Graphic summary
  • Show / hide key
  • Information


Scientific and technological production
  •  

1 to 50 of 206 results
  • Blood pressure variability analysis in supine and sitting position of healthy subjects

     Giraldo Giraldo, Beatriz F.; Calvo, Alejandro; Martínez, Beatriz; Arcentales Viteri, Andrés Ricardo; Jane Campos, Raimon; Benito Vales, Salvador
    DOI: 10.1007/978-3-319-00846-2_253
    Date of publication: 2014
    Book chapter

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Blood pressure carries a great deal of information about people¿s physical attributes. We analyzed the blood pressure signal in healthy subjects considering two positions, supine and sitting. 44 healthy subjects were studied. Parameters extracted from the blood pressure signal, related to time and frequency domain were used to compare the effect of postural position between supine and sitting. In time domain analysis, the time systolic interval and the time of blood pressure interval were higher in supine than in sitting position (p = 0.001 in both case). Parameters related to frequency peak, interquartile range, in frequency domain presented statistically significant difference (p¿< 0.0005 in both case). The blood pressure variability parameters presented smaller values in supine than in sitting position (p¿< 0.0005). In general, the position change of supine to sitting produces an increment in the pressure gradient inside heart, reflected in the blood pressure variability.

  • SVM-based feature selection to optimize sensitivity¿specificity balance applied to weaning

     Garde Martinez, Ainara; Voss, Andreas; Caminal Magrans, Pedro; Benito Vales, Salvador; Giraldo Giraldo, Beatriz F.
    Computers in biology and medicine
    Vol. 43, num. 5, p. 533-540
    DOI: 10.1016/j.compbiomed.2013.01.014
    Date of publication: 2013
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Classification algorithms with unbalanced datasets tend to produce high predictive accuracy over the majority class, but poor predictive accuracy over the minority class. This problem is very common in biomedical datamining. This paper introduces a Support Vector Machine (SVM)- based optimized feature selection method, to select the most relevant features and maintain an accurate and well- balanced sensitivity¿specificity result between unbalanced groups. A new metric called the balance index (B) is defined to implement this optimization. The balance index measures the difference between the misclassified data within each class. The proposed optimized feature selection is applied to the classification of patients¿ weaning trials from mechanical ventilation: patients with successful trials who were able to maintain spontaneous breathing after 48h and patients who failed to maintain spontaneous breathing and were reconnected to mechanical ventilation after 30min.

    Classification algorithms with unbalanced data sets tend to produce high predictive accuracy over the majority class, but poor predictive accuracy over the minority class. This problem is very common in biomedical data mining. This paper introduces a Support Vector Machine(SVM)-based optimized features election method, to select the most relevant features and maintain an accurate and well-balanced sensitivity–specificity result between unbalanced groups. A new metric called the balance index(B) is defined to implement this optimization. The balance index measures the difference between the misclassified data within each class. The proposed optimized feature selection is applied to the classification of patients’ weaning trials from mechanical ventilation: patients with successful trials who were able to maintain spontaneous breathing after 48 h and patients who failed to maintain spontaneous breathing and were reconnected to mechanical ventilation after 30min. Patients are characterized through cardiac and respiratory signals, applying joint symbolic dynamic (JSD) analys is to cardiac interbeat and breath durations. First, the most suitable parameters (C þ ,C ,s)are selected to define the appropriate SVM. Then, the features election process is carried out with this SVM, to maintain B lower than 40%. The best result is obtained using 6 features with an accuracy of 80%, a B of 18.64%, a sensitivity of 74.36% and a specificity of 82.42%.

  • Jornades de Recerca EUETIB 2013

    Date of publication: 2013-12-04
    Book

    Read the abstract Read the abstract  Share Reference managers Reference managers Open in new window

    Les Jornades de recerca 2013 es programen, dissenyen i realitzen amb l'objectiu d'afavorir l'assistència dels estudiants, així com la seva participació activa. Inicialment, les jornades eren reunions entre investigadors per ara esdevenir trobades obertes a tota la comunitat acadèmica. En aquestes es visibilitza l'activitat dels investigadors i la seva contextualització amb la docència reglada a l'EUETIB posant a la seva disposició dels dos col·lectius (PDI i estudiants) nous marcs de col·laboració

  • Analysis of heart rate variability in elderly patients with chronic heart failure and periodic breathing

     Giraldo Giraldo, Beatriz F.; Tellez Gabriel, Juan Pablo; Herrera Mateo, Sergio; Benito Vales, Salvador
    Computing in Cardiology
    p. 991-994
    Presentation's date: 2013-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Assessment of the dynamic interactions between cardiovascular signals can provide valuable information that improves the understanding of cardiovascular control. Heart rate variability (HRV) analysis is known to provide information about the autonomic heart rate modulation mechanism. Using the HRV signal, we aimed to obtain parameters for classifying patients with and without chronic heart failure (CHF), and with periodic breathing (PB), non-periodic breathing (nPB), and Cheyne-Stokes respiration (CSR) patterns. An electrocardiogram (ECG) and a respiratory flow signal were recorded in 36 elderly patients: 18 patients with CHF and 18 patients without CHF. According to the clinical criteria, the patients were classified into the follow groups: 19 patients with nPB pattern, 7 with PB pattern, 4 with Cheyne-Stokes respiration (CSR), and 6 non-classified patients (problems with respiratory signal). From the HRV signal, parameters in the time and frequency domain were calculated. Frequency domain parameters were the most discriminant in comparisons of patients with and without CHF: P Tot (p = 0.02), PLF (p = 0.022) and fpHF (p = 0.021). For the comparison of the nPB vs. CSR patients groups, the best parameters were RMSSD (p = 0.028) and SDSD (p = 0.028). Therefore, the parameters appear to be suitable for enhanced diagnosis of decompensated CHF patients and the possibility of developed periodic breathing and a CSR pattern.

