20230170057. ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
- 1 ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
James R. Kozloski of New Fairfield CT (US)
Viatcheslav Gurev of Bedford Hills NY (US)
Tim Rumbell of Raleigh NC (US)
ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20230170057 titled 'ASSOCIATING COMPLEX DISEASE SCORES AND BIOMARKERS WITH MODEL PARAMETERS USING MODEL INVERSE SURROGATES
Simplified Explanation
The abstract describes a method, computer system, and computer program product for model inversion. This involves training a generator of a generative adversarial network to sample input parameters for a mechanistic model, generating a distribution of parameters for the model, and simulating the model using the parameter distribution.
- The invention involves training a generator of a generative adversarial network.
- The generator is trained to sample a distribution of input parameters for a mechanistic model.
- A distribution of parameters is generated for the mechanistic model.
- The mechanistic model is then simulated using the generated parameter distribution.
Potential Applications
- This technology can be applied in various fields where mechanistic models are used, such as physics, chemistry, biology, and engineering.
- It can be used for predictive modeling, optimization, and analysis of complex systems.
- It can assist in understanding and predicting the behavior of physical or biological systems.
Problems Solved
- Model inversion allows for the estimation of model parameters based on observed data, which can be challenging in complex systems.
- The use of generative adversarial networks helps in generating realistic parameter distributions for the mechanistic model.
- The method provides a more efficient and accurate way to simulate the mechanistic model with a distribution of parameters.
Benefits
- The technology enables the generation of parameter distributions for mechanistic models, allowing for better understanding and analysis of complex systems.
- It provides a more efficient and automated approach to model inversion, reducing the need for manual parameter estimation.
- The use of generative adversarial networks improves the accuracy and realism of the generated parameter distributions.
Original Abstract Submitted
a method, computer system, and a computer program product for model inversion is provided. the present invention may include training a generator of a generative adversarial network to sample a distribution of input parameters of a mechanistic model. the present invention may include generating a distribution of parameters for the mechanistic model. the present invention may include simulating the mechanistic model with the distribution of parameters.
