Beatriz F. Giraldo

Correntropy-Based Spectral Characterization of Respiratory Patterns in Patients With Chronic Heart Failure

A correntropy-based technique is proposed for the characterization and classification of respiratory flow signals in chronic heart failure (CHF) patients with periodic or nonperiodic breathing (PB or nPB, respectively) and healthy subjects. The correntropy is a recently introduced, generalized correlation measure whose properties lend themselves to the definition of a correntropy-based spectral density (CSD). Using this technique, both respiratory and modulation frequencies can be reliably detected at their original positions in the spectrum without prior demodulation of the flow signal. Single-parameter classification of respiratory patterns is investigated for three different parameters extracted from the respiratory and modulation frequency bands of the CSD, and one parameter defined by the correntropy mean. The results show that the ratio between the powers in the modulation and respiratory frequency bands provides the best result when classifying CHF patients with either PB or nPB, yielding an accuracy of 88.9%. The correntropy mean offers excellent performance when classifying CHF patients versus healthy subjects, yielding an accuracy of 95.2% and discriminating nPB patients from healthy subjects with an accuracy of 94.4%.

Factores de riesgo de mortalidad en la EPOC

Objetivo Aunque los factores que predicen la supervivencia en pacientes con enfermedad pulmonar obstructive cronica (EPOC) han sido ampliamente estudiados, no disponemos de un consenso establecido. El objetivo de este estudio ha sido contribuir a clarificar el papel que desempenan los parametros de funcion pulmonar, tolerancia al esfuerzo y calidad de vida en la supervivencia en la EPOC. Pacientes y metodos Se diseno un estudio prospectivo en el que se incluyo a 60 pacientes diagnosticados de EPOC. Al inicio del estudio realizaron pruebas funcionales respiratorias, prueba de esfuerzo maximo y prueba de la marcha de 6 min, y respondieron un cuestionario de enfermedad respiratoria cronica para determinar la calidad de vida relacionada con la salud. El seguimiento de los pacientes fue de 7 anos. Resultados Se retiraron del estudio 5 de los 60 pacientes. De los 55 restantes, 26 (47%) murieron durante el estudio. El analisis univariante con regresion de Cox mostro que existia relacion entre la supervivencia y la edad, el grado de obstruccion, la capacidad inspiratoria, la capacidad de difusion del monoxido de carbono y la tolerancia al ejercicio maximo; no se observo dicha relacion entre la supervivencia y el indice de masa corporal, la presion arterial de oxigeno y anhidrido carbonico, la capacidad pulmonar total, el volumen residual, las presiones maximas respiratorias, la prueba de la marcha de 6 min ni la calidad de vida relacionada con la salud. En el analisis multivariante con regresion de Cox con pasos hacia adelante, en el que se introdujeron la edad, el grado de obstruccion (medido con la relacion volumen espiratorio forzado en el primer segundo/capacidad vital forzada tras la administracion de broncodilatador) y la ventilacion minuto maxima en la prueba de esfuerzo, solo esta ultima entro en el modelo final (riesgo relativo = 0,926; p Conclusiones Nuestros hallazgos demuestran que la tolerancia al ejercicio maximo es el mejor predictor de supervivencia en los pacientes con EPOC.

Variability analysis of the respiratory volume based on non-linear prediction methods

This work proposed and studied a method of automatically classifying respiratory volume signals as high or low variability by means of non-linear analysis of the respiratory volume. The analysis used volume signals generated by the respiratory system to construct a model of its dynamics and to estimate the quality of the predictions made with the model. Different methods of prediction evaluation, prediction horizons and embedding dimensions were also analysed. Assessment of the method was made using a database that contained 40 respiratory volume signals classified using clinical criteria into two classes: low or high variability. The results obtained using the method of surrogate data provided evidence of non-linear determinism in the respiratory volume signals. A discriminant analysis carried out using non-linear prediction variables classified the respiratory volume signals with an accuracy of 95%.

Symbolic Dynamic Analysis of Relations Between Cardiac and Breathing Cycles in Patients on Weaning Trials

Traditional time-domain techniques of data analysis are often not sufficient to characterize the complex dynamics of the cardiorespiratory interdependencies during the weaning trials. In this paper, the interactions between the heart rate (HR) and the breathing rate (BR) were studied using joint symbolic dynamic analysis. A total of 133 patients on weaning trials from mechanical ventilation were analyzed: 94 patients with successful weaning (group S) and 39 patients that failed to maintain spontaneous breathing (group F). The word distribution matrix enabled a coarse-grained quantitative assessment of short-term nonlinear analysis of the cardiorespiratory interactions. The histogram of the occurrence probability of the cardiorespiratory words presented a higher homogeneity in group F than in group S, measured with a higher number of forbidden words in group S as well as a higher number of words whose probability of occurrence is higher than a probability threshold in group S. The discriminant analysis revealed the best results when applying symbolic dynamic variables. Therefore, we hypothesize that joint symbolic dynamic analysis provides enhanced information about different interactions between HR and BR, when comparing patients with successful weaning and patients that failed to maintain spontaneous breathing in the weaning procedure.

