Publication:
Characterization of Cardiac and Respiratory System of Healthy Subjects in Supine and Sitting Position

Thumbnail Image
Files

Files

Characterization of cardiac and respiratory system of healthy subjects in supine and sitting position.pdf (759.46 KB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Ruiz, Angel D.
Mejía, Juan S.
López, Juan M.
Giraldo, Beatriz F.
Abstract (Spanish)
Estudios basados ​​en el sistema cardíaco y respiratorio han permitido una un mejor conocimiento de su comportamiento para contribuir con el diagnóstico y tratamiento de enfermedades asociadas a ellos. El objetivo principal de este proyecto era analizar el comportamiento del sistema cardiorrespiratorio en sujetos sanos, dependiendo de la posición del cuerpo. La electrocardiografía y el flujo respiratorio. Las señales se registraron en dos posiciones, supina y sentada. Cada señal fue analizado considerando ventanas corredizas de 30 s, con un traslape del 50%. Se extrajeron características temporales y espectrales de cada señal. Un total de 187 Se extrajeron características para cada ventana. Según el análisis estadístico, 148 características mostraron diferencias significativas al comparar la posición del sujeto. Posteriormente se aplicaron los métodos de clasificación basados ​​en árboles de decisión, máquinas de vecinos más cercanos y de vectores de soporte para identificar las mejores. modelo de clasificación. Se obtuvo el modelo de rendimiento más ventajoso. con un método de máquina de vectores de soporte lineal, con una precisión del 99,5%, un sensibilidad del 99,2% y una especificidad del 99,6%. En conclusión, hemos observado que la posición del cuerpo (decúbito supino o sentado) podría modular la función cardíaca y respuesta del sistema respiratorio. Los nuevos modelos estadísticos podrían proporcionar nuevas herramientas para analizar el comportamiento de estos sistemas y la interacción cardiorrespiratoria complejidad.
Abstract (English)
Studies based on the cardiac and respiratory system have allowed a better knowledge of their behavior to contribute with the diagnosis and treatment of diseases associated with them. The main goal of this project was to analyze the behavior of the cardiorespiratory system in healthy subjects, depending on the body position. The electrocardiography and respiratory flow signals were recorded in two positions, supine and sitting. Each signal was analyzed considering sliding windows of 30 s, with and overlapping of 50%. Temporal and spectral features were extracted from each signal. A total of 187 features were extracted for each window. According to statistical analysis, 148 features showed significant differences when comparing the position of the subject. Afterwards, the classifications methods based on decision trees, knearest neighbor and support vector machines were applied to identify the best classification model. The most advantageous performance model was obtained with a linear support vector machine method, with an accuracy of 99.5%, a sensitivity of 99.2% and a specificity of 99.6%. In conclusion, we have observed that the position of the body (supine or sitting) could modulate the cardiac and respiratory system response. New statistical models might provide new tools to analyze the behavior of these systems and the cardiorespiratory interaction complexity.
Extent
11 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/3346
Collections

Collections

AA. Gibiome
References

Serra, M., Iturralde Torres, P., Aranda Fraustro, A.: Orígenes del conocimiento de la estructura y función del sistema cardiovascular. Arch. Cardiol. México 83(3), 225–231 (2013)

Thibodeau, A., Patton, K.T.: Structure and Function of the Body, 13th edn. Mosby/Elsevier, Missouri (2008)

Dabbagh, A., Imani, A., Rajaei, S.: Cardiac Physiology. In: Dabbagh, A., Esmailian, F., Aranki, S. (eds.) Postoperative Critical Care for Adult Cardiac Surgical Patients, pp. 25–74. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75747-6_3

Madias, J.E.: Comparability of the standing and supine standard electrocardiograms and standing sitting and supine stress electrocardiograms. J. Electrocardiol 39(2), 142–149 (2006)

Muehlhan, M., Marxen, M., Landsiedel, J., Malberg, H., Zaunseder, S.: The effect of body posture on cognitive performance: a question of sleep quality. Front. Hum. Neurosci. 8, 171 (2014)

