Modelos computacionales en la posturografía

Computational models in posturography

Autores/as

  • Lely Adriana Luengas Universidad Distrital Francisco José de Caldas https://orcid.org/0000-0002-3600-4666
  • Luis Felipe Wanumen Silva Universidad Distrital Francisco José de Caldas

Palabras clave:

transtibial amputees, machine learning, static stability, computational models (en).

Palabras clave:

amputados transtibiales, aprendizaje automático, estabilidad estática, modelos computacionales (es).

Descargas

Resumen (es)

Objetivo: Realizar la clasificación y el mapeo de parámetros de balanceo corporal a partir de datos de posturografía estática para diferenciar individuos amputados transtibiales unilaterales de no amputados utilizando técnicas de aprendizaje automático y minería de datos.

Metodología: El balanceo corporal se midió en 74 individuos, 37 amputados por mina antipersonal y 37 controles sanos. Se clasificó la estabilidad según el grupo haciendo uso de aprendizaje automático. Se desarrolló un mapa bidimensional continuo de las alteraciones de la postura utilizando la teoría de la información de Shannon, la prueba de U Mann-Whitney(p<0.05) fue usada con el fin de identificar diferencias entre grupos.

Resultados: Se entrenaron cinco algoritmos de aprendizaje automático, un árbol de decisión, reglas de decisión, una red neuronal, una máquina de soporte vectorial y el clúster. La validación y la comparación se llevaron a cabo con las métricas obtenidas a partir de la matriz de confusión, utilizando validación cruzada para obtener dos subconjuntos. La condición de postura más discriminativa se clasificó como desplazamiento del centro de presión (CoP) lado no amputado dirección antero-posterior. El algoritmo de mayor desempeño fue la máquina de soporte vectorial y el de menor desempeño el clúster, sin embargo, todos los modelos realizaron clasificación de grupos con una puntuación F1 mayor a 0,4.

Conclusiones: El mapeo de las características del desplazamiento del balanceo en el espacio 2D reveló agrupaciones claras entre amputados y controles, lo cual confirma que el aprendizaje automático puede ayudar en la clasificación de patrones de balanceo clínico medidos con posturografía estática. Los modelos computacionales permiten evaluar de forma objetiva la estabilidad, así como reconocer el aporte de contralateral en el control de la postura bípeda estática ya que compensa la no existencia de los aferentes y eferentes de ipsilateral.

Financiamiento: Artículo de investigación científica derivado del proyecto de investigación “Caracterización de la Estabilidad en Amputados Transtibiales Unilaterales”, financiado por la Universidad Distrital Francisco José de Caldas, Bogotá, Colombia.

Resumen (en)

Objective: To perform the classification and mapping of body sway parameters from static posturography data to differentiate unilateral transtibial amputees from non-amputees using machine learning and data mining techniques.

Methodology: Body sway was measured in 74 individuals, 37 landmine amputees and 37 healthy controls. Stability was classified by group using five machine learning algorithms. A continuous two-dimensional map of posture alterations was developed using Shannon's information theory, the U Mann-Whitney test (p <0.05) was used to identify differences between groups.

Results: Five machine learning algorithms (decision tree, decision rules, neural network, vector support machine and clustering) were trained. Validation and comparison were carried out with the metrics obtained from the confusion matrix, using cross-validation to obtain two subsets. The most discriminatory posture condition was classified as displacement of the center of pressure (CoP) on the non-amputated side, anteroposterior direction. The algorithm with the highest performance was the vector support machine and the one with the lowest performance was the cluster; however, all the models performed group classification with an F1 score greater than 0,4.

Conclusions: Mapping of sway displacement characteristics into 2D space revealed clear clusters between amputees and controls, confirming that machine learning can aid in the classification of clinical sway patterns measured with static posturography. Computational models allow to objectively evaluate the stability, as well as to recognize the contribution of the contralateral in the control of the static bipedal posture, since it compensates for the non-existence of the ipsilateral afferents and efferents.

