International Business Machines Corporation

Xerox Corporation

University of Southern California

Other

Guerbet

Merative US L.p.

Tanveer Fathima Syeda-Mahmood

David James Beymer

Mehdi Moradi

Hongzhi Wang

Ehsan Dehghan Marvast

Yaniv Gur

Fei Wang

Ahmed El Harouni

Guy Maring Lohman

Peter Haas

John Michael Lake

Ashutosh Jadhav

Joy Tzung-yu Wu

Yu Long Cao

Arnon Amir

Ritwik K Kumar

Ali Madani

Chaitanya Shivade

Anup Pillai

Deepika Kakrania

Yufan Guo

Satyananda Kashyap

Vandana Mukherjee

Yong Zhang

Alexandros Karargyris

Karen Wolfe Brannon

Mohammadreza Negahdar

Marina Bendersky

Allen Lu

Simona Cohen

Amin Katouzian

Gopalkrishna Veni

Colin Compas

Amram Abutbul

Rui Zhang

Dulce Beatriz Ponceleon

Rahil Garnavi

Andrea Giovannini

Laura Chiticariu

Chun Lok Wong

Xi Liang

Sangeeta T Doraiswamy

Tyler Shore Baldwin

Quan Wang

Shafiqul Abedin

Hakan Bulu

Hayit Greenspan

Patrick McNeillie

Guy Talmor

Omar U F Choque

Dai Shi

John Paul Francis

Nripesh Parajuli

Simon Frank Wail

Ting Chen

Nimrod Megiddo

John C Handley

Thomas Guthrie Zimmerman

Prabhakar Raghavan

Cartic Ramakrishnan

Dragutin Petkovic

Noel C Codella

Lukas Rupprecht

Ashutosh Singh

Constantine Arnold

Deepta Rajan

John T Timm

Nitin Ramchandani

Hui Tang

Prasanth Prasanna

Moritz A W Hardt

Vaishnavi Subramanian

Girish Narayan

Alexandras Karargyris

Joy Wu

King Chung Ho

Mechanisms are provided to implement a machine learning framework that operates to register a plurality of machine learning algorithms used to train machine learning models to perform related tasks, and to index the machine learning algorithms to generate and store a machine learning algorithm metadata model for each machine learning algorithm. The machine learning framework receives a user specification of an analytics pipeline task for which a machine learning model is to be trained, and converts the user specification to machine learning algorithm search criteria used to search the index to identify matching machine learning algorithms having a corresponding machine learning algorithm metadata model that matches the machine learning algorithm search criteria. The machine learning framework outputs information describing the matching machine learning algorithms.

Machine learning model repository management and search engine

Mechanisms are provided to implement a visual analytics pipeline. The mechanisms generate, from an input database of records, a chronology-aware graph data structure of a plurality of records based features specified in an ontology data structure. The chronology-aware graph data structure has vertices representing one or more of events or records based features corresponding to events, and edges representing chronological relationships between events. The mechanisms execute a chronology-aware graph query on the chronology-aware graph data structure to generate a filtered set of vertices and corresponding features corresponding to criteria of the chronology-aware graph query. The mechanisms execute a pattern discovery operation on the filtered set of vertices and corresponding features to identify a subset of vertices and corresponding features that correspond to a relatively higher frequency set of patterns of event paths, and generate a visual analytics graphical representation for the subset of vertices and corresponding features.

Scalable visual analytics pipeline for large datasets

Mechanisms are provided to implement a patient summary generation engine with deduplication of instances of medical concepts. The patient summary generation engine parses a patient electronic medical record (EMR) to extract a plurality of instances of a medical concept, at least two of which utilize different representations of the medical concept. The patient summary generation engine performs a similarity analysis between each of the instances of a medical concept to thereby calculate, for a plurality of combinations of instances of the medical concept, a similarity metric value. The patient summary generation engine clusters the instances of the medical concept based on the calculated similarity metric values for each combination of instances in the plurality of combinations of instances of the medical concept to thereby generate one or more clusters, and select a representative instance of the medical concept from each cluster in the one or more clusters. The patient summary generation engine generates a summary output of the patient EMR comprising the selected representative instances of the medical concept from each cluster.

Deduplication of medical concepts from patient information

Mechanisms are provided to implement a machine learning training model. The machine learning training model trains an image generator of a generative adversarial network (GAN) to generate medical images approximating actual medical images. The machine learning training model augments a set of training medical images to include one or more generated medical images generated by the image generator of the GAN. The machine learning training model trains a machine learning model based on the augmented set of training medical images to identify anomalies in medical images. The trained machine learning model is applied to new medical image inputs to classify the medical images as having an anomaly or not.

Generative adversarial network medical image generation for training of a classifier

Mechanisms for implementing a text encoder and text encoder operations are provided. A contrastive machine learning training operation trains an encoder of a machine learning computer model, to learn a sense and similarity preserving embedding that operates to encode input natural language text data to generate encoded natural language text data based on a sense attribute of one or more terms in the input natural language text data. The contrastive machine learning training operation learns to separate positive samples in training data from negative samples in the training data. The trained encoder processes a term specified in an input natural language text to generate an encoded natural language text based on the learned embedding and inputs, to a downstream computing system, the encoded natural language text to cause the downstream computing system to perform a computer natural language processing operation based on the embedding.

