Charleston-Villalobos Sonia, Castaneda-Villa Norma, Gonzalez-Camarena Ramon, Mejia-Avila M, Mateos-Toledo H, Aljama-Corrales Tomas
Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug;2016:3175-3178. doi: 10.1109/EMBC.2016.7591403.
The combined pulmonary fibrosis emphysema syndrome (CPFES) overall has a poor prognosis with a 5-year survival of 35-80%. Consequently, to evaluate possible positive effects on patients of novel agents as pirfenidone is relevant. However, the efficacy of pirfenidone in CPFES patients is still not well-known. In this study we propose an alternative to evaluate the effects of pirfenidone treatment on CPFES patients via acoustic information. Quantitative analysis of discontinuous adventitious lung sounds (DLS), known as crackles, has been promising to detect and characterize diverse pulmonary pathologies. The present study combines independent components (ICs) analysis of LS and the automated selection of ICs associated with DLS. ICs's features as fractal dimension, entropy and sparsity produce several clusters by kmeans. Those clusters containing ICs of DLS are exclusively considered to finally estimate the number of DLS per ICs by a time-variant AR modeling. For the evaluation of the effects of pirfenidone, the 2D DLS-ICs spatial distribution in conjunction with the estimated number of DLS events are shown. The methodology is applied to two real cases of CPFES with 6 and 12 months of treatment. The acoustical evaluation indicates that pirfenidone treatment may not be satisfactory for CPFES patients but further evaluation has to be performed.
