Publication:
Characterization of the respiratory pattern variability of patients with different pressure support levels

Thumbnail Image
Files

Files

Characterization of the respiratory pattern variability of patients with different pressure support levels.pdf (239.57 KB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Giraldo, Beatriz F.
Chaparro Preciado, Javier Alberto
Pere Camina, Salvador Benito
Abstract (Spanish)
Uno de los problemas más difíciles en cuidados intensivos sigue siendo el proceso de interrupción de la ventilación mecánica, denominado proceso de destete. Tanto un retraso innecesario en el proceso de interrupción como un ensayo de destete demasiado precoz son indeseables. En este estudio, analizamos la variabilidad del patrón respiratorio utilizando la señal de volumen respiratorio de pacientes sometidos a dos niveles diferentes de ventilación con presión de soporte (PSV), antes de la retirada de la ventilación mecánica. Para caracterizar el patrón respiratorio, se analizaron las siguientes series temporales: tiempo inspiratorio, tiempo espiratorio, duración de la respiración, volumen corriente, tiempo inspiratorio fraccional, flujo inspiratorio medio y respiración rápida superficial. Se consideraron varias técnicas de modelización autorregresiva: modelos autorregresivos (AR), modelos autorregresivos de medias móviles (ARMA) y modelos autorregresivos con entrada exógena (ARX). Se utilizaron los siguientes métodos de clasificación: regresión logística (LR), análisis discriminante lineal (LDA) y máquinas de vectores soporte (SVM). Se analizaron 20 pacientes en ensayos de destete de la ventilación mecánica. Los pacientes, sometidos a dos niveles diferentes de PSV, se clasificaron como PSV baja y PSV alta. Se analizó la variabilidad de los patrones respiratorios de estos pacientes. Se extrajeron los parámetros más relevantes utilizando los métodos clasificadores. Los mejores resultados se obtuvieron con el rango intercuartílico y los errores finales de predicción de los modelos AR, ARMA y ARX. Se obtuvo una precisión del 95% (93% de sensibilidad y 90% de especificidad) cuando el rango intercuartílico del tiempo espiratorio y las series temporales de duración de la respiración se utilizaron un modelo LDA. Todos los clasificadores mostraron un buen compromiso entre sensibilidad y especificidad.
Abstract (English)
One of the most challenging problems in intensive care is still the process of discontinuing mechanical ventilation, called weaning process. Both an unnecessary delay in the discontinuation process and a weaning trial that is undertaken too early are undesirable. In this study, we analyzed respiratory pattern variability using the respiratory volume signal of patients submitted to two different levels of pressure support ventilation (PSV), prior to withdrawal of the mechanical ventilation. In order to characterize the respiratory pattern, we analyzed the following time series: inspiratory time, expiratory time, breath duration, tidal volume, fractional inspiratory time, mean inspiratory flow and rapid shallow breathing. Several autoregressive modeling techniques were considered: autoregressive models (AR), autoregressive moving average models (ARMA), and autoregressive models with exogenous input (ARX). The following classification methods were used: logistic regression (LR), linear discriminant analysis (LDA) and support vector machines (SVM). 20 patients on weaning trials from mechanical ventilation were analyzed. The patients, submitted to two different levels of PSV, were classified as low PSV and high PSV. The variability of the respiratory patterns of these patients were analyzed. The most relevant parameters were extracted using the classifiers methods. The best results were obtained with the interquartile range and the final prediction errors of AR, ARMA and ARX models. An accuracy of 95% (93% sensitivity and 90% specificity) was obtained when the interquartile range of the expiratory time and the breath duration time series were used a LDA model. All classifiers showed a good compromise between sensitivity and specificity.
Extent
4 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/2316
Collections

Collections

AB - Ecitrónica
References

M. J.F. and J. Kress, “Weaning patients from the ventilator,” The new england journal of medicine, vol. 367, pp. 2233–9, 2012.

J.-M. Boles, J. Bion, A. Connors, M. Herridge, B. Marsh, C. Melot, R. Pearl, H. Silverman, M. Stanchina, A. Vieillard-Baron, and T. Welte, “Weaning from mechanical ventilation,” Eur Respir J, vol. 29, no. 5, pp. 1033–1056, 2007.

J. P. Casaseca, M. Martin-Fernandez, and C. Alberola-Lopez, “Weaning from mechanical ventilation: a multimodal signal analysis,” IEEE Transactions on Biomedical Engineering, vol. 53, no. 7, pp. 1330– 1345, July 2006.

A. Kulkarni and V. Agarwal, “Extubation failure in intensive care unit: Predictors and management,” Indian J Crit Care Med, vol. 12, no. 1, pp. 1–9, 2008.

J.-C. Hsu, Y.-F. Chen, H.-H. Lin, C.-H. Li, and X. Jiang, “Construction of prediction module for successful ventilator weaning,” Lecture notes in computer science, no. 4570, pp. 766–775, 2007.

J. Durbin, “Efficient estimation of parameters in moving - average models,” Biometrika, vol. 46, no. 3 - 4, pp. 306–316, 1959.

P. M. T. Broersen, “Modified durbin method for accurate estimation of moving-average models,” IEEE Transaction on Instrumentation and measurement, vol. 58, no. 5, pp. 1361–1369, 2009.

P. Stoica, T. McKelvey, and J. Mari, “Ma estimation in polynomial time,” IEEE Trans. Signal Process., vol. 48, no. 7, p. 19992012, 2000.

P. M. T. Broersen, “Finite sample criteria for autoregressive order selection,” IEEE Trans Signal Processing, vol. 48, no. 12, pp. 3550– 3558, 2000.

B. F. Giraldo, J. Chaparro, D. Lpez-Rodrguez, D. Great, S. Benito, and P. Caminal, “Study of the respiratory pattern variability in patients during weaing trials,” Engineerring in Medicine and Biology Society, IEMBS, 2004.

J. A. Chaparro, B. F. Giraldo, P. Caminal, and S. Benito, “Analysis of the respiratory pattern variability of patients in weaning process using autoregressive modeling techniques,” Proc. IEEE Conf. Eng. Med. Biol., pp. 5690–5693, 2011.

L. Ljung, “System identification: Theory for the user,” Prentice-Hall, Englewood Cliffs, New Jersey, 1987.

S. Khorshidi and M. Karimi, “Modified aic and fpe criteria for autoregressive (ar) model order selection by using lsfb estimation method,” International Conference on Advances in Computational Tools for Engineering Applications, 2009.

G. Box, G. Jenkins, and G. Reinsel, “Time series analysis, forescasting and control,” Third Edition, Prentice Hall International Inc., 1994.

H.Tinsley and S. Brown, “Handbook of applied multivariate statistics and mathematical modeling,” Academic Press, 2000.

R. Jhonson and D. Wicher, “Applied multivariate statistical analysis,” Quinta Edicin, Editorial Prentice Hall Hispanoamericana., 2006.

A. Garde, R. Schroeder, A. Voss, P. Caminal, S. Benito, and B. F. Giraldo, “Patients on weaning trials classified with support vector machines,” Physiol. Meas., no. 31, p. 979993, 2010.

I. Steinwart and A. Chrismann, “Super vector machine, information science and statistics,” Editorial Springer., 2008.