Meaning and sense preserving textual encoding and embedding

A mechanism is provided for implement a discrepancy detection mechanism for detecting discrepancies between clinical notes and administrative records. Clinical concepts are extracted from the clinical notes and the administrative records in a patient's electronic medical records (EMRs). The extracted clinical concepts are filtered based on semantic type information to identify concepts that reference diseases or syndromes while also removing negated instances. Utilizing the positive mentions of diseases in clinical notes, the positive mentions of diseases or syndromes in the clinical notes are compared against each positive entry in the administrative records. A discrepancy summary is then generated for diseases or syndromes that failed to translate correctly from clinical notes to the administrative records in the patient's EMRs.

Detecting discrepancies between clinical notes and administrative records

Mechanisms are provided to improve an output of a trained machine learning (ML) computer model based on label co-occurrence statistics. For a corpus, label vector representations of the knowledge data structures are generated. Co-occurrence scores for each pairing of labels, across the label vector representations, are generated. A vector output of the ML computer model is received and a knowledge driven reasoning (KDR) computer model is configured with threshold(s) and delta value(s) specifying condition(s) of a co-occurrence of a first label in the output with a second label in the plurality of labels which, if present, causes the delta value(s) to be applied to modify a probability value associated with the second label in the output of the ML computer model. The KDR computer model is executed on the output of the ML computer model to modify probability value(s) in the output.

Combined deep learning and knowledge driven reasoning for artificial intelligence classification

A method and system for automatically inferring a subject's body position in a two-dimensional image produced by a medical-imaging system are disclosed. The image is labeled with a body position selected from a semantically meaningful set of candidate positions sequenced in order of their relative locations in a subject's body. A processor performs procedures that each identify a class of image features related to pixel intensity, such as a histogram of gradients, local binary patterns, or Haar-like features. A second set of procedures employs applications of a pretrained convolutional neural network that has learned to recognize features of a specific class of medical images. The results of both types of procedures are then mapped by a pretrained support-vector machine onto candidate image labels, which are mathematically combined into a single, semantically meaningful, label most likely to identify a body position of the subject shown by the image.

Identifying subject matter of a digital image

Mechanisms are provided to implement an automated echocardiograph measurement extraction system. The automated echocardiograph measurement extraction system receives medical imaging data comprising one or more medical images and inputs the one or more medical images into a deep learning network. The deep learning network automatically processes the one or more medical images to generate an extracted echocardiograph measurement vector output comprising one or more values for echocardiograph measurements extracted from the one or more medical images. The deep learning network outputs the extracted echocardiograph measurement vector output to a medical image viewer.

Automated extraction of echocardiograph measurements from medical images

Mechanisms are provided to implement a fine-grained finding descriptor generation computing tool that automatically generates fine-grained labels for downstream computer system operations. The mechanisms process medical report content based on a core finding lexicon, to extract core finding instances from the medical report content. The mechanisms execute, for each core finding instance, automated computer NLP operations that generate a parse tree for the portion of the medical report content corresponding to the core finding instance, perform phrasal grouping on the parse tree to thereby associate one or more modifiers of core findings specified in the portion of the medical report content with the core finding instance, and generate a fine-grained finding descriptor data structure for the core finding instance based on the association of one or more modifiers of the core finding with the core finding instance.

Extracting fine grain labels from medical imaging reports

Systems and methods for developing a classification model for classifying medical reports, such as radiology reports. One method includes selecting, from a corpus of reports, a training set and a testing set, assigning labels of a modality and an anatomical focus to the reports in both sets, and extracting a sparse representation matrix for each set based on features in the training set. The method also includes learning, with one or more electronic processors, a correlation between the features of the training set and the corresponding labels using a machine learning classifier, thereby building a classification model and testing the classification model on the reports in the testing set for accuracy using the sparse representation matrix of the testing set. The method further includes predicting, with the classification model, labels of an anatomical focus and a modality for remaining reports in the corpus not included in the sets.

Method and apparatus for selecting radiology reports for image labeling by modality and anatomical region of interest

Mechanisms are provided to implement an automated medical image processing pipeline selection (MIPPS) system. The MIPPS system receives medical image data associated with a patient electronic medical record and analyzes the medical image data to extract evidence data comprising characteristics of one or more medical images in the medical image data indicative of a medical image processing pipeline to select for processing the one or more medical images. The evidence data is provided to a machine learning model of the MIPPS system which selects a medical image processing pipeline based on a machine learning based analysis of the evidence data. The selected medical image processing pipeline processes the medical image data to generate a results output.

Determining appropriate medical image processing pipeline based on machine learning

A joint multimodal fusion computer model architecture is provided that receives prediction output data from a machine learning (ML) computer model set comprising a plurality of different subsets of ML computer models operating on input data of different modalities and generating different prediction outputs. Prediction outputs are fused by executing an uncertainty and correlation weighted (UCW) joint multimodal fusion operation on the prediction outputs to generate a fused output providing multimodal prediction output data. The UCW joint multimodal fusion operation applies different weights to different ones of prediction outputs from the different subsets of ML computer models operating on input data of different modalities. The different weights are determined based on an estimation of uncertainty in each of the different subsets of ML computer models and an estimate of a correlation between different modalities.

Multi-modal fusion techniques considering inter-modality correlations and computer model uncertainty

Growing community of inventors

Cupertino, CA, United States of America

Tanveer Fathima Syeda-Mahmood