Abstract
Objective: To develop an unsupervised learning approach to study the prosthesis adaptation process using functional assessment tests and their scales, health-related behaviors, and socio-demographic da-ta.
Subjects: 199 low-cost lower limb prosthesis users with below-knee and/or above-knee amputation.
Methods: For the unsupervised learning approach, different methods, such as K-Means, Agglomerative Clustering, and Fuzzy C-Means, were used to comprise clusters and classify individuals based on factors associated with the lower limb prosthesis. Davies Boulding, Dunn, and Calinski-Harabasz index as well as the Silhouette coefficient were used to validate, study, and understand the resulting clusters from the dataset.
Results: The unsupervised learning approach strategies provided patient phenotyping clusters that could be interpreted as adaptation levels in low-cost lower limb prosthesis users, while allowing the interpretation and patient phenotyping by physicians.
Conclusions : Patient care customization is important, especially in multidimensional problems. To do so, it is necessary to use historic-data-based tools, which allow better control of the current state of the prosthesis and the person's functional capacity.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arelekatti, V.N.M.: Detc2015–47385 Passive Prosthetic Knee for Users With Transfemoral Amputation, pp. 1–8 (2015)
Sansam, K., Neumann, V., O’Connor, R., Bhakta, B.: Predicting walking ability following lower limb amputation: a systematic review of the literature. J. Rehabil. Med. 41(8), 593–603 (2009). https://doi.org/10.2340/16501977-0393
Baars, E.C., Schrier, E., Dijkstra, P.U., Geertzen, J.H.B.: Prosthesis satisfaction in lower limb amputees: A systematic review of associated factors and questionnaires. Medicine 97(39), e12296 (2018). https://doi.org/10.1097/MD.0000000000012296
Zoellick, C.M.: Informe Mundial La Discapacidad Sobre R E S U M E N”, B. R. Organ. Mund. la Salud, p. 27 (2011).
Biddiss, E.A., Chau, T.T.: Multivariate prediction of upper limb prosthesis acceptance or rejection. Disabil. Rehabil.: Assist. Technol. 3(4), 181–192 (2008). https://doi.org/10.1080/17483100701869826
Salinas-Durán, F.A., et al.: “Guía de práctica clínica para el diagnóstico y tratamiento preoperatorio, intraoperatorio y posoperatorio de la persona amputada, la prescripción de la prótesis y la rehabilitación integral: Recomendaciones para el tratamiento de rehabilitación en adultos”. Iatreia 29(4), S-82–S-95 (2016)
Matamoros-Villegas, A., Plata-Contreras, J., Payares-Álvarez, K.: Correlation among tests and functional assessment scales in the follow-up of prosthetic adaptation in people with lower limb amputation. Rehabilitacion (2021)
Shamout, F., Zhu, T., Clifton, D.A.: Machine learning for clinical outcome prediction. IEEE Rev. Biomed. Eng. 14, 116–126 (2021). https://doi.org/10.1109/RBME.2020.3007816
Chahar, R.: Computational decision support system in healthcare: a review and analysis. Int. J. Adv. Technol. Eng. Explor. 8(75), 199–220 (2021). https://doi.org/10.19101/IJATEE.2020.762142
Ritter, M.A., Berend, M.E., Harty, L.D., Davis, K.E., Meding, J.B., Michael Keating, E.: Predicting range of motion after revision total knee arthroplasty. J. Arthro. 19(3), 338–343 (2004). https://doi.org/10.1016/j.arth.2003.11.001
Syed Thouheed Ahmed, S., Thanuja, K., Guptha, N.S., Narasimha, S.: Telemedicine approach for remote patient monitoring system using smart phones with an economical hardware kit. In: 2016 International Conference on Computing Technologies and Intelligent Data Engineering. ICCTIDE 2016, pp. 1–4, 2016.
