View source for 18177199. USING A GAN FOR ELECTRONIC HEALTH RECORD EXTRAPOLATION simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

=USING A GAN FOR ELECTRONIC HEALTH RECORD EXTRAPOLATION=


==Organization Name==

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


[[Category:INTERNATIONAL BUSINESS MACHINES CORPORATION]]

==Inventor(s)==

[[:Category:VADIM Ratner of Haifa (IL)|VADIM Ratner of Haifa (IL)]][[Category:VADIM Ratner of Haifa (IL)]]

[[:Category:Yoel Shoshan of Haifa (IL)|Yoel Shoshan of Haifa (IL)]][[Category:Yoel Shoshan of Haifa (IL)]]

==USING A GAN FOR ELECTRONIC HEALTH RECORD EXTRAPOLATION - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18177199 titled 'USING A GAN FOR ELECTRONIC HEALTH RECORD EXTRAPOLATION

**Simplified Explanation:**
This patent application describes a method of using a generative adversarial network (GAN) to extrapolate Electronic Health Records (EHRs) for patients. The GAN generates artificial patient trajectories for a disease based on real EHR data, which can then be used to predict hypothetical patient trajectories or diagnoses for new patients.

**Key Features and Innovation:**
* Utilizes a generative adversarial network (GAN) to generate artificial patient trajectories for a disease.
* Trains the GAN using real EHR data to improve accuracy in predicting patient trajectories.
* Predicts hypothetical patient trajectories or latent diagnoses for new patients based on the trained GAN.

**Potential Applications:**
* Personalized medicine
* Disease progression modeling
* Clinical decision support systems

**Problems Solved:**
* Lack of personalized patient trajectory prediction
* Limited ability to extrapolate EHR data for new patients
* Enhancing accuracy in disease progression modeling

**Benefits:**
* Improved personalized healthcare
* Enhanced disease prediction and management
* Better clinical decision-making support

**Commercial Applications:**
* "Using Generative Adversarial Networks for EHR Extrapolation in Personalized Medicine"

**Prior Art:**
Prior research on GANs in healthcare data generation and disease progression modeling.

**Frequently Updated Research:**
Ongoing studies on the application of GANs in healthcare data analysis and prediction.

**Questions about GANs in Healthcare:**
1. How do GANs improve the accuracy of predicting patient trajectories in healthcare?
2. What are the potential limitations of using GANs for extrapolating EHR data in personalized medicine?


==Original Abstract Submitted==

A method of using a generative adversarial network (GAN) for EHR extrapolation is provided. The method includes obtaining EHRs for a plurality of patients. A generative component of the GAN is used to generate artificial patient trajectories for a disease that are marked as real by a discriminative component of the GAN based on the obtained EHRs. The artificial patient trajectories for the disease that are marked as real are used to iteratively train the GAN. The trained GAN is applied to a new patient EHR to predict at least one hypothetical patient trajectory or latent diagnosis for the disease.



[[Category:G16H10/60]]
[[Category:G06N3/08]]
[[Category:CPC_G16H10/60]]