Cognitive impairment inference in Parkinson's disease patients from spatiotemporal gait assessments using machine learning
dc.contributor.advisor | Romero Castro, Edgar Eduardo | |
dc.contributor.author | Serna Soto, Jose Elkin | |
dc.contributor.cvlac | Serna Soto, Jose Elkin [0001593674] | spa |
dc.contributor.researchgroup | Cim@Lab | spa |
dc.date.accessioned | 2025-03-25T14:46:07Z | |
dc.date.available | 2025-03-25T14:46:07Z | |
dc.date.issued | 2025 | |
dc.description | ilustraciones, diagramas | spa |
dc.description.abstract | Cognitive decline is a significant complication in Parkinson’s disease (PD), severely impacting patients’ quality of life. Early identification of these deficits is crucial to improving clinical intervention and disease prognosis. This study investigates the relationship between spatiotemporal gait characteristics and cognitive decline in early-stage PD patients. Data from 48 patients were obtained from the Parkinson’s Progression Markers Initiative (PPMI) database, categorised into two groups: patients without cognitive impairment (PD) and those exhibiting some degree of cognitive decline (PD-CD). Seven machine learning algorithms were implemented, optimising hyperparameters and addressing class imbalance. Model performance was evaluated using Recall, Precision, F1-score, and Accuracy, prioritising sensitivity to assess the classifiers’ ability to detect the minority class. The results indicate that spatiotemporal gait characteristics significantly differentiate PD and PD-CD groups. Among the evaluated models, the Multilayer Perceptron (MLP) and the Cognitive Assessment through Gait in Parkinson’s Disease (CoGait-PD) demonstrated the highest performance, achieving accuracy scores of 0.78 ± 0.08 and 0.77 ± 0.05, respectively. Both models balanced sensitivity and precision, excelling in identifying positive cases and reducing false negatives. These findings suggest that gait characteristics may serve as non-invasive biomarkers for early detection of cognitive decline in PD patients. Additionally, machine learning models, particularly CoGait-PD and MLP, show strong potential for clinical assessment. Further studies are recommended to validate these findings and explore their applicability in clinical settings. | eng |
dc.description.abstract | El deterioro cognitivo es una de las complicaciones más relevantes en la enfermedad de Parkinson (PD), afectando significativamente la calidad de vida de los pacientes. La identificación temprana de estos déficits es crucial para mejorar la intervención clínica y el pronóstico de la enfermedad. Este estudio analiza la relación entre las características espaciotemporales de la marcha y el deterioro cognitivo en pacientes con PD en etapa temprana. Se utilizaron datos de 48 pacientes de la base de datos de la Parkinson’s Progression Markers Initiative (PPMI), dividiendo la muestra en dos grupos: pacientes sin deterioro cognitivo (PD) y aquellos con algún grado de deterioro cognitivo (PD-DC). Para el análisis, se implementaron siete algoritmos de aprendizaje automático, optimizando sus hiperparámetros y abordando el desequilibrio de clases. El desempeño de los modelos se evaluó mediante métricas como Recall, Precisión, F1-score y Exactitud (Accuracy), priorizando la sensibilidad para evaluar la capacidad de detección de la clase minoritaria. Los resultados indicaron que las características espaciotemporales de la marcha permiten diferenciar significativamente entre los grupos PD y PD-DC. Entre los modelos evaluados, el Perceptrón Multicapa (MLP) y el Cognitive Assessment through Gait in Parkinson’s Disease (CoGait-PD) presentaron el mejor desempeño, alcanzando valores de exactitud de 0.78 ± 0.08 y 0.77 ± 0.05, respectivamente. Estos modelos lograron un equilibrio entre sensibilidad y precisión, destacándose en la identificación de casos positivos y reduciendo falsos negativos. Los hallazgos sugieren que las características de la marcha pueden servir como biomarcadores no invasivos para la detección temprana del deterioro cognitivo en pacientes con PD. Además, los modelos de aprendizaje automático, particularmente CoGait-PD y MLP, muestran un alto potencial en la evaluación clínica. Se recomienda realizar estudios adicionales para validar estos hallazgos y explorar su aplicabilidad en entornos clínicos (Texto tomado de la fuente) | spa |