Zimina, E.Y., Novopashin, M.A., Shmid., A.V.:Application of medical data classification methods for a medical decision support system. CEUR Workshop Proceedinggs, vol. 2843 (2021)
Bose, E., Radhakrishnan, K.: Using unsupervised machine learning to identify subgroups among home health patients with heart failure using telehealth. CIN: Comput. Inf. Nurs. 36(5), 242–248 (2018). https://doi.org/10.1097/CIN.0000000000000423
John, B., Wickramasinghe, N.: Clustering questions in healthcare social question answering based on design science theory. In: Wickramasinghe, N., Schaffer, J.L. (eds.) Theories to Inform Superior Health Informatics Research and Practice. HDIA, pp. 95–108. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72287-0_7
Nunes, M.A., Campos-Neto, I., Ferraz, L.C., Lima, C.A., Rocha, T.O., Rocha, T.F.: Adaptation to prostheses among patients with major lower-limb amputations and its association with sociodemographic and clinical data. Sao Paulo Med. J. 132(2), 80–84 (2014). https://doi.org/10.1590/1516-3180.2014.1322572
Wong, C.K., Gibbs, W., Chen, E.S.: Use of the houghton scale to classify community and household walking ability in people with lower-limb amputation: criterion-related validity. Arch. Phys. Med. Rehabil. 97(7), 1130–1136 (2016)
Houghton, A.D., Taylor, P.R., Thurlow, S., Rootes, E., McColl, I.: Success rates for rehabilitation of vascular amputees: implications for preoperative assessment and amputation level. British J. Surg. 79(8), 753–755 (1992). https://doi.org/10.1002/bjs.1800790811
Sangve, S.S.B.S.M.: Clinical decision support system using SVM with the preservation of privacy. Int. J. Sci. Res 5(7), 2122–2125 (2016)
Biddiss, E.A., Chau, T.T.: Multivariate prediction of upper limb prosthesis acceptance or rejection. Disabil. Rehabil.: Assist. Technol. 3(4), 181–192 (2008). https://doi.org/10.1080/17483100701869826f
Kim, T.K.: Understanding one-way anova using conceptual figures. Korean J. Anesthesiol. 70(1), 22–26 (2017)
Cardona, D., Uribe, J.: Identificación de las variables cinéticas, cinemáticas y funcionales en el proceso de adaptación protésica y la rehabilitación postprotésica en”, Cent. Doc. Ing. (Bl. 20–146)Colección Tesis Electrónicas, Univ. Antioquia. (2018)
Malembaka, E.B., et al.: A new look at population health through the lenses of cognitive, functional and social disability clustering in eastern DR Congo: a community-based cross-sectional study. BMC Public Health 19(1), 1–13 (2019)
McInnes, L., Healy, J., Melville, J.: UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv (2018)
Indulska, M.: The curse of dimensionality in data quality. ACIS 2013 Proc. 2013(December), 4–6 (2013)
Dilts, D., Khamalah, J., Plotkin, A.: Using cluster analysis for medical resource decision making. Med. Dec. Making 15(4), 333–346 (1995). https://doi.org/10.1177/0272989X9501500404
Ogbuabor, G., Ugwoke, F.N.: Clustering algorithm for a healthcare dataset using silhouette score value. Int. J. Comput. Sci. Inf. Technol. 10(2), 27–37 (2018). https://doi.org/10.5121/ijcsit.2018.10203
Graham, L.A., Fyfe, N.C.M.: Prosthetic rehabilitation of amputees aged over 90 is usually successful. Disabil. Rehabil. 24(13), 700–701 (2002). https://doi.org/10.1080/09638280210142194
Windgassen, S., Moss-Morris, R., Goldsmith, K., Chalder, T.: The importance of cluster analysis for enhancing clinical practice: an example from irritable bowel syndrome. J. Mental Health 27(2), 94–96 (2018). https://doi.org/10.1080/09638237.2018.1437615
Malli, S., Dr. Nagesh, H.R., Dr. Joshi, H.G.: A study on rural health care data sets using clustering algorithms. Int. J. Eng. Res. 3(9), 546–548 (2014)
Granato, D., Santos, J.S., Escher, G.B., Ferreira, B.L., Maggio, R.M.: Use of principal component analysis (PCA) and hierarchical cluster analysis (HCA) for multivariate association between bioactive compounds and functional properties in foods: a critical perspective. Trends Food Sci. Technol. 72, 83–90 (2018)
Siriwardena, G.J.A., Bertrand, P.V.: Factors influencing rehabilitation of arteriosclerotic lower limb amputees. J. Rehabil. Res. Dev. 28(3), 35 (1991). https://doi.org/10.1682/JRRD.1991.07.0035
Islam, T., Rafa, S.R., Kibria, G.: Early Prediction of Heart Disease Using PCA and Hybrid Genetic Algorithm with k -Means, pp. 19–21 (2020)
Acknowledgements
This work was supported by Medellín Higher Education Agency (Sapiencia) and the Ministry of Science, Technology, and Innovation of Colombia (Minciencias), and is part of a multi-disciplinary study called “Evaluation of a mixed strategy to improve the adherence of subjects amputated by Improvised Explosive Devices (IED) to the use of low-cost lower limb prostheses” with code 111580863475. We express our gratitude to the Mahavir Kmina Corporation and its entire work team, who were a great support throughout the research.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Ethics declarations
Conflict of Interest
The authors declare that there is no conflict of interest regarding the publication of this paper.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Colmenares, G.M., Nieto Aristizabal, J.K. (2021). Multivariate Analysis of Adaptation Level in Low-Cost Lower Limb Prostheses: An Unsupervised Learning Approach. In: Figueroa-García, J.C., Díaz-Gutierrez, Y., Gaona-García, E.E., Orjuela-Cañón, A.D. (eds) Applied Computer Sciences in Engineering. WEA 2021. Communications in Computer and Information Science, vol 1431. Springer, Cham. https://doi.org/10.1007/978-3-030-86702-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-86702-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86701-0
Online ISBN: 978-3-030-86702-7
eBook Packages: Computer ScienceComputer Science (R0)