  • Access to the full text
    Methodology for determine the moment of disconnection of patients of the mechanical ventilation using neural network  Open access

     Arizmendi Pereira, Carlos Julio; Giraldo Giraldo, Beatriz F.; Gonzalez Acevedo, Hernando; Acevedo, Holmann Erick
    Latin American and Caribbean Conference for Engineering and Technology
    p. 1-6
    Presentation's date: 2013-08
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    The process of weaning from mechanical ventilation is one of the challenges in intensive care units. In this paper 66 patients under extubation process (T-tube test) were studied: 33 patients with successful trials and 33 patients who failed to maintain spontaneous breathing and were reconnected. Each patient was characterized using 7 time series from respiratory signals, and for each serie was extracted 4 statistics data. Two types of Neural Networks were applied for discriminate between patients from the two groups: radial basis function and multilayer perceptron, getting better results with the second type of network.

  • Characterization of blood pressure signal considering low and high risk stratification in cardiomyopathy patients

     Arcentales Viteri, Andrés Ricardo; Voss, Andreas; Caminal Magrans, Pedro; Bayés Genis, Antoni; Domingo, Maite; Giraldo Giraldo, Beatriz F.
    Computing in Cardiology
    p. 795-798
    Presentation's date: 2013-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Ischemic and dilated cardiomyopathy are associated with disorders of myocardium. Using the blood pressure (BP) signal and the values of the ventricular ejection fraction, we obtained parameters for stratifying cardiomyopathy patients as low- and high-risk. We studied 48 cardiomyopathy patients characterized by NYHA '22: 19 patients with dilated cardiomyopathy (DCM) and 29 patients with ischemic cardiomyopathy (lCM). The left ventricular ejection fraction (LVEF) percentage was used to classify patients in low risk (LR: LVEF > 35%, 17 patients) and high risk (HR: LVEF::; 35%, 31 patients) groups. From the BP signal, we extracted the upward systolic slope (BPsl), the difference between systolic and diastolic BP (B P A), and systolic time intervals (ST I). When we compared the LR and HR groups in the time domain analysis, the best parameters were standard deviation (SD) of 1/ ST I, kurtosis (K) of B Psl, and K of B P A. In the frequency domain analysis, very low frequency (VLF) and high frequency (HF) bands showed statistically significant differences in comaprisons of LR and HR groups. The area under the curve of power spectral density was the best parameter in all classifications, and particularly in the very low- and high- frequency bands (p < 0.001). These parameters could help to improve the risk stratification of cardiomyopathy patients.

    Ischemic and dilated cardiomyopathy are associated with disorders of myocardium. Using the blood pressure (BP) signal and the values of the ventricular ejection fraction, we obtained parameters for stratifying cardiomyopathy patients as low- and high-risk. We studied 48 cardiomyopathy patients characterized by NYHA '22: 19 patients with dilated cardiomyopathy (DCM) and 29 patients with ischemic cardiomyopathy (lCM). The left ventricular ejection fraction (LVEF) percentage was used to classify patients in low risk (LR: LVEF > 35%, 17 patients) and high risk (HR: LVEF::; 35%, 31 patients) groups. From the BP signal, we extracted the upward systolic slope (BPsl), the difference between systolic and diastolic BP (B P A), and systolic time intervals (ST I). When we compared the LR and HR groups in the time domain analysis, the best parameters were standard deviation (SD) of 1/ ST I, kurtosis (K) of B Psl, and K of B P A. In the frequency domain analysis, very low frequency (VLF) and high frequency (HF) bands showed statistically significant differences in comaprisons of LR and HR groups. The area under the curve of power spectral density was the best parameter in all classifications, and particularly in the very low- and high- frequency bands (p < 0.001). These parameters could help to improve the risk stratification of cardiomyopathy patients.

  • Study of the oscillatory breathing pattern in elderly patients

     Giraldo Giraldo, Beatriz F.; Tellez Gabriel, Juan Pablo; Herrera Mateo, Sergio; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 5228-5231
    DOI: 10.1109/EMBC.2013.6610727
    Presentation's date: 2013-06
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Some of the most common clinical problems in elderly patients are related to diseases of the cardiac and respiratory systems. Elderly patients often have altered breathing patterns, such as periodic breathing (PB) and Cheyne-Stokes respiration (CSR), which may coincide with chronic heart failure. In this study, we used the envelope of the respiratory flow signal to characterize respiratory patterns in elderly patients. To study different breathing patterns in the same patient, the signals were segmented into windows of 5 min. In oscillatory breathing patterns, frequency and time-frequency parameters that characterize the discriminant band were evaluated to identify periodic and non-periodic breathing (PB and nPB). In order to evaluate the accuracy of this characterization, we used a feature selection process, followed by linear discriminant analysis. 22 elderly patients (7 patients with PB and 15 with nPB pattern) were studied. The following classification problems were analyzed: patients with either PB (with and without apnea) or nPB patterns, and patients with CSR versus PB, CSR versus nPB and PB versus nPB patterns. The results showed 81.8% accuracy in the comparisons of nPB and PB patients, using the power of the modulation peak. For the segmented signal, the power of the modulation peak, the frequency variability and the interquartile ranges provided the best results with 84.8% accuracy, for classifying nPB and PB patients.