dc.description.degreelevel | Maestría | spa |
dc.description.degreename | Magíster en Ingeniería Biomédica | spa |
dc.description.researcharea | Motion and Biosignal Analysis | spa |
dc.format.extent | xiv, 40 páginas | spa |
dc.format.mimetype | application/pdf | spa |
dc.identifier.instname | Universidad Nacional de Colombia | spa |
dc.identifier.reponame | Repositorio Institucional Universidad Nacional de Colombia | spa |
dc.identifier.repourl | https://repositorio.unal.edu.co/ | spa |
dc.identifier.uri | https://repositorio.unal.edu.co/handle/unal/87725 | |
dc.language.iso | eng | spa |
dc.publisher | Universidad Nacional de Colombia | spa |
dc.publisher.branch | Universidad Nacional de Colombia - Sede Bogotá | spa |
dc.publisher.faculty | Facultad de Medicina | spa |
dc.publisher.place | Bogotá, Colombia | spa |
dc.publisher.program | Bogotá - Medicina - Maestría en Ingeniería Biomédica | spa |
dc.relation.references | [1] W. H. Organization, Parkinson disease: a public health approach. Technical Brief. World Health Organization, 2022. | spa |
dc.relation.references | [2] N. Maserejian, L. Vinikoor-Imler, and A. Dilley, “Estimation of the 2020 global population of parkinson’s disease (pd),” MDS Abstracts, 2020. Accessed: 2024- 08-28. | spa |
dc.relation.references | [3] Lancet, “What next in parkinson’s disease?,” The Lancet, vol. 403, no. 10370, p. 219, 2024. Accessed: 2024-08-28. | spa |
dc.relation.references | [4] D. Aarsland, B. Creese, M. Politis, K. R. Chaudhuri, D. Weintraub, C. Ballard, et al., “Cognitive decline in parkinson disease,” Nature Reviews Neurology,vol. 13, no. 4, pp. 217–231, 2017. | spa |
dc.relation.references | [5] D. Aarsland, K. Bronnick, C. Williams-Gray, D. Weintraub, K. Marder, J. Kulisevsky, D. Burn, P. Barone, J. Pagonabarraga, L. Allcock, et al., “Mild cognitive impairment in parkinson disease: a multicenter pooled analysis,” Neurology, vol. 75, no. 12, pp. 1062–1069, 2010. | spa |
dc.relation.references | [6] C. C. Janvin, J. P. Larsen, D. Aarsland, and K. Hugdahl, “Subtypes of mild cognitive impairment in parkinson’s disease: progression to dementia,” Movement disorders: official journal of the Movement Disorder Society, vol. 21, no. 9, pp. 1343–1349, 2006. | spa |
dc.relation.references | [7] C. Williams-Gray, T. Foltynie, C. Brayne, T. Robbins, and R. Barker, “Evolution of cognitive dysfunction in an incident parkinson’s disease cohort,” Brain, vol. 130, no. 7, pp. 1787–1798, 2007. | spa |
dc.relation.references | [8] C. H. Williams-Gray, J. R. Evans, A. Goris, T. Foltynie, M. Ban, T. W. Robbins, C. Brayne, B. S. Kolachana, D. R. Weinberger, S. J. Sawcer, et al., “The distinct cognitive syndromes of parkinson’s disease: 5 year follow-up of the campaign cohort,” Brain, vol. 132, no. 11, pp. 2958–2969, 2009. | spa |
dc.relation.references | [9] R. Morris, S. Lord, R. A. Lawson, S. Coleman, B. Galna, G. W. Duncan, T. K. Khoo, A. J. Yarnall, D. J. Burn, and L. Rochester, “Gait rather than cognition predicts decline in specific cognitive domains in early parkinson’s disease,” Journals of Gerontology Series A: Biomedical Sciences and Medical Sciences, vol. 72, no. 12, pp. 1656–1662, 2017. | spa |
dc.relation.references | [10] J. Verghese, C. Wang, R. B. Lipton, R. Holtzer, and X. Xue, “Quantitative gait dysfunction and risk of cognitive decline and dementia,” Journal of Neurology, Neurosurgery & Psychiatry, vol. 78, no. 9, pp. 929–935, 2007. | spa |
