector port. The blood flow velocity for each patch may be determined by: determining transducer blood flow velocities for ultrasound transducers () of a transducer array of the patch; and determining the blood flow velocity for the patch as a highest determined transducer blood flow velocity or as an aggregation of highest determined transducer blood flow velocities.

Multi-site concurrent ultrasound blood flow velocity measurement for continuous hemodynamic management

Various embodiments described herein relate to methods and apparatus for robust classification. Many real-world datasets suffer from missing or incomplete data. By assigning weights to certain features of a dataset based on which feature(s) are missing or incomplete, embodiments of the prevention can provide robustness and resilience to missing data.

Robust classifier

A system () for assessing fluid responsiveness includes an infusion pump () in communication with at least one processor (), and a plurality of physiological monitors () operable to receive physiological signals from an associated patient. Physiological signals () acquired from the associated patient () during a fluid challenge are synchronized with a timing signal () of the infusion pump () administering the fluid challenge. One or more dynamic indices and/or features () is calculated from the synchronized physiological signals (), and one or more dynamic indices and/or features () is calculated from baseline physiological signals () acquired from the associated patient () prior to the fluid challenge. A fluid responsiveness probability value () of the patient () is determined based on dynamic indices and/or features () from the synchronized physiological signals () and dynamic indices and/or features () from the baseline physiological signals ().

Method and system for assessing fluid responsiveness using multimodal data

The disclosure features visual assistive devices that include a detection apparatus configured to receive information about an environment surrounding a user of the visual assistive device, a communication apparatus configured to transmit information to the user, and an electronic processor coupled to the detection apparatus and the communication apparatus, and configured to: receive information about an activity of the user; filter the information about the environment surrounding the user based on the activity of the user; assign a priority rank to each element of the filtered information based on the activity of the user; and transmit at least some of the elements of the filtered information, according to the assigned priority ranks, to the user using the communication apparatus.

Growing community of inventors

Cambridge, MA, United States of America

Minnan Xu