Dynamic Bayesian Networks for Longitudinal Hypertension Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cardiovascular disease diagnosis and management tools are inadequate, particularly for hypertension, as they fail to account for the fluctuating nature of blood pressure over time and lack transparency, leading to underdiagnosis and undertreatment.
Innovation Solution
A dynamic artificial intelligence model using causal inference engines and deep learning recurrent neural networks, combined with dynamic Bayesian belief networks, to accurately predict hypertension stages and support treatment management, incorporating clinical guidelines and expert validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional diagnostic tools are used for hypertension, then the system is simple and easy to operate, but the diagnosis accuracy is low and transparency is insufficient
Solution Approach 1:
The patent replaces traditional mechanical/deterministic diagnostic methods with artificial intelligence systems including deep learning recurrent neural networks and dynamic Bayesian belief networks. This substitution enables the system to achieve near 100% diagnosis accuracy by processing complex temporal patterns in blood pressure data, while the AI models provide transparent explanations for their predictions through interpretable computational processes.
2Measurement precision
If blood pressure is measured at a single time point, then the measurement process is simple and quick, but it fails to capture the fluctuating nature of hypertension
Solution Approach 1:
The patent implements continuous blood pressure monitoring over extended periods using wearable devices and electronic health records. The system processes temporal sequences of blood pressure measurements to capture fluctuations and patterns, achieving accurate hypertension detection by analyzing data across multiple time points rather than relying on single snapshots.
Solution Approach 2:
The patent employs dynamic diagnostic models that adapt to changing blood pressure patterns over time. The recurrent neural networks and Bayesian belief networks continuously update their assessments based on new measurements, allowing the system to detect hypertension accurately despite the fluctuating and variable nature of blood pressure readings.
3Reliability
If AI models are used to improve diagnosis accuracy, then prediction fidelity increases to nearly 100%, but model complexity and computational requirements increase
Solution Approach 1:
The patent divides the diagnostic system into multiple specialized components: recurrent neural networks for temporal pattern recognition, dynamic Bayesian belief networks for probabilistic reasoning, and explainable AI modules for transparency. This segmentation allows each component to handle specific aspects of the diagnostic challenge, achieving high reliability while maintaining manageable complexity through modular architecture.
Data Source
AI summary
Technology is described for identifying hypertension in a person. The method can include identifying a first group of medical features for a person at a first time point and a second group of medical features for the person at a second time point. An additional operation may be determining a time difference interval between the first time point and the second time point. The first group of medical features may be processed using an initial Bayesian belief network. An initial hypertension classification may also be received from the initial Bayesian belief network. In a further operation, the second group of medical features may be processed with an additional Bayesian belief network, while using the initial hypertension classification and the time difference interval as inputs. A joint hypertension classification may be obtained from the additional Bayesian belief network.