Optimized symbolic dynamics approach for the analysis of the respiratory pattern

Traditional time domain techniques of data analysis are often not sufficient to characterize the complex dynamics of respiration. In this paper, the respiratory pattern variability is analyzed using symbolic dynamics. A group of 20 patients on weaning trials from mechanical ventilation are studied at two different pressure support ventilation levels, in order to obtain respiratory volume signals with different variability. Time series of inspiratory time, expiratory time, breathing duration, fractional inspiratory time, tidal volume and mean inspiratory flow are analyzed. Two different symbol alphabets, with three and four symbols, are considered to characterize the respiratory pattern variability. Assessment of the method is made using the 40 respiratory volume signals classified using clinical criteria into two classes: low variability (LV) or high variability (HV). A discriminant analysis using single indexes from symbolic dynamics has been able to classify the respiratory volume signals with an out-of-sample accuracy of 100%.

Support Vector Machine Classification Applied on Weaning Trials Patients

One of the most frequent reasons for instituting mechanical ventilation is to decrease patients work of breathing. Many attempts have been made to increase the effectiveness of the evaluation of the respiratory pattern with the analysis of the respiratory signals. This work proposes a method for the study of the differences in respiratory pattern variability in patients on weaning trials. The proposed method is based on a support vector machine using 35 features extracted from the respiratory flow signal. In this paper, a group of 146 patients with mechanical ventilation were studied: group S of 79 patients with successful weaning trials and group F of 67 patients that failed to maintain spontaneous breathing and were reconnected. Applying a feature selection procedure based on the use of the support vector machine with a leave-one-out cross-validation, it was obtained 86.67% of well classified patients on group S and 73.34% on group F, using only 8 of the 35 features. Therefore, support vector machine can be a classification method of the respiratory pattern variability useful in the study of patients on weaning trials

Time-frequency analysis of cardiac and respiratory parameters for the prediction of ventilator weaning

Mechanical ventilators are used to provide life support in patients with respiratory failure. Assessing autonomic control during the ventilator weaning provides information about physiopathological imbalances. Autonomic parameters can be derived and used to predict success in discontinuing from the mechanical support. Time-frequency analysis is used to derive cardiac and respiratory parameters, as well as their evolution in time, during ventilator weaning in 130 patients. Statistically significant differences have been observed in autonomic parameters between patients who are considered ready for spontaneous breathing and patients who are not. A classification based on respiratory frequency, heart rate and heart rate variability spectral components has been proposed and has been able to correctly classify more than 80% of the cases.

Breathing pattern characterization in chronic heart failure patients using the respiratory flow signal

This study proposes a method for the characterization of respiratory patterns in chronic heart failure (CHF) patients with periodic breathing (PB) and nonperiodic breathing (nPB), using the flow signal. Autoregressive modeling of the envelope of the respiratory flow signal is the starting point for the pattern characterization. Spectral parameters extracted from the discriminant frequency band (DB) are used to characterize the respiratory patterns. For each classification problem, the most discriminant parameter subset is selected using the leave-one-out cross-validation technique. The power in the right DB provides an accuracy of 84.6% when classifying PB vs. nPB patterns in CHF patients, whereas the power of the DB provides an accuracy of 85.5% when classifying the whole group of CHF patients vs. healthy subjects, and 85.2% when classifying nPB patients vs. healthy subjects.

Study of the respiratory pattern variability in patients during weaning trials

Mechanical ventilators are used to provide life support in patients with respiratory failure. One of the challenges in intensive care is the process of weaning from mechanical ventilation. We studied the differences in respiratory pattern variability between patients capable of maintaining spontaneous breathing during weaning trials and patients that fail to maintain spontaneous breathing. The respiratory pattern was characterized by the following time series: inspiratory time (T/sub I/), expiratory time (T/sub E/), breath duration (T/sub Tot/), tidal volume (V/sub T/), fractional inspiratory time (T/sub I//T/sub Tot/), mean inspiratory flow (V/sub T//T/sub I/), respiratory frequency (f), and rapid shallow breathing index (f/V/sub T/). The variational activity of breathing was partitioned into autoregressive, periodic and white noise fractions. Patients with unsuccessful trial presented a tendency to higher values of gross variability of V/sub T//T/sub I/ and f/V/sub T/, and lower values of T/sub I/. The autocorrelation coefficients tended to present higher values for T/sub I/, T/sub I//T/sub Tot/ and V/sub T//T/sub I/. During both successful and unsuccessful T-tube test uncorrelated random behavior constituted > 75% of the variance of each time breath components and represented 50 to 70% in the breath component related to V/sub T/. Correlated behavior represented 6 to 21% in time components and 28 to 50% in component related to V/sub T/.

Analysis of Respiratory Flow Signals in Chronic Heart Failure Patients with Periodic Breathing

In patients with chronic heart failure (CHF), oscillatory breathing pattern predicts poor prognosis. This work proposes a method to identify the respiratory pattern to determine periodic breathing (PB), Cheyne-Stokes respiration (CSR) and non-periodic respiratory patterns (nPB) through the respiratory flow signal. 26 patients are studied, classified in G1 (PB), G2 (CSR) and G3 (nPB). The flow signal is filtered and normalized, to obtain the positive envelope that describes the respiratory pattern. With this new signal some features are extracted through its power spectral density (PSD). An adaptive feature selection algorithm is applied before the linear and non linear classification applying Leave-one-out cross-validation technique. The result obtained with linear classification was 93% using the relation between total energy and frequency interval (ll), peak amplitude (ampp), peak frequency (fp), and the highest slope of the positive envelopes PSD (Slopemax). And the best result was obtained with non linear technique, with 100% correctly classified patients, using only two parameters, fp and Slopemax.