Systems and methods for creating and selecting models for predicting medical conditions
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-9824190-B2
Publication Date
2017-11-21
Expiration Date
Abstract
Systems and methods are provided for selecting one or more models for predicting medical conditions. An exemplary method may include receiving data related to a patient and extracting metadata from the received data. The method may further include selecting the one or more models from a library of models based on the extracted metadata and applying the selected one or more models. The method also may include generating a notification when the application of the selected one or more model indicates an intervention is necessary.
Core Innovation
The invention relates to a computer-implemented method for selecting one or more models for predicting medical conditions. The method receives initial data related to a user, including blood glucose levels, nutrition consumed, times of day associated with checking blood glucose, sleep, exercise performed, medication consumed, and mood, with blood glucose levels received wirelessly over a server from a continuous glucose monitoring (CGM) device and self-monitored blood glucose data.
The method processes the initial data using one or more machine learning algorithms to identify patterns between the blood glucose levels and the user factors including nutrition consumed, sleep, exercise, medication, and mood, including patterns involving times of day associated with checking blood glucose and times of day associated with nutrition consumed. The method assigns values to an additional data category for which no measured data is received, and then processes the additional data category to identify one or more patterns between the additional data category and the same user factors.
After creating a library of models containing a plurality of models based on the identified patterns, the method receives additional data related to the user, again including blood glucose levels from CGM and self-monitored blood glucose data. The method extracts metadata indicating whether a stream of blood glucose data is continuous glucose monitor data or self-monitored blood glucose data, selects the appropriate one or more models from the library based on that extracted metadata, applies the selected models, and generates a notification when the application indicates an intervention is necessary.
Claims Coverage
Independent claims are present in clm-00001, clm-00012, and clm-00014. They cover a selection-and-prediction framework with a library of models, metadata-based model selection for continuous glucose monitor data and self-monitored blood glucose data, and notification generation when intervention is necessary.
Model library creation from identified patterns
creating a library of models containing a plurality of models based on the identified patterns
CGM and self-monitored blood glucose data reception
receiving initial data wirelessly over a server from a continuous glucose monitoring (CGM) device and receiving self-monitored blood glucose data
Additional data category with assigned values
assigning values to an additional data category for which no measured data is received and processing the additional data category to identify patterns
Metadata extraction for CGM vs self-monitored model selection
extracting metadata indicating whether a given stream of data relating to blood glucose levels is continuous glucose monitor data or self-monitored blood glucose data
Conditional model type selection based on extracted metadata
selecting a first type of model when the extracted metadata indicates that the blood glucose levels are continuous glucose monitor data, selecting a second type of model when the extracted metadata indicates that the blood glucose levels are self-monitored blood glucose data, and selecting the second type of model when the extracted metadata indicates that the blood glucose levels include both continuous glucose monitor data and self-monitored blood glucose data
Notification when intervention is necessary
generating a notification when the application of the selected one or more models indicates an intervention is necessary
The claim coverage centers on building a library of models from identified patterns, using extracted metadata to select model type(s) based on CGM and self-monitored blood glucose data, and generating a notification when intervention is necessary.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?