dc.relation.references | [11] M. M. Mielke, R. O. Roberts, R. Savica, R. Cha, D. I. Drubach, T. Christianson, V. S. Pankratz, Y. E. Geda, M. M. Machulda, R. J. Ivnik, et al., “Assessing the temporal relationship between cognition and gait: slow gait predicts cognitive decline in the mayo clinic study of aging,” Journals of Gerontology Series A: Biomedical Sciences and Medical Sciences, vol. 68, no. 8, pp. 929–937, 2013. | spa |
dc.relation.references | [12] S. Lord, B. Galna, S. Coleman, A. Yarnall, D. Burn, and L. Rochester, “Cognition and gait show a selective pattern of association dominated by phenotype in incident parkinson’s disease,” Frontiers in aging neuroscience, vol. 6, p. 249, 2014. | spa |
dc.relation.references | [13] A.-M. De Cock, E. Fransen, S. Perkisas, V. Verhoeven, O. Beauchet, M. Vandewoude, and R. Remmen, “Comprehensive quantitative spatiotemporal gait analysis identifies gait characteristics for early dementia subtyping in community dwelling older adults,” Frontiers in neurology, vol. 10, p. 313, 2019. | spa |
dc.relation.references | [14] R. Morris, S. Lord, J. Bunce, D. Burn, and L. Rochester, “Gait and cognition: mapping the global and discrete relationships in ageing and neurodegenerative disease,” Neuroscience & Biobehavioral Reviews, vol. 64, pp. 326–345, 2016. | spa |
dc.relation.references | [15] C. Baiano, P. Barone, L. Trojano, and G. Santangelo, “Prevalence and clinical aspects of mild cognitive impairment in parkinson’s disease: A meta-analysis,” Movement Disorders, vol. 35, no. 1, pp. 45–54, 2020. | spa |
dc.relation.references | [16] A. Moncada-Torres, M. C. van Maaren, M. P. Hendriks, S. Siesling, and G. Geleijnse, “Explainable machine learning can outperform cox regression predictions and provide insights in breast cancer survival,” Scientific reports, vol. 11, no. 1, p. 6968, 2021. | spa |
dc.relation.references | [17] G. Álvarez Hernández, “Limitaciones metodológicas de la epidemiología moderna y una alternativa para superarlas: la epidemiología sociocultural,” Región y sociedad, vol. 20, no. SPE2, pp. 51–75, 2008. | spa |
dc.relation.references | [18] I. Martínez-Baz, I. Delfrade, and J. Etxeberria, “Characteristics and statistical methods used in original articles published in public health journals in spain,” in Anales Del Sistema Sanitario de Navarra, vol. 41, pp. 347–354, 2018. | spa |
dc.relation.references | [19] D. A. Morales, Y. Vives-Gilabert, B. Gómez-Ansón, E. Bengoetxea, P. Larrañaga, C. Bielza, J. Pagonabarraga, J. Kulisevsky, I. Corcuera-Solano, and M. Delfino, “Predicting dementia development in parkinson’s disease using bayesian network classifiers,” Psychiatry Research: NeuroImaging, vol. 213, no. 2, pp. 92–98, 2013. | spa |
dc.relation.references | [20] S. N. Gomperts, J. J. Locascio, D. Rentz, A. Santarlasci, M. Marquie, K. A. Johnson, and J. H. Growdon, “Amyloid is linked to cognitive decline in patients with parkinson disease without dementia,” Neurology, vol. 80, no. 1, pp. 85–91, 2013. | spa |
dc.relation.references | [21] P.-H. Chen, T.-Y. Hou, F.-Y. Cheng, and J.-S. Shaw, “Prediction of cognitive degeneration in parkinson’s disease patients using a machine learning method,” Brain Sciences, vol. 12, no. 8, p. 1048, 2022. | spa |
dc.relation.references | [22] F. Pieruccini-Faria, S. E. Black, M. Masellis, E. E. Smith, Q. J. Almeida, K. Z. Li, L. Bherer, R. Camicioli, and M. Montero-Odasso, “Gait variability across neurodegenerative and cognitive disorders: Results from the canadian consortium of neurodegeneration in aging (ccna) and the gait and brain study,” Alzheimer’s & Dementia, vol. 17, no. 8, pp. 1317–1328, 2021. | spa |
dc.relation.references | [23] P.-H. Chen, C.-W. Lien, W.-C. Wu, L.-S. Lee, and J.-S. Shaw, “Gait-based machine learning for classifying patients with different types of mild cognitive impairment,” Journal of medical systems, vol. 44, pp. 1–6, 2020. | spa |
dc.relation.references | [24] D. Trabassi, M. Serrao, T. Varrecchia, A. Ranavolo, G. Coppola, R. De Icco, C. Tassorelli, and S. F. Castiglia, “Machine learning approach to support the detection of parkinson’s disease in imu-based gait analysis,” Sensors, vol. 22, no. 10, p. 3700, 2022. | spa |
