Ge Precision Healthcare LLC

Travis Frosch

Garry M Whitley

Eszter Csernai

Erazmus Gerencser

Andras Kerekes

Elodie Weber

Bence Lantos

Manuel Vegas Santiago

Andras Lanczky

Steve M Lawson

Heather McCombs Chait

Sylvain Adam

Gopal Biligeri Avinash

Marc Thomas Edgar

Sylvie Jacquot Ingles

Anastasia Marie Van Dyke Dunn

Alvaro Molina

Weston R Olmstead

Systems and techniques that facilitate automated machine learning model feedback with data capture and synthetic data generation are provided. In various embodiments, a receiver component can receive electronic input identifying a deployed machine learning model. In various aspects, a listener component can retrieve from a data pipeline a data candidate that has been analyzed by the deployed machine learning model, an inference generated by the deployed machine learning model based on the data candidate, and an expert conclusion provided by a subject matter expert based on the data candidate. In various instances, a comparison component can compare the inference with the expert conclusion to determine whether the inference is consistent with the expert conclusion. In various cases, an augmentation component can, in response to a determination that the inference is not consistent with the expert conclusion, generate a set of synthetic training data based on the data candidate.

Automated machine learning model feedback with data capture and synthetic data generation

A computer-implemented system is provided that includes a plurality of endpoint databases employed to store medical images and metadata that describes attributes of the respective medical images. A management and orchestration platform periodically scans the endpoint databases to determine an index of the recently acquired medical images and associated metadata and updates to metadata associated with previously stored medical images. A search engine executes the search function to retrieve at least one of the recently acquired medical images and associated metadata and the recent updates to metadata associated with the previously stored medical images. The platform can also provide project management services and various collaborative, social networking type services. For example, the platform can facilitate collaborative review of medical image data, allowing users to rate and review the medical image data, annotate the medical image data, edit and augment the medical image data, and the like.

Federated, centralized, and collaborative medical data management and orchestration platform to facilitate healthcare image processing and analysis

Systems, methods, and apparatus to generate and utilize predictive workflow analytics and inferencing are disclosed and described. An example predictive workflow analytics apparatus includes a data store to receive healthcare workflow data including at least one of a schedule or a worklist including a patient and an activity in the at least one of the schedule or the worklist involving the patient. The example apparatus includes a data access layer to combine the healthcare workflow data with non-healthcare data to enrich the healthcare workflow data for analysis with respect to the patient. The example apparatus includes an inferencing engine to generate a prediction including a probability of patient no-show to the activity by processing the combined, enriched healthcare workflow data using a model and triggering a corrective action proportional to the probability of patient no-show.

Workflow predictive analytics engine

Techniques are provided for enhancing the efficiency and accuracy of annotating data samples for supervised machine learning algorithms using an advanced annotation pipeline. According to an embodiment, a method can comprise collecting, by a system comprising a processor, unannotated data samples for input to a machine learning model and storing the unannotated data samples in an annotation queue. The method further comprises determining, by the system, annotation priority levels for respective unannotated data samples of the unannotated data samples, selecting, by the system from amongst different annotation techniques, one or more of the different annotation techniques for annotating the respective unannotated data samples based the annotation priority levels associated with the respective unannotated data samples.

Annotation pipeline for machine learning algorithm training and optimization

Systems, methods, and apparatus to generate and utilize predictive workflow analytics and inferencing are disclosed and described. An example apparatus includes processor(s) to at least: generate a prediction including a probability of a patient no-show to a scheduled appointment using an artificial intelligence engine including a patient no-show model to predict the probability of the patient no-show based on a combination of healthcare workflow data and non-healthcare information; synchronize the prediction and a schedule including the scheduled appointment; and generate an interactive dashboard including the synchronized prediction and the schedule and at least one of: a) a first option to adjust the schedule to replace the patient based on the probability of the patient no-show orb) a second option to adjust the schedule to move the patient to a different time based on the probability of the patient no-show.

Growing community of inventors

Orlando, FL, United States of America

Travis Frosch