  • Coherence between respiratory flow signal and heart rate variability applied to classify weaning trials patients

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador
    IBEC Symposium on Bioengineering and Nanomedicine
    Presentation's date: 2013-05-05
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Influence of respiration in the very low frequency modulation of QRS slopes and heart rate variability in cardiomyopathy patients

     Hernando, David; Alcaine, A; Pueyo, Esther; Laguna, Pablo; Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Voss, Andreas; Bayés Genis, Antoni; Bailón, Raquel
    Computing in Cardiology
    p. 117-120
    Presentation's date: 2013-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    This work investigates the very low frequency (VLF) modulation of QRS slopes and heart rate variability (HRV). Electrocardiogram (ECG) and respiratory flow signal were acquired from patients with dilated cardiomyopathy and ischemic cardiomyopathy. HRV as well as the upward QRS slope (IUS) and downward QRS slope (IDS) were extracted from the ECG. The relation between HRV and QRS slopes in the VLF band was measured using ordinary coherence in 5-minute segments. Partial coherence was then used to remove the influence that respiration simultaneously exerts on HRV and QRS slopes. A statistical threshold was determined, below which coherence values were considered not to represent a linear relation.

    This work investigates the very low frequency (VLF) modulation of QRS slopes and heart rate variability (HRV). Electrocardiogram (ECG) and respiratory flow signal were acquired from patients with dilated cardiomyopathy and ischemic cardiomyopathy. HRV as well as the upward QRS slope (IUS) and downward QRS slope (IDS) were extracted from the ECG. The relation between HRV and QRS slopes in the VLF band was measured using ordinary coherence in 5-minute segments. Partial coherence was then used to remove the influence that respiration simultaneously exerts on HRV and QRS slopes. A statistical threshold was determined, below which coherence values were considered not to represent a linear relation.

  • Access to the full text
    Methodology for determine the moment of disconnection of patients of the mechanical ventilation using discrete wavelet transform  Open access

     González Acuña, Hernan; Gonzalez Acevedo, Hernando; Arizmendi Pereira, Carlos Julio; Giraldo Giraldo, Beatriz F.
    International Conference on Complex Medical Engineering
    p. 483-486
    DOI: 10.1109/ICCME.2013.6548296
    Presentation's date: 2013-05
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    The process of weaning from mechanical ventilation is one of the challenges in intensive care units. 66 patients under extubation process (T-tube test) were studied: 33 patients with successful trials and 33 patients who failed to maintain spontaneous breathing and were reconnected. Each patient was characterized using 7 time series from respiratory signals, and for each serie was evaluated the discrete wavelet transform. It trains a neural network for discriminating between patients from the two groups.

    The process of weaning from mechanical ventilation is one of the challenges in intensive care units. 66 patients under extubation process (T-tube test) were studied: 33 patients with successful trials and 33 patients who failed to maintain spontaneous breathing and were reconnected. Each patient was characterized using 7 time series from respiratory signals, and for each serie was evaluated the discrete wavelet transform. It trains a neural network for discriminating between patients from the two groups.

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

     Giraldo Giraldo, Beatriz F.; Chaparro Preciado, Javier; Caminal Magrans, Pedro; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 3849-3852
    DOI: 10.1109/EMBC.2013.6610384
    Presentation's date: 2013-07-03
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    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. © 2013 IEEE.

  • Characterization of patients with different ventricular ejection fractions using blood pressure signal analysis

     Arcentales Viteri, Andrés Ricardo; Voss, Andreas; Caminal Magrans, Pedro; Bayés Genis, Antoni; Domingo, Mar Teresa; Giraldo Giraldo, Beatriz F.
    Computing in Cardiology
    p. 795-798
    Presentation's date: 2013-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    Ischemic and dilated cardiomyopathy are associated with disorders of myocardium. Using the blood pressure (BP) signal and the values of the ventricular ejection fraction, we obtained parameters for stratifying cardiomyopathy patients as low- and high-risk. We studied 48 cardiomyopathy patients characterized by NYHA =2: 19 patients with dilated cardiomyopathy (DCM) and 29 patients with ischemic cardiomyopathy (ICM). The left ventricular ejection fraction (LVEF) percentage was used to classify patients in low risk (LR: LVEF > 35%, 17 patients) and high risk (HR: LVEF = 35%, 31 patients) groups. From the BP signal, we extracted the upward systolic slope (BP sl), the difference between systolic and diastolic BP (BPA), and systolic time intervals (STI). When we compared the LR and HR groups in the time domain analysis, the best parameters were standard deviation (SD) of 1=STI, kurtosis (K) of BPsl, and K of BPA. In the frequency domain analysis, very low frequency (VLF) and high frequency (HF) bands showed statistically significant differences in comaprisons of LR and HR groups. The area under the curve of power spectral density was the best parameter in all classifications, and particularly in the very-low-and high- frequency bands (p < 0.001). These parameters could help to improve the risk stratification of cardiomyopathy patients.

