Non-invasive continuous blood pressure measurement based on mean impact value method, BP neural network, and genetic...

Area of Science:

• Biomedical Engineering
• Cardiovascular Technology
• Artificial Intelligence in Medicine

Background:

• Non-invasive continuous blood pressure monitoring is crucial for patient assessment and cardiovascular disease management.
• Existing methods using pulse wave transit time or parameters have limitations.
• Accurate, non-invasive blood pressure measurement is essential in clinical settings.

Purpose of the Study:

• To introduce a novel non-invasive continuous blood pressure measurement method: the GA-MIV-BP neural network model.
• To overcome the shortcomings of current blood pressure monitoring techniques.
• To improve the accuracy and clinical utility of non-invasive blood pressure assessment.

Main Methods:

• Utilized the Mean Impact Value (MIV) method to identify key blood pressure influencing factors from pulse wave data.
• Employed a Backpropagation (BP) neural network trained with selected factors and actual blood pressure values.
• Optimized model parameters using a Genetic Algorithm (GA) to create the GA-MIV-BP model.

Main Results:

• Bland-Altman analysis confirmed strong consistency and interchangeability between measured and predicted blood pressure values.
• The GA-MIV-BP model demonstrated reliable performance in non-invasive blood pressure estimation.
• Validation showed the model's potential for accurate continuous blood pressure tracking.

Conclusions:

• The developed GA-MIV-BP algorithm holds significant promise for advancing non-invasive continuous blood pressure monitoring.
• This method can facilitate broader clinical adoption of non-invasive blood pressure assessment tools.
• The study highlights the potential of AI-driven approaches in cardiovascular diagnostics.