20240021310. Data Transformations to Create Canonical Training Data Sets simplified abstract (GOOGLE LLC)

From WikiPatents
Jump to navigation Jump to search

Data Transformations to Create Canonical Training Data Sets

Organization Name

GOOGLE LLC

Inventor(s)

Farhana Bandukwala of Mountain View CA (US)

Peter Brune of Mountain View CA (US)

Fanyu Kong of Mountain View CA (US)

David Roger Anderson of West Lakeville MN (US)

Data Transformations to Create Canonical Training Data Sets - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240021310 titled 'Data Transformations to Create Canonical Training Data Sets

Simplified Explanation

The patent application describes a method that involves using a dataset containing health data in the FHIR standard to generate an events table and a traits table. These tables are indexed by time and a unique identifier per patient encounter. A machine learning model is then trained using the events table and the traits table to predict health outcomes for patients based on additional healthcare events associated with them.

  • The method involves obtaining a dataset of health data in the FHIR standard.
  • The dataset is used to generate an events table indexed by time and a unique identifier per patient encounter.
  • The dataset is also used to generate a traits table indexed by the unique identifier per patient encounter.
  • A machine learning model is trained using the events table and the traits table.
  • The trained model is used to predict health outcomes for patients based on additional healthcare events associated with them.

Potential applications of this technology:

  • Predicting health outcomes for patients based on their healthcare events.
  • Assisting healthcare providers in making informed decisions about patient care.
  • Identifying patterns and trends in healthcare data to improve patient outcomes.

Problems solved by this technology:

  • The method provides a standardized way to process and analyze health data in the FHIR standard.
  • It allows for the efficient indexing and retrieval of healthcare events and static data.
  • The machine learning model can help identify potential health issues and provide early intervention.

Benefits of this technology:

  • Improved patient care and outcomes through predictive modeling.
  • Enhanced efficiency in processing and analyzing health data.
  • Potential cost savings by identifying and addressing health issues earlier.


Original Abstract Submitted

a method includes obtaining a dataset that includes health data in a fast healthcare interoperability resources (fhir) standard. the health data includes a plurality of healthcare events. the method includes generating, using the dataset, an events table that includes the plurality of healthcare events and is indexed by time and a unique identifier per patient encounter. the method also includes generating, using the dataset, a traits table that includes static data and is indexed by the unique identifier per patient encounter. the method includes training a machine learning model using the events table and the traits table and predicting, using the trained machine learning model and one or more additional healthcare events associated with a patient, a health outcome for the patient.

Retrieved from "http://wikipatents.org/index.php?title=20240021310._Data_Transformations_to_Create_Canonical_Training_Data_Sets_simplified_abstract_(GOOGLE_LLC)&oldid=28895"