Evaluation of Pulmonary Disease Using Static Lung Volumes Measurement in Primary Ciliary Dyskinesia

Soft computing analysis of data The Principal Component Analysis (PCA) methodology was applied to display data. PCA is a mathematical linear transformation aimed to scale the data in a three-dimensional uncorrelated space, in order to display statistically meaningful differences among the original variables while retaining as much as possible of the variance present in the original dataset. PCA projects the original data along new uncorrelated variables called principal components, i.e. the directions where the variances of data are maximized. These directions are determined by the eigenvectors of the covariance matrix of the original data corresponding to the largest eigenvalues. The prefix eigen-is adopted from the German word "eigen" for "own" in the sense of a characteristic description. The magnitude of the eigenvalues corresponds to the variance of the data along the eigenvector directions. In fact, for a given p-dimensional data set X, the m principal components Y 1 , Y 2 ,…, Ym, where 1<m<p, are orthonormal axes evaluated by the m leading eigenvectors of the covariance matrix, onto which the retained variance is maximum. The information of the observation vectors is contained in the subspace spanned by the first m principal components. Therefore, each original data vector can be represented by its principal component vector with dimensionality. Data were analyzed with soft computing methodologies. Basic elements of soft computing and the application of intelligent control have been recently introduced. The term soft computing denotes methodologies that seek to integrate arithmetical computing, reasoning and decision making into a framework trading off precision and uncertainty. The methodologies used are fuzzy logic, neural networks (NNs) and genetic algorithms and programming. [1] Soft computing-based models are capable of analyzing complex medical data, exploiting meaningful relationships in a data set to help physicians in the diagnosis, treatment and recognition of the clinical outcomes.