Google Inc.

Alvin Rishi Rajkomar

Katherine Irene Chou

Christopher S Co

William Ito

Rebecca Rolfe

Melissa Strader

Andrew M Dai

Kai Chen

James Wilson

Eyal Oren

Hector Yee

Michaela Hardt

Jeffrey Adgate Dean

Quoc V Le

Yi Zhang

Kun Zhang

Gregory Sean Corrado

Yingwei Cui

Nissan Hajaj

Peter Junteng Liu

Benjamin Irvine

James Wexler

Patrik Sundberg

Xiaomi Sun

Xiaobing Liu

Jacob Marcus

Jonas Beachey Kemp

Alexander Mossin

Ryan Michael Rifkin

Aren Jansen

Daniel Ellis

Henry George Wei

Gang Li

David Parish

Kurt Litsch

Daniel Shing Shun Tse

Gerardo Flores

Gavin Duggan

Philip Chung

Justin Paul

Diana Jaunzeikare

Michael Dwight Howell

Kasumi Widner

Michael Philip Brenner

Example embodiments relate to a method for training a predictive model from data. The method includes defining a multitude of predicates as binary functions operating on time sequences of the features or logical operations on the time sequences of the features. The method also includes iteratively training a boosting model by generating a number of new random predicates, scoring all the new random predicates by weighted information gain with respect to a class label associated with a prediction of the boosting model, selecting a number of the new random predicates with the highest weighted information gain and adding them to the boosting model, computing weights for all the predicates in the boosting model, removing one or more of the selected new predicates with the highest information gain from the boosting model in response to input from an operator. The method may include repeating the prior steps a plurality of times.

Human-in-the-loop interactive model training

The present disclosure provides systems and methods that generating health diagnostic information from an audio recording. A computing system can include a machine-learned health model comprising that includes a sound model trained to receive data descriptive of a patient audio recording and output sound description data. The computing system can include a diagnostic model trained to receive the sound description data and output a diagnostic score. The computing system can include at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the patient audio recording; inputting data descriptive of the patient audio recording into the sound model; receiving, as an output of the sound model, the sound description data; inputting the sound description data into the diagnostic model; and receiving, as an output of the diagnostic model, the diagnostic score.

System and method for generating diagnostic health information using deep learning and sound understanding

A method and workstation for generating a transcript of a conversation between a patient and a healthcare practitioner is disclosed. A workstation is provided with a tool for rendering of an audio recording of the conversation and generating a display of a transcript of the audio recording using a speech-to-text engine, thereby enabling inspection of the accuracy of conversion of speech to text. A tool is provided for scrolling through the transcript and rendering the portion of the audio according to the position of the scrolling. There is a highlighting in the transcript of words or phrases spoken by the patient relating to symptoms, medications or other medically relevant concepts. Additionally, there is provided a set of transcript supplement tools enabling editing of specific portions of the transcript based on the content of the corresponding portion of audio recording.

Method and system for generating transcripts of patient-healthcare provider conversations

A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order. An electronic device configured with a healthcare provider-facing interface displays the predicted one or more future clinical events and the pertinent past medical events of the patient.

System and method for predicting and summarizing medical events from electronic health records

A computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. The method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neural network having been trained to cause two image renditions associated with a same textual description to attract each other and two image renditions associated with different textual descriptions to repel each other based on mutual information between a plurality of corresponding pairs, wherein the plurality of corresponding pairs comprise an image-to-image pair and a text-to-image pair. The method further includes predicting the output image rendition of the scene.

Interface for patient-provider conversation and auto-generation of note or summary

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting future patient health using neural networks. One of the methods includes receiving electronic health record data for a patient; generating a respective observation embedding for each of the observations, comprising, for each clinical note: processing the sequence of tokens in the clinical note using a clinical note embedding LSTM to generate a respective token embedding for each of the tokens; and generating the observation embedding for the clinical note from the token embeddings; generating an embedded representation, comprising, for each time window: combining the observation embeddings of observations occurring during the time window to generate a patient record embedding; and processing the embedded representation of the electronic health record data using a prediction recurrent neural network to generate a neural network output that characterizes a future health status of the patient.

Processing clinical notes using recurrent neural networks

A method and system is provided for assisting a user to assign a label to words or spans of text in a transcript of a conversation between a patient and a medical professional and form groupings of such labelled words or spans of text in the transcript. The transcript is displayed on an interface of a workstation. A tool is provided for highlighting spans of text in the transcript consisting of one or more words. Another tool is provided for assigning a label to the highlighted spans of text. This tool includes a feature enabling searching through a set of predefined labels available for assignment to the highlighted span of text. The predefined labels encode medical entities and attributes of the medical entities. The interface further includes a tool for creating groupings of related highlighted spans of texts. The tools can consist of mouse action or key strokes or a combination thereof.

Capturing detailed structure from patient-doctor conversations for use in clinical documentation

A method for automatically generating a note summarizing a conversation between a patient and a healthcare provider is disclosed. A workstation is provided with a tool for rendering an audio recording of the conversation and a display for displaying a transcript of the audio recording obtained from a speech-to-text engine. The display of the workstation includes first transcript region for display of the transcript and a second note region for simultaneous displaying of elements of a note summarizing the conversation. Words or phrases in the transcript related to medical topics relating to the patient are extracted with the aid of a trained machine learning model. The extracted words or phrases are highlighted in the transcript and displayed in the note region. Links or a mapping between the extracted words or phrases in the note region and the portions of the transcript from which the extracted words or phrases originated are provided whereby the source and accuracy of the extracted words or phrases in the note region can be verified by a user.

Growing community of inventors

San Jose, CA, United States of America

Alvin Rishi Rajkomar