dc.relation.references | [25] A. Shahzad, A. Dadlani, H. Lee, and K. Kim, “Automated prescreening of mild cognitive impairment using shank-mounted inertial sensors based gait biomarkers,” IEEE Access, vol. 10, pp. 15835–15844, 2022. | spa |
dc.relation.references | [26] S. Toledo-Cortés, D. H. Useche, H. Müller, and F. A. González, “Grading diabetic retinopathy and prostate cancer diagnostic images with deep quantum ordinal regression,” Computers in biology and medicine, vol. 145, p. 105472, 2022. | spa |
dc.relation.references | [27] I. H. Sarker, “Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions,” SN Computer Science, vol. 2, no. 6, p. 420, 2021. | spa |
dc.relation.references | [28] K. Marek, D. Jennings, S. Lasch, A. Siderowf, C. Tanner, T. Simuni, C. Coffey, K. Kieburtz, E. Flagg, S. Chowdhury, et al., “The parkinson progression marker initiative (ppmi),” Progress in neurobiology, vol. 95, no. 4, pp. 629–635, 2011. | spa |
dc.relation.references | [29] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. | spa |
dc.relation.references | [31] S. Lerman and C. Manski, “On the use of simulated frequencies to approximate choice probabilities,” Structural analysis of discrete data with econometric applications, vol. 10, pp. 305–319, 1981. | spa |
dc.relation.references | [32] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” 2017. | spa |
dc.relation.references | [33] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mané, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viégas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, “TensorFlow: Large-scale machine learning on heterogeneous systems,” 2015. Software available from tensorflow.org. | spa |
dc.relation.references | [34] Z. Li, J. Zhu, J. Liu, M. Shi, P. Liu, J. Guo, Z. Hu, S. Liu, and D. Yang, “Using dual-task gait to recognize alzheimer’s disease and mild cognitive impairment: a cross-sectional study,” Frontiers in Human Neuroscience, vol. 17, 2023. | spa |
dc.relation.references | [35] T. Krasovsky, A. Lamontagne, A. G. Feldman, and M. F. Levin, “Effects of walking speed on gait stability and interlimb coordination in younger and older adults,” Gait & posture, vol. 39, no. 1, pp. 378–385, 2014. | spa |
dc.relation.references | [36] J. A. Cohen and J. Verghese, “Gait and dementia,” Handbook of clinical neurology, vol. 167, pp. 419–427, 2019. | spa |
dc.relation.references | [37] E. I. Baron, M. M. Koop, M. C. Streicher, A. B. Rosenfeldt, and J. L. Alberts, “Altered kinematics of arm swing in parkinson’s disease patients indicates declines in gait under dual-task conditions,” Parkinsonism & related disorders, vol. 48, pp. 61–67, 2018. | spa |
dc.relation.references | [38] V. N. Poole, S. Oveisgharan, L. Yu, R. J. Dawe, S. E. Leurgans, S. Zhang, K. Arfanakis, A. S. Buchman, and D. A. Bennett, “Volumetric brain correlates of gait associated with cognitive decline in community-dwelling older adults,” Frontiers in Aging Neuroscience, vol. 15, 2023. | spa |
dc.relation.references | [39] I. Hoang, M. Ranchet, R. Derollepot, F. Moreau, and L. Paire-Ficout, “Measuring the cognitive workload during dual-task walking in young adults: a combination of neurophysiological and subjective measures,” Frontiers in human neuroscience, vol. 14, p. 592532, 2020. | spa |
dc.relation.references | [40] W. Wright, V. Gurfinkel, J. Nutt, F. Horak, and P. Cordo, “Axial hypertonicity in parkinson’s disease: direct measurements of trunk and hip torque,” Experimental neurology, vol. 208, no. 1, pp. 38–46, 2007. | spa |
dc.relation.references | [41] M. Mancini, F. B. Horak, C. Zampieri, P. Carlson-Kuhta, J. G. Nutt, and L. Chiari, “Trunk accelerometry reveals postural instability in untreated parkinson’s disease,” Parkinsonism & related disorders, vol. 17, no. 7, pp. 557–562, 2011. | spa |
