View source for 18624576. MACHINE LEARNING BASED RECONSTRUCTION OF INTRACARDIAC ELECTRICAL BEHAVIOR BASED ON ELECTROCARDIOGRAMS simplified abstract (LAWRENCE LIVERMORE NATIONAL SECURITY, LLC)

=MACHINE LEARNING BASED RECONSTRUCTION OF INTRACARDIAC ELECTRICAL BEHAVIOR BASED ON ELECTROCARDIOGRAMS=


==Organization Name==

[[:Category:LAWRENCE LIVERMORE NATIONAL SECURITY, LLC|LAWRENCE LIVERMORE NATIONAL SECURITY, LLC]]


[[Category:LAWRENCE LIVERMORE NATIONAL SECURITY, LLC]]

==Inventor(s)==

[[:Category:Robert C. Blake of Mountain House CA (US)|Robert C. Blake of Mountain House CA (US)]][[Category:Robert C. Blake of Mountain House CA (US)]]

[[:Category:Thomas J. O'hara of Alameda CA (US)|Thomas J. O'hara of Alameda CA (US)]][[Category:Thomas J. O'hara of Alameda CA (US)]]

[[:Category:Mikel L. Landajuela of Dublin CA (US)|Mikel L. Landajuela of Dublin CA (US)]][[Category:Mikel L. Landajuela of Dublin CA (US)]]

[[:Category:Rushil Anirudh of Dublin CA (US)|Rushil Anirudh of Dublin CA (US)]][[Category:Rushil Anirudh of Dublin CA (US)]]

==MACHINE LEARNING BASED RECONSTRUCTION OF INTRACARDIAC ELECTRICAL BEHAVIOR BASED ON ELECTROCARDIOGRAMS - A simplified explanation of the abstract==


This abstract first appeared for US patent application 18624576 titled 'MACHINE LEARNING BASED RECONSTRUCTION OF INTRACARDIAC ELECTRICAL BEHAVIOR BASED ON ELECTROCARDIOGRAMS

'''Simplified Explanation''': This patent application describes a computer-based system and process for reconstructing the internal electrical behavior of a patient's heart using their electrocardiogram (ECG) data.

* The system reconstructs the patient's cardiac activation map and transmembrane potentials over time without the need for medical imaging or special equipment.
* Machine learning models, such as neural networks, are trained with ECGs and intracardiac electrical data to reconstruct the internal electrical behavior.
* The process can be performed using actual patient data or simulated data obtained through computer simulations.

'''Key Features and Innovation''':
* Reconstruction of internal electrical behavior of the heart based on ECG data.
* Utilization of machine learning models for accurate reconstruction.
* Ability to perform reconstruction without medical imaging or special equipment.

'''Potential Applications''':
* Cardiac diagnostics and monitoring.
* Treatment planning for cardiac conditions.
* Research in cardiology and electrophysiology.

'''Problems Solved''':
* Eliminates the need for invasive procedures for internal electrical behavior assessment.
* Provides a non-invasive and efficient method for analyzing cardiac activity.

'''Benefits''':
* Improved accuracy in reconstructing internal electrical behavior.
* Non-invasive and cost-effective approach to cardiac assessment.
* Enhanced understanding of cardiac conditions and treatment planning.

'''Commercial Applications''':
* Title: Non-Invasive Cardiac Electrical Behavior Reconstruction System.
* Potential commercial uses in healthcare institutions, research facilities, and medical device companies.
* Market implications include improved patient care, research advancements, and potential for new diagnostic tools.

'''Prior Art''':
Prior art related to this technology may include research on machine learning in cardiology, ECG analysis algorithms, and non-invasive cardiac imaging techniques.

'''Frequently Updated Research''':
Ongoing research in machine learning applications in cardiology, advancements in ECG analysis algorithms, and developments in non-invasive cardiac imaging technologies are relevant to this technology.

'''Questions about the Technology''':
1. How does this technology compare to traditional methods of assessing cardiac electrical behavior?
   - This technology offers a non-invasive and efficient alternative to traditional invasive procedures for assessing cardiac electrical behavior.
2. What are the potential limitations of using machine learning models for reconstructing internal electrical behavior?
   - Some limitations may include the need for large datasets for training the models and potential challenges in interpreting the results accurately.


==Original Abstract Submitted==

A computer-based system and process are disclosed for reconstructing the internal electrical behavior of a patient's heart based partly or wholly on the patient's electrocardiogram (ECG). The output of the process may include, for example, a cardiac activation map, and/or a representation of transmembrane potentials over time. The process advantageously does not require any medical imaging of the patient, and does not require any special medical equipment. For example, the patient's activation map and transmembrane potentials may be reconstructed based solely on a preexisting or newly-obtained 12-lead cardiac ECG of the patient. The process makes use of a machine learning model, such as a neural network based model, trained with actual and/or simulated ECGs and intracardiac electrical data (typically transmembrane potentials) of many thousands of patients. Because an insufficient quantity of such data exists for actual patients, model training may be performed using ECGs and intracardiac electrical data obtained through computer simulations.



[[Category:G06N3/04]]
[[Category:A61B5/327]]
[[Category:A61B5/367]]
[[Category:G06N3/08]]
[[Category:G16H50/20]]
[[Category:G16H50/50]]
[[Category:CPC_G06N3/04]]