Financing: Scientific research article derived from the research "Characterization of Stability in Unilateral Transtibial Amputees", funded by "Francisco José de Caldas District University".

Biografía del autor/a

Lely Adriana Luengas, Universidad Distrital Francisco José de Caldas

Doctor en Ingeniería, Universidad Distrital Francisco José de Caldas

Luis Felipe Wanumen Silva, Universidad Distrital Francisco José de Caldas

Magíster en Ingeniería de Sistemas y Computación. Universidad Distrital Francisco José de Caldas.

Referencias

Abdul Razak, A. H., Zayegh, A., Begg, R. K. y Wahab, Y. (2012). Foot plantar pressure measurement system: A review. Sensors, 12(7), 9884-9912. https://doi.org/10.3390/s120709884

Ahmadi, S., Vivar, G., Navab, N., Möhwald, K., Maier, A., Hadzhikolev, H., Brandt, T., Grill, E., Dieterich, M., Jahn, K. y Zwergal, A. (2020). Modern machine‑learning can support diagnostic diferentiation. Journal of Neurology, 267(1), 143-152. https://doi.org/10.1007/s00415-020-09931-z

Albertsen, I. M., Ghédira, M., Gracies, J. M. y Hutin, É. (2017). Postural stability in young healthy subjects – Impact of reduced base of support, visual deprivation, dual tasking. Journal of Electromyography and Kinesiology, 33, 27-33. https://doi.org/10.1016/j.jelekin.2017.01.005

Amato, F., López, A., Peña-Méndez, E. M., Vaňhara, P., Hampl, A. y Havel, J. (2013). Artificial neural networks in medical diagnosis. Journal of Applied Biomedicine, 11, 47-58. http://www.sciencedirect.com/science/article/pii/S1214021X14600570 https://doi.org/10.2478/v10136-012-0031-x

Arifin, N., Abu Osman, N. A., Ali, S., Gholizadeh, H. y Wan Abas, W. A. B. (2014). Postural stability characteristics of transtibial amputees wearing different prosthetic foot types when standing on various support surfaces. Scientific World Journal, 2014, 856279. https://doi.org/10.1155/2014/856279

Arora, S., Venkataraman, V., Donohue, S., Biglan, K. M., Dorsey, E. R. y Little, M. A. (2014). High accuracy discrimination of Parkinson’s disease participants from healthy controls using smartphones. En ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing – Proceedings (pp. 3641-3644). https://doi.org/10.1109/ICASSP.2014.6854280

Audiffren, J., Bargiotas, I., Vayatis, N., Vidal, P. P. y Ricard, D. (2016). A non linear scoring approach for evaluating balance: Classification of elderly as fallers and non-fallers. PLoS ONE, 11(12), e0167456.

https://doi.org/10.1371/journal.pone.0167456

Baig, S., Dansereau, R. M., Chan, A. D. C., Remaud, A. y Bilodeau, M. (2012). Cluster analysis of center-of-pressure measures. International Journal of Electrical and Computer Engineering, 1(1), 9-17. https://doi.org/10.11159/ijecs.2012.002

Buldt, A. K., Murley, G. S., Butterworth, P., Levinger, P., Menz, H. B. y Landorf, K. B. (2018). The relationship between foot posture and lower limb kinematics during walking: A systematic review. Gait & Posture, 62(3), 56-67. https://doi.org/10.1016/j.gaitpost.2013.01.010

Caicedo, C. H. y Smida, A. (2016). Informational intensity for longitudinality care in health systems. Visión Electrónica, 10(1), 83-95. https://doi.org/10.14483/22484728.11612

Claret, C. R., Herget, G. W., Kouba, L., Wiest, D., Adler, J., Von Tscharner, V., Stieglitz, T. y Pasluosta, C. (2019). Neuromuscular adaptations and sensorimotor integration following a unilateral transfemoral amputation. Journal of NeuroEngineering and Rehabilitation, 16(1), 115. https://doi.org/10.1186/s12984-019-0586-9

