Related Experiment Video
Updated: Aug 23, 2025
Measuring the Carotid to Femoral Pulse Wave Velocity Cf-PWV to Evaluate Arterial Stiffness
Published on: May 3, 2018
Classification and regression of stenosis using an in-vitro pulse wave data set: Dependence on heart rate, waveform
Alexander Mair1, Michelle Wisotzki1, Stefan Bernhard2
1Technische Hochschule Mittelhessen, Department Life Science Engineering, Wiesenstrasse 14, 35390 Gießen, Germany.
Insights
This study introduces a new cardiovascular dataset for diagnosing diseases using pulse-wave analysis. Machine learning accurately identified stenosis locations (93%) and estimated positions, advancing cardiovascular diagnostics.
Area of Science:
- Cardiovascular physiology
- Biomedical engineering
- Machine learning in healthcare
Background:
- Cardiovascular signals hold potential for diagnosing cardiovascular diseases.
- Pulse-wave analysis is a key area for harnessing this information.
- Inferring arterial properties from waveform measurements remains a challenge, limiting diagnostic applications.
Purpose of the Study:
- To create a publicly available dataset from an in-vitro cardiovascular simulator.
- To explore machine learning for classifying and regressing arterial properties from pressure signals.
- To investigate the influence of varying input conditions on diagnostic tasks.
Main Methods:
- Collected 800 measurements on a cardiovascular simulator with varied heart rates and waveform shapes.
- Focused on six distinct stenosis locations within the arterial system.
- Applied machine learning algorithms to features extracted from four peripheral pressure signals.
Main Results:
- Achieved 93% accuracy in distinguishing six different stenosis locations.
- Transfer function-based features outperformed signal shape features for classification.
- Estimated stenosis position with a root mean square error of 2.4 cm using a shallow neural network.
Conclusions:
- The developed dataset supports research into cardiovascular disease diagnosis.
- Transfer function features show promise for accurate stenosis classification.
- Further research should focus on minimizing the influence of boundary conditions for improved performance.
Background:
Data-based approaches promise to use the information in cardiovascular signals to diagnose cardiovascular diseases. Considerable effort has been undertaken in the field of pulse-wave analysis to harness this information. However, the inverse problem, inferring arterial properties from waveform measurements, is not well understood today. Consequently, uncertainties within the estimation hinder the diagnostic application of such methods.
Method:
This work contributes a publicly available data set measured at an in-vitro cardiovascular simulator, focusing on a set of input conditions (heart rate, waveform) and stenosis locations. Furthermore, a first attempt is undertaken to perform classification and regression on this data set using standard machine learning methods on features extracted from four peripheral pressure signals.
Results:
The locations of six different stenoses could be distinguished at high accuracy of 93%, where transfer function-based features outperformed features based solely on signal shape in almost all cases. Furthermore, regression on the stenosis position could be performed with a root mean square error of 2.4 cm along a 20 cm section of the arterial system using a shallow neural network. However, the performance difference between shape and transfer function features was not clear for this task.
Conclusion:
The data set contains 800 measurements and allows investigating the influence of different heart boundary conditions, such as heart rate and waveform shape, on classification and regression tasks. Extracting features that minimise this influence is a promising way of improving the performance of these tasks.
