View source for 17930477. CREATING SYNTHETIC PATIENT DATA USING A GENERATIVE ADVERSARIAL NETWORK HAVING A MULTIVARIATE GAUSSIAN GENERATIVE MODEL simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

=CREATING SYNTHETIC PATIENT DATA USING A GENERATIVE ADVERSARIAL NETWORK HAVING A MULTIVARIATE GAUSSIAN GENERATIVE MODEL=


==Organization Name==

[[:Category:INTERNATIONAL BUSINESS MACHINES CORPORATION|INTERNATIONAL BUSINESS MACHINES CORPORATION]]


[[Category:INTERNATIONAL BUSINESS MACHINES CORPORATION]]

==Inventor(s)==

[[:Category:Daniel Enoch Platt of Putnam Valley NY (US)|Daniel Enoch Platt of Putnam Valley NY (US)]][[Category:Daniel Enoch Platt of Putnam Valley NY (US)]]

[[:Category:Aritra Bose of White Plains NY (US)|Aritra Bose of White Plains NY (US)]][[Category:Aritra Bose of White Plains NY (US)]]

[[:Category:Kahn Rhrissorrakrai of Woodside NY (US)|Kahn Rhrissorrakrai of Woodside NY (US)]][[Category:Kahn Rhrissorrakrai of Woodside NY (US)]]

[[:Category:Aldo Guzman Saenz of White Plains NY (US)|Aldo Guzman Saenz of White Plains NY (US)]][[Category:Aldo Guzman Saenz of White Plains NY (US)]]

[[:Category:Niina Haiminen of Tampere (FI)|Niina Haiminen of Tampere (FI)]][[Category:Niina Haiminen of Tampere (FI)]]

[[:Category:Laxmi Parida of Mohegan Lake NY (US)|Laxmi Parida of Mohegan Lake NY (US)]][[Category:Laxmi Parida of Mohegan Lake NY (US)]]

==CREATING SYNTHETIC PATIENT DATA USING A GENERATIVE ADVERSARIAL NETWORK HAVING A MULTIVARIATE GAUSSIAN GENERATIVE MODEL - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17930477 titled 'CREATING SYNTHETIC PATIENT DATA USING A GENERATIVE ADVERSARIAL NETWORK HAVING A MULTIVARIATE GAUSSIAN GENERATIVE MODEL

==Simplified Explanation==

The patent application describes a computer-implemented method for encoding and generating synthetic versions of risk factor variables using a multivariate Gaussian generative model.

* Processor system encodes binary, genotypic, and continuous risk factor variables.
* Adversarially trains a multivariate Gaussian generative model.
* Generates synthetic versions of the risk factor variables.

== Potential Applications ==
This technology could be applied in:
* Healthcare for generating synthetic patient data for research purposes.
* Finance for simulating risk factors in economic models.

== Problems Solved ==
This technology helps in:
* Protecting sensitive data by using synthetic versions for analysis.
* Generating diverse datasets for training machine learning models.

== Benefits ==
The benefits of this technology include:
* Improved privacy protection for sensitive information.
* Enhanced data diversity for more robust analysis.

== Potential Commercial Applications ==
* Optimizing marketing strategies using synthetic customer data.
* Enhancing cybersecurity by simulating various risk scenarios.


==Original Abstract Submitted==

Embodiments are directed to a computer-implemented method that includes using a processor system to encode binary risk factor variables, genotypic risk factor variables, and continuous risk factor variables. The processor system is further used to adversarially train a multivariate Gaussian (MVG) generative model to generate synthetic versions of the binary risk factor variables, synthetic versions of the genotypic risk factor variables, and synthetic versions of the continuous risk factor variables.



[[Category:G16H50/70]]
[[Category:G16H50/30]]