Cordero-Civantos, C. y Calle-Cabanillas, M. I. (2017). Primeros pasos en la posturografía dinámica computarizada. Revista ORL, 9(3), 227-237. https://doi.org/10.14201/orl.17370

De la Hoz Manotas, A. K., Martínez-Palacio, U. J. y Mendoza-Palechor, F. E. (2013). Técnicas de ML en medicina cardiovascular. Memorias, 11(20), 41-46. https://doi.org/10.16925/me.v11i20.498

De Vassimon-Barroso, V., Catai, A. M., Buto, M. S. D. S., Porta, A. y Takahashi, A. C. D. M. (2017). Linear and nonlinear analysis of postural control in frailty syndrome. Brazilian Journal of Physical Therapy, 21(3), 184-191. https://doi.org/10.1016/j.bjpt.2017.03.015

Drozdova-Statkevičienė, M., Česnaitienė, V. J., Pukėnas, K., Levin, O. y Masiulis, N. (2018). Sway regularity and sway activity in older adults’ upright stance are differentially affected by dual task. Neuroscience Letters, 666, 153-157. https://doi.org/10.1016/j.neulet.2017.12.054

Funato, T., Aoi, S., Tomita, N. y Tsuchiya, K. (2016). Smooth enlargement of human standing sway by instability due to weak reaction floor and noise. Royal Society Open Science, 3(1). https://doi.org/10.1098/rsos.150570

Gholipour, A. y Arjmand, N. (2016). Artificial neural networks to predict 3D spinal posture in reaching and lifting activities: Applications in biomechanical models. Journal of Biomechanics, 49(13), 2946-2952. https://doi.org/10.1016/j.jbiomech.2016.07.008

Giovanini, L. H. F., Manffra, E. F. y Nievola, J. C. (2018). Discriminating postural control behaviors from posturography with statistical tests and machine learning models: Does time series length matter? En Y. Shi, Y. Tian, H. Fu, V. V. Krzhizhanovskaya, M. H. Lees, P. M. A. Sloot y J. Dongarra (eds.), Computational Science – ICCS 2018. Lecture Notes in Computer Science (LNCS 10862) (pp. 350-357). Springer. https://doi.org/10.1007/978-3-319-93713-7_28

Giovanini, L. H. F., Silva, S. M., Manffra, E. F. y Nievola, J. C. (2017). Sampling and digital filtering effects when recognizing postural control with statistical tools and the decision tree classifier. Procedia Computer Science, 108, 129-138. https://doi.org/10.1016/j.procs.2017.05.117

Goble, D. J. y Baweja, H. S. (2018). Postural sway normative data across the adult lifespan: Results from 6280 individuals on the Balance Tracking System balance test. Geriatrics and Gerontology International, 18(8), 1225-1229. https://doi.org/10.1111/ggi.13452

Hahn, M. E., Farley, A. M., Lin, V. y Chou, L. (2005). Neural network estimation of balance control during locomotion. Journal of Biomechanics, 38(4), 717-724. https://doi.org/10.1016/j.jbiomech.2004.05.012

Haid, T. H., Doix, A. C. M., Nigg, B. M. y Federolf, P. A. (2018). Age effects in postural control analyzed via a principal component analysis of kinematic data and interpreted in relation to predictions of the optimal feedback control theory. Frontiers in Aging Neuroscience, 10. https://doi.org/10.3389/fnagi.2018.00022

Hessert, M. J., Vyas, M., Leach, J., Hu, K., Lipsitz, L. A. y Novak, V. (2005). Foot pressure distribution during walking in young and old adults. BMC Geriatrics, 5, 8. https://doi.org/10.1186/1471-2318-5-8

Kamali, M., Karimi, M. T., Eshraghi, A. y Omar, H. (2013). Influential factors in stability of lower-limb amputees. American Journal of Physical Medicine & Rehabilitation, 92(12), 1110-1118. https://doi.org/10.1097/PHM.0b013e31829b4b7a