dc.relation.references | [42] M. Duncan, J. Cholfin, and L. Restrepo, “Clinical reasoning: a 72-year-old man with rapid cognitive decline and unilateral muscle jerks,” Neurology, vol. 82, no. 22, pp. e194–e197, 2014. | spa |
dc.relation.references | [43] A. Mirelman, A. Weiss, A. S. Buchman, D. A. Bennett, N. Giladi, and J. M. Hausdorff, “Association between performance on timed up and go subtasks and mild cognitive impairment: further insights into the links between cognitive and motor function,” Journal of the American Geriatrics Society, vol. 62, no. 4, pp. 673–678, 2014. | spa |
dc.relation.references | [44] A. Pantall, P. Suresparan, L. Kapa, R. Morris, A. Yarnall, S. Del Din, and L. Rochester, “Postural dynamics are associated with cognitive decline in parkinson’s disease,” Frontiers in neurology, vol. 9, p. 1044, 2018. | spa |
dc.relation.references | [45] T. Chen, Y. Fan, X. Zhuang, D. Feng, Y. Chen, P. Chan, and Y. Du, “Postural sway in patients with early parkinson’s disease performing cognitive tasks while standing,” Neurological research, vol. 40, no. 6, pp. 491–498, 2018. | spa |
dc.relation.references | [46] C. J. Lamoth, F. J. van Deudekom, J. P. van Campen, B. A. Appels, O. J. de Vries, and M. Pijnappels, “Gait stability and variability measures show effects of impaired cognition and dual tasking in frail people,” Journal of neuroengineering and rehabilitation, vol. 8, pp. 1–9, 2011. | spa |
dc.relation.references | [47] T. Doi, H. Makizako, H. Shimada, D. Yoshida, K. Ito, T. Kato, H. Ando, and T. Suzuki, “Brain atrophy and trunk stability during dual-task walking among older adults,” Journals of Gerontology Series A: Biomedical Science and Medical Sciences, vol. 67, no. 7, pp. 790–795, 2012. | spa |
dc.rights.accessrights | info:eu-repo/semantics/openAccess | spa |
dc.rights.license | Atribución-NoComercial-SinDerivadas 4.0 Internacional | spa |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | spa |
dc.subject.ddc | 610 - Medicina y salud::616 - Enfermedades | spa |
dc.subject.decs | Estudio Comparativo | spa |
dc.subject.decs | Comparative Study | eng |
dc.subject.decs | Comorbilidad | spa |
dc.subject.decs | Comorbidity | eng |
dc.subject.decs | Machine Learning | eng |
dc.subject.decs | Pronóstico | spa |
dc.subject.decs | Prognosis | eng |
dc.subject.proposal | Deterioro cognitivo | spa |
dc.subject.proposal | Evaluación de la marcha | spa |
dc.subject.proposal | Aprendizaje automático interpretable | spa |
dc.subject.proposal | Biomarcadores no invasivos | spa |
dc.subject.proposal | Enfermedad de Parkinson | spa |
dc.subject.proposal | Cognitive impairment | eng |
dc.subject.proposal | Gait assessment | eng |
dc.subject.proposal | Interpretive machine learning | eng |
dc.subject.proposal | Non-invasive biomarkers | eng |
dc.subject.proposal | Parkinson's disease | eng |
dc.title | Cognitive impairment inference in Parkinson's disease patients from spatiotemporal gait assessments using machine learning | eng |
dc.title.translated | Inferencia de deterioro cognitivo en pacientes con enfermedad de Parkinson a partir de evaluaciones espaciotemporales de la marcha mediante aprendizaje automático | spa |
dc.type | Trabajo de grado - Maestría | spa |
dc.type.coar | http://purl.org/coar/resource_type/c_bdcc | spa |
dc.type.coarversion | http://purl.org/coar/version/c_ab4af688f83e57aa | spa |
dc.type.content | Text | spa |
dc.type.driver | info:eu-repo/semantics/masterThesis | spa |
dc.type.redcol | http://purl.org/redcol/resource_type/TM | spa |
dc.type.version | info:eu-repo/semantics/acceptedVersion | spa |
oaire.accessrights | http://purl.org/coar/access_right/c_abf2 | spa |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- 75104416.2025.pdf
- Tamaño:
- 990.39 KB
- Formato:
- Adobe Portable Document Format
- Descripción:
- Tesis de Maestría Ingeniería Biomédica
Bloque de licencias
1 - 1 de 1
No hay miniatura disponible
- Nombre:
- license.txt
- Tamaño:
- 5.74 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción: