Mining data from hemodynamic simulations for generating prediction and explanation models
| Autor: | Zoran Bosnić, Petar Vračar, Igor Kononenko, Goran Devedzic, Milos Radovic, Nenad Filipovic |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Databases
Factual Computer science Quantitative Biology::Tissues and Organs Reliability (computer networking) Physics::Medical Physics 02 engineering and technology Data modeling Software 020204 information systems 0202 electrical engineering electronic engineering information engineering Shear stress Data Mining Humans Carotid Stenosis Computer Simulation Electrical and Electronic Engineering Simulation Bifurcation Models Statistical Artificial neural network business.industry Work (physics) Hemodynamics Models Cardiovascular Reproducibility of Results General Medicine Computer Science Applications Carotid Arteries Regression Analysis 020201 artificial intelligence & image processing Neural Networks Computer business Algorithm Predictive modelling Biotechnology |
| Zdroj: | IEEE Transactions on Information Technology in Biomedicine |
| ISSN: | 1558-0032 |
| Popis: | Arterial geometry variability is present both within and across individuals. To analyze the influence of geometric parameters on maximal wall shear stress (MWSS) in the human carotid artery bifurcation, the computer simulations were run to generate the data pertaining to this phenomenon. In our work we evaluate various prediction models for modeling relationship between geometric parameters of the carotid bifurcation and the MWSS. The results revealed the highest potential of using the neural network model for this prediction task. The achieved results and generated explanations of the prediction model represent progress in assessment of stroke risk for a given patient's geometry in real time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|