Kendell, C., Lemaire, E. D., Dudek, N. L. y Kofman, J. (2010). Indicators of dynamic stability in transtibial prosthesis users. Gait & Posture, 31(3), 375-379. https://doi.org/10.1016/j.gaitpost.2010.01.003

Kolarova, B., Janura, M., Svoboda, Z. y Elfmark, M. (2013). Limits of stability in persons with transtibial amputation with respect to prosthetic alignment alterations. Archives of Physical Medicine and Rehabilitation, 94(11), 2234-2240. https://doi.org/10.1016/j.apmr.2013.05.019

Krafczyk, S., Tietze, S., Swoboda, W., Valkovič, P. y Brandt, T. (2006). Artificial neural network: A new diagnostic posturographic tool for disorders of stance. Clinical Neurophysiology, 117(8), 1692-1698. https://doi.org/10.1016/j.clinph.2006.04.022

Lamoth, C. J. C., Ainsworth, E., Polomski, W. y Houdijk, H. (2010). Variability and stability analysis of walking of transfemoral amputees. Medical Engineering and Physics, 32(9), 1009-1014. https://doi.org/10.1016/j.medengphy.2010.07.001

Lau, H. Y., Tong, K. Y. y Zhu, H. (2008). Support vector machine for classification of walking conditions using miniature kinematic sensors. Medical and Biological Engineering and Computing, 46(6), 563-573. https://doi.org/10.1007/s11517-008-0327-x

Luengas, L. A. y Penagos, A. (2016). Identificación del comportamiento de parámetros biomecánicos en la alineación estática de prótesis transtibiales utilizando SVM’S. Tecnura, 20, 31-42. https://doi.org/10.14483/udistrital.jour.tecnura.2016.SE1.a02

Luengas, L. A. y Toloza, D. C. (2019). Análisis de estabilidad en amputados transtibiales unilaterales. Editorial Universidad Distrital Francisco José de Caldas.

Luengas, L. A. y Toloza, D. C. (2020a). Frequency and spectral power density analysis of the stability of amputees subjects. TecnoLógicas, 23(48), 1-16. https://doi.org/https://doi.org/10.22430/22565337.1453

Luengas, L. A. y Toloza, D. C. (2020b). Application of wavelet transform to stability analysis in transtibial amputees. Investigación e Innovación en Ingenierías, 8(1), 214-225. https://doi.org/https://doi.org/10.17081/invinno.8.1.3640

Moghadam, M., Ashayeri, H., Salavati, M., Sarafzadeh, J., Taghipoor, K. D., Saeedi, A. y Salehi, R. (2011). Reliability of center of pressure measures of postural stability in healthy older adults: Effects of postural task difficulty and cognitive load. Gait and Posture, 33(4), 651-655. https://doi.org/10.1016/j.gaitpost.2011.02.016

Molero-Sánchez, A., Molina-Rueda, F., Alguacil-Diego, I. M., Cano-de la Cuerda, R. y Miangolarra-Page, J. C. (2015). Comparison of stability limits in men with traumatic transtibial amputation and a nonamputee control group. PM and R, 7(2), 123-129. https://doi.org/10.1016/j.pmrj.2014.08.953

Muniz, A. M. S., Liu, H., Lyons, K. E., Pahwa, R., Liu, W., Nobre, F. F. y Nadal, J. (2010). Comparison among probabilistic neural network, support vector machine and logistic regression for evaluating the effect of subthalamic stimulation in Parkinson disease on ground reaction force during gait. Journal of Biomechanics, 43(4), 720-726. https://doi.org/10.1016/j.jbiomech.2009.10.018

Overgaard, M., Gehlert, T. F., Pedersen, L. K. y Nordbye-Nielsen, K. (2018). Objective assessment of postural control after lower-limb amputation: A pilot study. Journal of Prosthetics and Orthotics, 30(4), 236-241. https://doi.org/10.1097/JPO.0000000000000206

