| Autor: |
Salau, Ayodeji Olalekan, Pooja, M. R., Hasani, Nahla Flayyih, Braide, Sepiribo Lucky |
| Předmět: |
|
| Zdroj: |
Mathematical Modelling of Engineering Problems; Aug2022, Vol. 9 Issue 4, p1053-1060, 8p |
| Abstrakt: |
Predictive modeling of asthma characterized by the systematic use of Machine Learning and Deep Learning techniques to develop classification/prediction models is a vital tool which is being deployed in most of the computer mediated decision making processes. Spirometry, being one of the most commonly used lung function tests, helps in the diagnosis and continuous monitoring of asthma and is recommended by both the national and international guidelines for the management of the disease when compared to other pulmonary function tests. It has been found to be more reliable because it has more parametric values. Despite the generalization of the respiratory equations in spirometry with respect of selected ethnic groups, the equation yields a considerable difference when compared to the spirometric readings in the general population. In an effort to overcome such differences that deviate from actual observations, in this paper, we have proposed a neural network model that can output a vector of Tiffeneau-Pinelli Index. The neural network model for the prediction of Tiffeneau-Pinelli index was able to reproduce a vector of indices that very closely approximated the actual observed values with a very low estimated error with an optimized radial basis fit neural net. This can be used as a reliable means to estimate some of the vital lung function parameters irrespective of the differences in the general population. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