El-Saadawy, H., Tantawi, M., Shedeed, Howida A., Tolba, M.F.: Diagnosing heart diseases using morphological and dynamic features of electrocardiogram (ECG). In: Hassanien, A.E., Shaalan, K., Gaber, T., Tolba, Mohamed F. (eds.) AISI 2017. AISC, vol. 639, pp. 342–352. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-64861-3_32

Tan, M.Y., Ong, T., Sivam, J., Al-Shuft, H., Sahota, O., Salem, K.: 32the role of dynamic supine-sitting spinal radiographs in the management of vertebral fragility fractures admitted to hospital. Age Ageing 47(suppl_3), iii9–iii12 (2018)

Sierra-Silvestre, E., Bosello, F., Fernández Carnero, J., Hoozemans, M.J.M., Coppieters, M. W.: Femoral nerve excursion withe knee and neck movements in supine, sitting and sidelying slump: an in vivo study using ultrasound imaging. Musculoskelet. Sci. Pract. 37, 58– 63 (2018)

Cicolini, G., et al.: Differences in blood pressure by body position (supine, fowler’s, and sitting) in hypertensive subjects. Am. J. Hypertens. 24(10), 1073–1079 (2011)

Zuttin, R.S., Moreno, M.A., César, M.C., Martins, L.E.B.: Evaluation of autonomic heart rate modulation among sedentary young men, in sitting and supine postures. Braz. J. Phys. Ther. 12(1), 7–12 (2008). Revista Brasileira de Fisioterapia, 6p. 1 Chart, 2 Graphs

Nemec, B., Petrič, T., Babič, J., Supej, M.: Estimation of alpine skier posture using machine learning techniques. Sensors 14(10), 18898–18914 (2014)

Antunes, B.O., de Souza, H.C.D., Gianinis, H.H., Passarelli-Amaro, R.D.C.V., Tambascio, J., Gastaldi, A.C.: Peak expiratory flow in healthy, young, non-active subjects in seated, supine, and prone postures. Physiother. Theory Pract. 32(6), 489–493 (2016)

Kim, Y., Son, Y., Kim, W., Jin, B., Yun, M.: Classification of children’s sitting postures using machine learning algorithms. Appl. Sci. 8(8), 1280 (2018)

Cecchin, T., Ranta, R., Koessler, L., Vespignani, H., Maillard, L., Caspary, O.: Seizure lateralization in scalp EEG using Hjorthparameters. Clin. Neurophysiol. 121(3), 290–300 (2010)

Falconer, K.: Geometría Fractal, p. 308. Wiley, Nueva York (2003). ISBN 978–0-470- 84862-3

Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. BME-32(3), 230–236 (1985)

Liu, Y., Lin, Y., Wang, J., Shang, P.: Refined generalized multiscale entropy analysis for physiological signals. Phys. A Stat. Mech. Appl. 490, 975–985 (2018)

Welch, P.D.: The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Transactions on audio and electroacoustics 15(2), 70–73 (1967)

Kamiński, B., Jakubczyk, M., Szufel, P.: A framework for sensitivity analysis of decision trees. CEJOR 26, 135–159 (2017)

Altman, N.: An introduction to kernel and nearest-neighbor nonparametric regression. Am. Stat. 46, 175–185 (1992)

Steinwart, I., Chrismann, A.: Super Vector Machine. Information Science and Statistics. Springer, Heidelberg (2008). https://doi.org/10.1007/978-0-387-77242-4

Garde, A., Schroeder, R., Voss, A., Caminal, P., Benito, S., Giraldo, B.F.: Patients on weaning trials classified with support vector machines. Physiol. Meas. 31, 979–993 (2010)

Vatavu, R.-D.: Beyond features for recognition: human-readable measures to understand users’ whole-body gesture performance. Int. J. Hum.-Comput. Interact. 33(9), 713–730 (2017)

Rasouli, M.S., Payandeh, S.: A novel depth image analysis for sleep posture estimation. J. Ambient Intell. Hum. Comput. 10(5), 1999–2014 (2019)

Zemp, R., et al.: Application of machine learning approaches for classifying sitting posture based on force and acceleration sensors. Biomed. Res. Int. 2016, 1–9 (2016)