Peydro de Moya, M. F., Baydal, J. M. y Vivas, M. J. (2005). Evaluación y rehabilitación del equilibrio mediante posturografía. Rehabilitación, 39(6), 315-323. https://doi.org/10.1016/S0048-7120(05)74365-6

Qiu, H. y Xiong, S. (2015). Center-of-pressure based postural sway measures: Reliability and ability to distinguish between age, fear of falling and fall history. International Journal of Industrial Ergonomics, 47, 37-44. https://doi.org/10.1016/J.ERGON.2015.02.004

Rhea, C. K., Kiefer, A. W., Haran, F. J., Glass, S. M. y Warren, W. H. (2014). A new measure of the CoP trajectory in postural sway: Dynamics of heading change. Medical Engineering and Physics, 36(11), 1473-1479. https://doi.org/10.1016/j.medengphy.2014.07.021

Rhea, C. K., Kiefer, A. W., Wright, W. G., Raisbeck, L. D. y Haran, F. J. (2015). Interpretation of postural control may change due to data processing techniques. Gait and Posture, 41(2), 731-735. https://doi.org/10.1016/j.gaitpost.2015.01.008

Roman-Liu, D. (2018). Age-related changes in the range and velocity of postural sway. Archives of Gerontology and Geriatrics, 77, 68-80. https://doi.org/10.1016/j.archger.2018.04.007

Rosado Gómez, A. A. y Verjel Ibáñez, A. (2015). Minería de datos aplicada a la demanda del transporte aéreo en Ocaña, Norte de Santander. Tecnura, 19(45), 101-113. https://doi.org/10.14483/udistrital.jour.tecnura.2015.3.a08

Rougier, P. R. y Bergeau, J. (2009). Biomechanical analysis of postural control of persons with transtibial or transfemoral amputation. American Journal of Physical Medicine and Rehabilitation, 88(11), 896-903. https://doi.org/10.1097/PHM.0b013e3181b331af

Sadeghisani, M., Karimi, M. T. y Kamali, M. (2016). Nonlinear analysis of postural sway in subjects with below knee amputation during opened and closed eye conditions. Journal of Orthopaedics, 13(3), 152-156. https://doi.org/10.1016/j.jor.2016.03.009

Safi, K., Mohammed, S., Amirat, Y. y Khalil, M. (2017). Postural stability analysis: A review of techniques and methods for human stability assessment. Fourth International Conference on Advances in Biomedical Engineering (ICABME), 978(1), 3-6. https://doi.org/10.1109/ICABME.2017.8167565

Salarte, G. y Castro, Y. (2012). Modelo híbrido para el diagnóstico de enfermedades cardiovasculares basado en inteligencia artificial. Tecnura, 16(33), 35-52. http://www.redalyc.org/articulo.oa?id=257024374004

Şencan, S., Ayaş, Ş. y Saraçgil Coşar, S. N. (2016). A study which investigates the relationship of age, trunk strength, and balance parameters with fall risk. Turkish Journal of Geriatrics, 19(3), 174-182. https://www.scopus.com/inward/record.uri?eid=2-s2.0-84984846382&partnerID=40&md5=e6e6658f73f997f5bb34a463f46c017b

Shan, G., Wu, G. y Haugh, L. (2004). A method to determine the interdependent relationships between biomechanical variables in artificial neural network models: The case of lower extremity muscle activity and body sway. Neurocomputing, 61(1-4), 241-258. https://doi.org/10.1016/j.neucom.2003.05.002

Shannon, C. E. (2001). A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review, 5, 3-55. https://doi.org/10.1145/584091.584093

Sun, R., Hsieh, K. L. y Sosnoff, J. J. (2019). Fall risk prediction in multiple sclerosis using postural sway measures: A machine learning approach. Scientific Reports, 9(1), 1-7. https://doi.org/10.1038/s41598-019-52697-2