    Ischemic and dilated cardiomyopathy are associated with disorders of myocardium. Using the blood pressure (BP) signal and the values of the ventricular ejection fraction, we obtained parameters for stratifying cardiomyopathy patients as low- and high-risk. We studied 48 cardiomyopathy patients characterized by NYHA =2: 19 patients with dilated cardiomyopathy (DCM) and 29 patients with ischemic cardiomyopathy (ICM). The left ventricular ejection fraction (LVEF) percentage was used to classify patients in low risk (LR: LVEF > 35%, 17 patients) and high risk (HR: LVEF = 35%, 31 patients) groups. From the BP signal, we extracted the upward systolic slope (BP sl), the difference between systolic and diastolic BP (BPA), and systolic time intervals (STI). When we compared the LR and HR groups in the time domain analysis, the best parameters were standard deviation (SD) of 1=STI, kurtosis (K) of BPsl, and K of BPA. In the frequency domain analysis, very low frequency (VLF) and high frequency (HF) bands showed statistically significant differences in comaprisons of LR and HR groups. The area under the curve of power spectral density was the best parameter in all classifications, and particularly in the very-low-and high- frequency bands (p < 0.001). These parameters could help to improve the risk stratification of cardiomyopathy patients.

  • Analysis of the respiratory flow cycle morphology in chronic heart failure patients applying principal components analysis

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Sörnmo, Leif; Jane Campos, Raimon
    Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    Vol. 2012, p. 1725-1728
    Date of publication: 2012
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Analysis of roots in ARMA model for the classification of patients on weaning trials

     Giraldo Giraldo, Beatriz F.; Gaspar, Benjamín W.; Caminal Magrans, Pedro; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 698-701
    Presentation's date: 2012-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Estudio de la respiración periódica en el ascenso a altitudes extremas a partir de la señal de volumen respiratorio

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Jane Campos, Raimon; Latshang, T.D.; Turk, A. J.; Hess, T; Bosch, M. M.; Barthelmes, D.; Hefti, J. P.; Maggiorini, M.; Hefti, U; Merz, T. M.; Schoch, O. D.; Bloch, K. E.
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 1-4
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Performance of respiratory pattern parameters in classifiers for predict weaning process

     Chaparro Preciado, Javier; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 4349-4352
    Presentation's date: 2012-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Ensemble-based time alignment of biomedical signals

     Garde Martinez, Ainara; Laguna Lasaosa, Pablo; Giraldo Giraldo, Beatriz F.; Jane Campos, Raimon; Sörnmo, Leif
    International Workshop on Biosignal Interpretation
    p. 1-4
    Presentation's date: 2012-07
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Periodic breathing during ascent to extreme altitude quantified by spectral analysis of the respiratory volume signal

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Jane Campos, Raimon; Latshang, T.D.; Turk, A. J.; Hess, T.; Bosch, M. M.; Barthelmes, D.; Pichler, J.; Maggiorini, M.; Hefti, U; Merz, T. M.; Schoch, O. D.; Bloch, K. E.
    IEEE Engineering in Medicine and Biology Society
    p. 707-710
    Presentation's date: 2012-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Comportamiento de parámetros del patrón respiratorio en clasificadores para la predicción del proceso weaning

     Chaparro Preciado, Javier; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 1-4
    Presentation's date: 2012-11
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Cuantificación de la recurrencia en el estudio de la variabilidad del ritmo cardiaco y la duración del ciclo respiratorio en pacientes en proceso de extubación  Open access

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador; Voss, Andreas
    Congreso Anual de la Sociedad Española de Bioingeniería
    p. 471-474
    Presentation's date: 2011-11
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    El sistema nervioso autónomo regula el comportamiento de los sistemas cardiaco y respiratorio. Su evaluación durante la retirada de la ventilación mecánica puede proporcionar información sobre el comportamiento cardiorespiratorio de los pacientes. Este trabajo propone el análisis de la variabilidad del ritmo cardiaco (HRV) y la duración del ciclo respiratorio (TTot) aplicando la técnica ‘Recurrence Plot (RP)’ y su interacción ‘Joint Recurrence Plot (JRP)’. Se han analizado 131 pacientes, asistidos mediante ventilación mecánica, en proceso de extubación: 92 pacientes con éxito en la extubación (grupo E) y 39 pacientes que no pudieron mantener la respiración espontánea y fracasaron en la extubación (grupo F). Obtenida la matriz de recurrencia para cada señal, se calcularon parámetros que permitían cuantificar la recurrencia de éstas. Los resultados muestran que parámetros como el determinismo (DET), la duración media de la línea diagonal (L), y la entropía (ENTR), presentaron diferencias estadísticamente significativas aplicando RP en las series TTot, pero no en HRV. Al comparar la interacción entre los grupos con JRP, todos los parámetros han sido relevantes. En todos los casos, valores medios del análisis de la cuantificación de recurrencia es mayor en el grupo E que en el grupo F. Las principales diferencias entre los grupos se encuentran en las estructuras diagonales y verticales de la recurrencia conjunta.

  • Interpretación de datos biomédicos multimodales en trastornos del sueño y neurológicos, enfermedad pulmonar obstructiva, patología cardiaca e interacción cardiorespiratoria

     Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.; Torres Cebrian, Abel; Sola Soler, Jordi; Garde Martinez, Ainara; Sarlabous Uranga, Leonardo; Gil De Mesquita, Joana Margarida; Ruiz de Alda Cañamares, Maria Puy; Arcentales Viteri, Andrés Ricardo
    Competitive project

     Share

  • Análisis y clasificación del patrón respiratorio de pacientes en proceso de retirada del ventilador mecánico

     Chaparro Preciado, Javier; Giraldo Giraldo, Beatriz F.
    Revista Ingeniería Biomédica
    Vol. 5, num. 9, p. 43-49
    Date of publication: 2011-06
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Recurrence quantification analysis of heart rate variability and respiratory flow series in patients on weaning trials

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador; Voss, Andreas
    IEEE Engineering in Medicine and Biology Society
    p. 2724-2727
    DOI: 10.1109/IEMBS.2011.6090747
    Presentation's date: 2011-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Analysis of the respiratory flow cycle morphology in chronic heart failure patients applying principal components analysis

