Vascular Twin Surrogate Model for Hemodynamic Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current healthcare software solutions for predicting vascular behavior, particularly hemodynamic behavior, are either extremely resource-intensive or fail to accurately calibrate to individual patient anatomical and physiological features, leading to unreliable clinical measurements.
Innovation Solution
A computer-implemented method using a vascular model with a surrogate artificial neural network to predict vascular behavior, where the model is calibrated using inverse artificial neural networks trained on patient data, allowing for efficient prediction of hemodynamic behavior with reduced computational resources and improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional physics-based simulations are used to predict vascular behavior, then accuracy of hemodynamic prediction is improved, but computational resource consumption increases extremely
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the patient's vascular system that replicates hemodynamic behavior. This virtual model allows accurate prediction of vascular behavior without repeatedly running computationally expensive physics-based simulations on the actual patient data, thus resolving the contradiction between prediction accuracy and computational resource consumption
Solution Approach 2:
The patent performs preliminary calibration of the vascular model using patient-specific anatomical data and hemodynamic measurements before actual prediction tasks. This pre-calibration step establishes accurate baseline parameters that enable subsequent predictions to be made with reduced computational resources while maintaining high accuracy
2Reliability
If virtual twins are calibrated to match clinical measurements, then reliability of patient-specific model is improved, but complexity of calibration process increases
Solution Approach 1:
The patent adjusts key physiological parameters (such as vessel wall elasticity, blood viscosity, and boundary conditions) in the vascular model to match clinical measurements from the patient. By systematically varying and optimizing these parameters through automated calibration algorithms, the system achieves reliable patient-specific models while managing calibration complexity through structured parameter adjustment protocols
3Measurement precision
If more clinical measurements are collected for model calibration, then accuracy of vascular behavior prediction is improved, but time and cost of diagnosis increases
Solution Approach 1:
The patent introduces a surrogate model as an intermediary between clinical measurements and the full physics-based vascular simulation. This surrogate model provides approximate predictions that guide the calibration process, allowing the system to achieve accurate predictions with fewer clinical measurements by using the intermediary to bridge information gaps that would otherwise require additional measurements
Data Source
AI summary
A computer-implemented method for predicting vascular behavior of a patient, in particular a hemodynamic behavior. The method includes obtaining a vascular model of a circulatory system, one or more measurements of the vascular behavior of the patient, and a surrogate model comprising an artificial neural network. The vascular model represents a general vascular behavior and comprises a plurality of physiological parameters. The surrogate model is configured to predict a simulation of a vascular behavior from the physiological parameters. The method further includes calibrating the vascular model using the surrogate model and based on the one or more measurements; and predicting the vascular behavior of the patient using the calibrated vascular model.