Toloza, D. y Zequera, M. (2017). Linear and non-linear methods for analysis center pressure and its application in diabetic peripheral neuropathy: A systematic review. IFMBE Proceedings, 60, 713-716. https://doi.org/10.1007/978-981-10-4086-3_179

Tucker, M. R., Olivier, J., Pagel, A., Bleuler, H., Bouri, M., Lambercy, O., Millán, J. del R., Riener, R., Vallery, H. y Gassert, R. (2015). Control strategies for active lower extremity prosthetics and orthotics: A review. Journal of NeuroEngineering and Rehabilitation, 12, 1. https://doi.org/10.1186/1743-0003-12-1

Wu, L. C., Kuo, C., Loza, J., Kurt, M., Laksari, K., Yanez, L. Z., Senif, D., Anderson, S. C., Miller, L. E., Urban, J. E., Stitzel, J. D. y Camarillo, D. B. (2018). Detection of American football head impacts using biomechanical features and support vector machine classification. Scientific Reports, 8(1). https://doi.org/10.1038/s41598-017-17864-3

Xu, R. y Wunsch, D. C. (2010). Clustering algorithms in biomedical research: A review. IEEE Reviews in Biomedical Engineering, 3, 120-154. https://doi.org/10.1109/RBME.2010.2083647

Yamamoto, T., Smith, C. E., Suzuki, Y., Kiyono, K., Tanahashi, T., Morasso, P. y Nomura, T. (2015). Universal and individual characteristics of postural sway during quiet standing in healthy young adults. Physiological Reports, 3(3), 1-24. https://doi.org/10.14814/phy2.12329

Cómo citar

APA

Luengas, L. A., & Wanumen Silva, L. F. (2022). Modelos computacionales en la posturografía. Tecnura, 26(73). https://doi.org/10.14483/22487638.18060

ACM

[1]
Luengas, L.A. y Wanumen Silva, L.F. 2022. Modelos computacionales en la posturografía. Tecnura. 26, 73 (jul. 2022). DOI:https://doi.org/10.14483/22487638.18060.

ACS

(1)
Luengas, L. A.; Wanumen Silva, L. F. Modelos computacionales en la posturografía. Tecnura 2022, 26.

ABNT

LUENGAS, L. A.; WANUMEN SILVA, L. F. Modelos computacionales en la posturografía. Tecnura, [S. l.], v. 26, n. 73, 2022. DOI: 10.14483/22487638.18060. Disponível em: https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/18060. Acesso em: 13 ago. 2022.

Chicago

Luengas, Lely Adriana, y Luis Felipe Wanumen Silva. 2022. «Modelos computacionales en la posturografía». Tecnura 26 (73). https://doi.org/10.14483/22487638.18060.

Harvard

Luengas, L. A. y Wanumen Silva, L. F. (2022) «Modelos computacionales en la posturografía», Tecnura, 26(73). doi: 10.14483/22487638.18060.

IEEE

[1]
L. A. Luengas y L. F. Wanumen Silva, «Modelos computacionales en la posturografía», Tecnura, vol. 26, n.º 73, jul. 2022.

MLA

Luengas, L. A., y L. F. Wanumen Silva. «Modelos computacionales en la posturografía». Tecnura, vol. 26, n.º 73, julio de 2022, doi:10.14483/22487638.18060.

Turabian

Luengas, Lely Adriana, y Luis Felipe Wanumen Silva. «Modelos computacionales en la posturografía». Tecnura 26, no. 73 (julio 1, 2022). Accedido agosto 13, 2022. https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/18060.

Vancouver

1.
Luengas LA, Wanumen Silva LF. Modelos computacionales en la posturografía. Tecnura [Internet]. 1 de julio de 2022 [citado 13 de agosto de 2022];26(73). Disponible en: https://revistas.udistrital.edu.co/index.php/Tecnura/article/view/18060

Descargar cita

Visitas

20

Dimensions


PlumX


Descargas

Los datos de descargas todavía no están disponibles.