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Sörnmo, Leif; Jane Campos, Raimon
    IEEE Engineering in Medicine and Biology Society
    p. 1725-1728
    DOI: 10.1109/IEMBS.2011.6090494
    Presentation's date: 2011-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Estudio de la morfología del ciclo respiratorio mediante el análisis de componentes principales en pacientes con insuficiencia cardíaca crónica

     Garde Martinez, Ainara; Sörnmo, Leif; Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.
    Congreso Anual de la Sociedad Española de Bioingeniería
    p. 377-380
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Analysis of the respiratory pattern variability of patients in weaning process using autoregressive modeling techniques

     Chaparro Preciado, Javier; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 5690-5693
    Presentation's date: 2011-09
    Presentation of work at congresses

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    One of the most challenging problems in intensive care is the process of discontinuing mechanical ventilation, called weaning process. An unnecessary delay in the discontinuation process and an early weaning trial are undesirable. This paper proposes to analysis the respiratory pattern variability of these patients using autoregressive modeling techniques: autoregressive models (AR), autoregressive moving average models (ARMA), and autoregressive models with exogenous input (ARX). A total of 153 patients on weaning trials from mechanical ventilation were analyzed: 94 patients with successful weaning (group S); 38 patients that failed to maintain spontaneous breathing(group F), and 21 patients who had successful weaning trials,but required reintubation in less than 48 h (group R). The respiratory pattern was characterized by their time series. The results show that significant differences were obtained with parameters as model order and first coefficient of AR model, and final prediction error by ARMA model. An accuracy of 86% (84% sensitivity and 86% specificity) has been obtained when using order model and first coefficient of AR model, and mean of breathing duration.

  • Clasificación de pacientes en proceso de extubación mediante el análisis espectral de las series RR y las señales de flujo respiratorio

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Diaz, Ivan; Benito Vales, Salvador
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 260-
    Presentation's date: 2010-11
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Multi-Parameter Analysis of ECG and Respiratory Flow Signals to Identify Success of Patients on Weaning Trials

     Correa, Lorena; Laciar, Eric; Mut, V.; Giraldo Giraldo, Beatriz F.; Torres Cebrian, Abel
    IEEE Engineering in Medicine and Biology Society
    p. 6070-6073
    DOI: 10.1109/IEMBS.2010.5627623
    Presentation's date: 2010-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Análisis del patrón respiratorio de pacientes en proceso de extubación mediante modelado de la señal de flujo respiratorio

     Chaparro Preciado, Javier; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Benito Vales, Salvador
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 107-
    Presentation's date: 2010-11
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Test de no linealidad basado en correntropy aplicado a pacientes con insuficiencia cardiaca crónica

     Garde Martinez, Ainara; Sörnmo, Leif; Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 166-
    Presentation's date: 2010-11
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • RENOVACION DE LA RED TEMATICA EN INGENIERIA BIOMEDICA (REDINBIO)

     Mañanas Villanueva, Miguel Angel; Giraldo Giraldo, Beatriz F.; Gomis Román, Pedro; Jane Campos, Raimon; Vallverdú Ferrer, Montserrat; Perera Lluna, Alexandre; Caminal Magrans, Pedro
    Competitive project

     Share

  • Breathing pattern characterization in patients with respiratory and cardiac failure  Open access

     Garde Martinez, Ainara
    Department of Automatic Control, Universitat Politècnica de Catalunya
    Theses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    El objetivo principal de la tesis es estudiar los patrones respiratorios de pacientes en proceso de extubación y pacientes con insuficiencia cardiaca crónica (CHF), a partirde la señal de flujo respiratorio. La información obtenida de este estudio puede contribuir a la comprensión de los procesos fisiológicos subyacentes,y ayudar en el diagnóstico de estos pacientes. Uno de los problemas más desafiantes en unidades de cuidados intensivos es elproceso de desconexión de pacientes asistidos mediante ventilación mecánica. Más del 10% de pacientes que se extuban tienen que ser reintubados antes de 48 horas. Una prueba fallida puede ocasionar distrés cardiopulmonar y una mayor tasa de mortalidad. Se caracterizó el patrón respiratorio y la interacción dinámica entre la frecuenciacardiaca y frecuencia respiratoria, para obtener índices no invasivos que proporcionen una mayor información en el proceso de destete y mejorar el éxito de la desconexión.Las señales de flujo respiratorio y electrocardiográfica utilizadas en este estudio fueron obtenidas durante 30 minutos aplicando la prueba de tubo en T. Se compararon94 pacientes que tuvieron éxito en el proceso de extubación (GE), 39 pacientes que fracasaron en la prueba al mantener la respiración espontánea (GF), y 21 pacientes quesuperaron la prueba con éxito y fueron extubados, pero antes de 48 horas tuvieron que ser reintubados (GR). El patrón respiratorio se caracterizó a partir de las series temporales. Se aplicó la dinámica simbólica conjunta a las series correspondientes a las frecuencias cardiaca y respiratoria, para describir las interacciones cardiorrespiratoria de estos pacientes. Técnicas de "clustering", ecualización del histograma, clasificación mediante máquinasde soporte vectorial (SVM) y técnicas de validación permitieron seleccionar el conjunto de características más relevantes. Se propuso una nueva métrica B (índice de equilibrio) para la optimización de la clasificación con muestras desbalanceadas. Basado en este nuevo índice, aplicando SVM, se seleccionaron las mejores características que mantenían el mejor equilibrio entre sensibilidad y especificidad en todas las clasificaciones. El mejor resultado se obtuvo considerando conjuntamente la precisión y el valor de B, con una clasificación del 80% entre los grupos GE y GF, con 6 características. Clasificando GE vs. el resto de los pacientes, el mejor resultado se obtuvo con 9 características, con 81%. Clasificando GR vs. GE y GR vs. el resto de pacientes la precisión fue del 83% y 81% con 9 y 10 características, respectivamente. La tasa de mortalidad en pacientes con CHF es alta y la estratificación de estospacientes en función del riesgo es uno de los principales retos de la cardiología contemporánea. Estos pacientes a menudo desarrollan patrones de respiraciónperiódica (PB) incluyendo la respiración de Cheyne-Stokes (CSR) y respiración periódica sin apnea. La respiración periódica en estos pacientes se ha asociadocon una mayor mortalidad, especialmente en pacientes con CSR. Por lo tanto, el estudio de estos patrones respiratorios podría servir como un marcador de riesgo y proporcionar una mayor información sobre el estado fisiopatológico de pacientes con CHF. Se pretende identificar la condición de los pacientes con CHFde forma no invasiva mediante la caracterización y clasificación de patrones respiratorios con PBy respiración no periódica (nPB), y patrón de sujetos sanos, a partir registros de 15minutos de la señal de flujo respiratorio. Se caracterizó el patrón respiratorio mediante un estudio tiempo-frecuencia estacionario y no estacionario, de la envolvente de la señal de flujo respiratorio. Parámetros relacionados con la potencia espectral de la envolvente de la señal presentaron losmejores resultados en la clasificación de sujetos sanos y pacientes con CHF con CSR, PB y nPB. Las curvas ROC validan los resultados obtenidos. Se aplicó la "correntropy" para una caracterización tiempo-frecuencia mas completa del patrón respiratorio de pacientes con CHF. La "corretronpy" considera los momentos estadísticos de orden superior, siendo más robusta frente a los "outliers". Con la densidad espectral de correntropy (CSD) tanto la frecuencia de modulación como la dela respiración se representan en su posición real en el eje frecuencial. Los pacientes con PB y nPB, presentan diferentesgrados de periodicidad en función de su condición, mientras que los sujetos sanos no tienen periodicidad marcada. Con único parámetro se obtuvieron resultados del 88.9% clasificando pacientes PB vs. nPB, 95.2% para CHF vs. sanos, 94.4% para nPB vs. sanos.

    The main objective of this thesis is to study andcharacterize breathing patterns through the respiratory flow signal applied to patients on weaning trials from mechanicalventilation and patients with chronic heart failure (CHF). The aim is to contribute to theunderstanding of the underlying physiological processes and to help in the diagnosis of these patients. One of the most challenging problems in intensive care units is still the process ofdiscontinuing mechanical ventilation, as over 10% of patients who undergo successfulT-tube trials have to be reintubated in less than 48 hours. A failed weaning trial mayinduce cardiopulmonary distress and carries a higher mortality rate. We characterize therespiratory pattern and the dynamic interaction between heart rate and breathing rate toobtain noninvasive indices that provide enhanced information about the weaningprocess and improve the weaning outcome. This is achieved through a comparison of 94 patients with successful trials (GS), 39patients who fail to maintain spontaneous breathing (GF), and 21 patients who successfully maintain spontaneous breathing and are extubated, but require thereinstitution of mechanical ventilation in less than 48 hours because they are unable tobreathe (GR). The ECG and the respiratory flow signals used in this study were acquired during T-tube tests and last 30 minute. The respiratory pattern was characterized by means of a number of respiratory timeseries. Joint symbolic dynamics applied to time series of heart rate and respiratoryfrequency was used to describe the cardiorespiratory interactions of patients during theweaning trial process. Clustering, histogram equalization, support vector machines-based classification (SVM) and validation techniques enabled the selection of the bestsubset of input features. We defined a new optimization metric for unbalanced classification problems, andestablished a new SVM feature selection method, based on this balance index B. The proposed B-based SVM feature selection provided a better balance between sensitivityand specificity in all classifications. The best classification result was obtained with SVM feature selection based on bothaccuracy and the balance index, which classified GS and GFwith an accuracy of 80%, considering 6 features. Classifying GS versus the rest of patients, the best result wasobtained with 9 features, 81%, and the accuracy classifying GR versus GS, and GR versus the rest of the patients was 83% and 81% with 9 and 10 features, respectively.The mortality rate in CHF patients remains high and risk stratification in these patients isstill one of the major challenges of contemporary cardiology. Patients with CHF oftendevelop periodic breathing patterns including Cheyne-Stokes respiration (CSR) and periodic breathing without apnea. Periodic breathing in CHF patients is associated withincreased mortality, especially in CSR patients. Therefore it could serve as a risk markerand can provide enhanced information about thepathophysiological condition of CHF patients. The main goal of this research was to identify CHF patients' condition noninvasively bycharacterizing and classifying respiratory flow patterns from patients with PB and nPBand healthy subjects by using 15-minute long respiratory flow signals. The respiratory pattern was characterized by a stationary and a nonstationary time-frequency study through the envelope of the respiratory flow signal. Power-related parameters achieved the best results in all of the classifications involving healthy subjects and CHF patients with CSR, PB and nPB and the ROC curves validated theresults obtained for the identification of different respiratory patterns. We investigated the use of correntropy for the spectral characterization of respiratory patterns in CHF patients. The correntropy function accounts for higher-order moments and is robust to outliers. Due to the former property, the respiratory and modulationfrequencies appear at their actual locations along the frequency axis in the correntropy spectral density (CSD). The best results were achieved with correntropy and CSD-related parameters that characterized the power in the modulation and respiration discriminant bands, definedas a frequency interval centred on the modulation and respiration frequency peaks,respectively. All patients, i.e. both PB and nPB, exhibit various degrees of periodicitydepending on their condition, whereas healthy subjects have no pronounced periodicity.This fact led to excellent results classifying PB and nPB patients 88.9%, CHF versushealthy 95.2%, and nPB versus healthy 94.4% with only one parameter.

  • Diagnóstico y terapia asistidos por computador

     Caminal Magrans, Pedro; Giraldo Giraldo, Beatriz F.; Clarià Sancho, Francesc; Jane Campos, Raimon; Sola Soler, Jordi; Vallverdú Ferrer, Montserrat
    Automática e instrumentación
    num. 418, p. 52-54
    Date of publication: 2010-05-01
    Journal article

     Share Reference managers Reference managers Open in new window

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

     Garde Martinez, Ainara; Sörnmo, Leif; Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.
    Annals of biomedical engineering
    Vol. 38, num. 12, p. 3572-3580
    DOI: 10.1007/s10439-010-0109-0
    Date of publication: 2010-07-08
    Journal article

    Read the abstract Read the abstract View View Open in new window  Share Reference managers Reference managers Open in new window

    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.

  • Spectral analysis of the RR series and the respiratory flow signal on patients in weaning process

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Díaz, Ivan; Benito Vales, Salvador
    Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    Vol. 2010, p. 2485-2488
    DOI: 10.1109/IEMBS.2010.5626533
    Date of publication: 2010
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Correntropy-based spectral characterization of respiratory Patterns in patients with chronic heart failure  Open access

     Garde Martinez, Ainara; Sörnmo, Leif; Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.
    IEEE transactions on biomedical engineering
    Vol. 57, num. 8, p. 1964-1972
    DOI: 10.1109/TBME.2010.2044176
    Date of publication: 2010-08
    Journal article

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    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 correntropybased 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 PBor 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 fromhealthy subjects with an accuracy of 94.4%.

  • Patients on weaning trials classified with support vector machines

     Garde Martinez, Ainara; Schroeder, Rico; Voss, Andreas; Caminal Magrans, Pedro; Benito Vales, Salvador; Giraldo Giraldo, Beatriz F.
    Physiological measurement
    Vol. 31, num. 7, p. 979-993
    DOI: 10.1088/0967-3334/31/7/008
    Date of publication: 2010-07
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

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

     Caminal Magrans, Pedro; Giraldo Giraldo, Beatriz F.; Vallverdú Ferrer, Montserrat; Benito Vales, Salvador; Schroeder, Rico; Voss, Andreas
    Annals of biomedical engineering
    DOI: 10.1007/s10439-010-0027-1
    Date of publication: 2010
    Journal article

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Spectral analysis of the RR series and the respiratory flow signal on patients in weaning process

     Arcentales Viteri, Andrés Ricardo; Giraldo Giraldo, Beatriz F.; Caminal Magrans, Pedro; Díaz, Ivan; Benito Vales, Salvador
    IEEE Engineering in Medicine and Biology Society
    p. 2485-2488
    DOI: 10.1109/IEMBS.2010.5626533
    Presentation's date: 2010-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Automatic breathing pattern classification in chronic heart failure patients using respiratory flow

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Sörnmo, Leif; Jane Campos, Raimon; Herrera Mateo, Sergio; Bayés Genis, Antoni; Domingo, Maite; Benito Vales, Salvador
    European Respiratory Society Annual Congress
    p. 4409
    Presentation's date: 2010-09
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Study of periodic breathing in chronic heart failure patients based on correntropy

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Jane Campos, Raimon
    Symposium on Bioengineering and Nanomedicine
    p. 1-4
    Presentation's date: 2010-06
    Presentation of work at congresses

    View View Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Correntropy-based nonlinearity test applied to patients with chronic heart failure  Open access

     Garde Martinez, Ainara; Sörnmo, Leif; Jane Campos, Raimon; Giraldo Giraldo, Beatriz F.
    IEEE Engineering in Medicine and Biology Society
    p. 2399-2402
    DOI: 10.1109/IEMBS.2010.5627167
    Presentation's date: 2010-09
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    In this study we propose the correntropy function as a discriminative measure for detecting nonlinearities in the respiratory pattern of chronic heart failure (CHF) patients with periodic or nonperiodic breathing pattern (PB or nPB, respectively). The complexity seems to be reduced in CHF patients with higher risk level. Correntropy reflects information on both, statistical distribution and temporal structure of the underlying dataset. It is a suitable measure due to its capability to preserve nonlinear information. The null hypothesis considered is that the analyzed data is generated by a Gaussian linear stochastic process. Correntropy is used in a statistical test to reject the null hypothesis through surrogate data methods. Various parameters, derived from the correntropy and correntropy spectral density (CSD) to characterize the respiratory pattern, presented no significant differences when extracted from the iteratively refined amplitude adjusted Fourier transform (IAAFT) surrogate data. The ratio between the powers in the modulation and respiratory frequency bands R was significantly different in nPB patients, but not in PB patients, which reflects a higher presence of nonlinearities in nPB patients than in PB patients.

  • Access to the full text
    El temario adaptativo como herramienta de trabajo en grupo y motivación del estudiante de ingeniería en electrónica industrial  Open access

     Martínez García, Herminio; Domingo Peña, Joan; Giraldo Giraldo, Beatriz F.
    Jornada sobre Aprendizaje Cooperativo
    p. 1-10
    Presentation's date: 2010-07-02
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    La presente ponencia describe una experiencia de trabajo cooperativo en la asignatura obligatoria “Electrónica Analógica - II” (EA–2), asignatura obligatoria de 6 créditos en 3er cuatrimestre de la titulación de Ingeniería Técnica en Electrónica Industrial, impartida en la Escuela Universitaria de Ingeniería Técnica Industrial de Barcelona (EUETIB). En esta experiencia, han sido los propios estudiantes los que han decidido la evolución y temario de la asignatura, responsabilizándose de transmitir los conocimientos de buena parte de la misma (y siempre guiados por el profesor de teoría) al resto de compañeros a lo largo de las 15 semanas que dura el curso, de forma que el currículo de la misma, a lo largo de estas 15 semanas, ha sido decido en buena parte por el conjunto del alumnado. Con ello se ha conseguido una fuerte involucración en la materia impartida por parte de los estudiantes, puesto que han asumido la materia como propia, la han explicado al resto de compañeros, y han realizado problemas de análisis y diseño que han ayudado a la comprensión de la misma.

  • Data mining of patients on weaning trials from mechanical ventilation using cluster analysis and neural networks

     Arizmendi Pereira, Carlos Julio; Romero Merino, Enrique; Alquezar Mancho, Renato; Caminal Magrans, Pedro; Diaz, I; Salvador Vales, Benito; Giraldo Giraldo, Beatriz F.
    Annual International Conference of the IEEE Engineering in Medicine and Biology Society
    Vol. 1, p. 4343-4346
    Date of publication: 2009
    Journal article

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    El Falso Puzzle  Open access

     Domingo Peña, Joan; Martínez García, Herminio; Giraldo Giraldo, Beatriz F.; Almajano Pablos, Maria Pilar
    Jornada sobre Aprendizaje Cooperativo y Jornada sobre Innovación Docente
    p. 285-288
    Presentation's date: 2009-07-09
    Presentation of work at congresses

    Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

  • Access to the full text
    Data mining of patients on weaning trials from mechanical ventilation using cluster analysis and neural networks  Open access

     Arizmendi Pereira, Carlos Julio; Romero Merino, Enrique; Alquezar Mancho, Renato; Caminal Magrans, Pedro; Díaz, Ivan; Benito Vales, Salvador; Giraldo Giraldo, Beatriz F.
    IEEE Engineering in Medicine and Biology Society
    p. 4343-4346
    DOI: 10.1109/IEMBS.2009.5332742
    Presentation's date: 2009-09
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    The process of weaning from mechanical ventilation is one of the challenges in intensive care. 149 patients under extubation process (T-tube test) were studied: 88 patients with successful trials (group S), 38 patients who failed to maintain spontaneous breathing and were reconnected (group F), and 23 patients with successful test but that had to be reintubated before 48 hours (group R). Each patient was characterized using 8 time series and 6 statistics extracted from respiratory and cardiac signals. A moving window statistical analysis was applied obtaining for each patient a sequence of patterns of 48 features. Applying a cluster analysis two groups with the majority dataset were obtained. Neural networks were applied to discriminate between patients from groups S, F and R. The best performance obtained was 84.0% of well classified patients using a linear perceptron trained with a feature selection procedure (that selected 19 of the 48 features) and taking as input the main cluster centroid. However, the classification baseline 69.8% could not be improved when using the original set of patterns instead of the centroids to classify the patients.

  • Clasificación de pacientes en proceso de extubación mediante el estudio de las raíces del polinomio del modelo ARMA

     Gaspar, Benjamín W.; Giraldo Giraldo, Beatriz F.; Benito Vales, Salvador; Díaz, Iván; Caminal Magrans, Pedro
    Congreso Anual de la Sociedad Española de Ingeniería Biomédica
    p. 557-560
    Presentation's date: 2009-11
    Presentation of work at congresses

     Share Reference managers Reference managers Open in new window

  • Access to the full text
    Time-varying respiratory pattern characterization in chronic heart failure patients and healthy subjects  Open access

     Garde Martinez, Ainara; Giraldo Giraldo, Beatriz F.; Jane Campos, Raimon; Sörnmo, Leif
    IEEE Engineering in Medicine and Biology Society
    p. 4007-4010
    DOI: 10.1109/IEMBS.2009.5333501
    Presentation's date: 2009-09
    Presentation of work at congresses

    Read the abstract Read the abstract Access to the full text Access to the full text Open in new window  Share Reference managers Reference managers Open in new window

    Patients with chronic heart failure (CHF) with periodic breathing (PB) and Cheyne–Stokes respiration (CSR) tend to exhibit higher mortality and poor prognosis. This study proposes the characterization of respiratory patterns in CHF patients and healthy subjects using the envelope of the respiratory flow signal, and autoregressive (AR) time–frequency analysis. In time-varying respiratory patterns, the statistical distribution of the AR coefficients, pole locations, and the spectral parameters that characterize the discriminant band are evaluated to identify typical breathing patterns. In order to evaluate the accuracy of this characterization, a feature selection process followed by linear discriminant analysis is applied. 26 CHF patients (8 patients with PB pattern and 18 with non-periodic breathing pattern (nPB)) are studied. The results show an accuracy of 83.9% with the mean of the main pole magnitude and the mean of the total power, when classifying CHF patients versus healthy subjects, and 83.3% for nPB versus healthy subjects. The best result when classifying CHF patients into PB and nPB was an accuracy of 88.9%, using the coefficient of variation of the first AR coefficient and the mean of the total power.