Comparison of Machine Learning Models to Predict Risk

• Autorzy: Cuaya-Simbro German , Perez-Sanpablo Alberto-Isaac , Muñoz-Meléndez Angélica , Quiñones Ivett , Morales-Manzanares Eduardo-F. , Nuñez-Carrera Lidia

Identyfikatory

DOI

10.2478/fcds-2020-0005

• Języki publikacji: EN

Abstrakty

EN

Falls are a multifactorial cause of injuries for older people. Subjects with osteoporosis are more vulnerable to falls. The focus of this study is to investigate the performance of the different machine learning models built on spatiotemporal gait parameters to predict falls particularly in subjects with osteoporosis. Spatiotemporal gait parameters and prospective registration of falls were obtained from a sample of 110 community dwelling older women with osteoporosis (age 74.3 ± 6.3) and 143 without osteoporosis (age 68.7 ± 6.8). We built four different models, Support Vector Machines, Neuronal Networks, Decision Trees, and Dynamic Bayesian Networks (DBN), for each specific set of parameters used, and compared them considering their accuracy, precision, recall and F-score to predict fall risk. The F-score value shows that DBN based models are more efficient to predict fall risk, and the best result obtained is when we use a DBN model using the experts’ variables with FSMC’s variables, mixed variables set, obtaining an accuracy of 80%, and recall of 73%. The results confirm the feasibility of computational methods to complement experts’ knowledge to predict risk of falling within a period of time as high as 12 months.

Słowa kluczowe

EN

GaitRite data; prognosis falls; computational methods; osteoporosis

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2020
• Tom: Vol. 45, No. 2
• Strony: 65--77
• Opis fizyczny: Bibliogr. 25 poz., rys., tab.

Twórcy

autor

Cuaya-Simbro German

• Higher Technological Institute of the East of State of Hidalgo, Carretera Apan-Tepeapulco Km 3.5 , Colonia Las Peñitas, Apan Hidalgo, México.

autor

Perez-Sanpablo Alberto-Isaac

• National Rehabilitation Institute, Mexico-Xochimilco Av. 289, Arenal de Guadalupe, 14389, Mexico City, Mexico

autor

Muñoz-Meléndez Angélica

• National Institute of Astrophysics, Optics and Electronics, Luis Enrique Erro 1, Santa Maria Tonatzintla, 72840 Puebla, Mexico

autor

Quiñones Ivett

• National Rehabilitation Institute, Mexico-Xochimilco Av. 289, Arenal de Guadalupe, 14389, Mexico City, Mexico

autor

Morales-Manzanares Eduardo-F.

• National Institute of Astrophysics, Optics and Electronics, Luis Enrique Erro 1, Santa Maria Tonatzintla, 72840 Puebla, Mexico

autor

Nuñez-Carrera Lidia

• National Rehabilitation Institute, Mexico-Xochimilco Av. 289, Arenal de Guadalupe, 14389, Mexico City, Mexico

Bibliografia

• [1] Barry E., Galvin R., Keogh C., Horgan F., Fahey T., Is the Timed Up and Go test a useful predictor of risk of falls in community dwelling older adults: a systematic review and metaanalysis, BMC geriatrics, 14, 1, 2014, doi:10.1186/1471-2318-14-14.
• [2] Beauchet O., Freiberger E., Annweile, C., Kressig R.W., Herrmann F.R., Allali G., Test-retest reliability of stride time variability while dual tasking in healthy and demented adults with frontotemporal degeneration, Journal of neuroengineering and rehabilitation, 8, 1, 2011, doi:10.1186/1743-0003-8-37.
• [3] Bruijn S.M., Meijer O.G., Beek P.J., van Dieёn J.H., Assessing the stability of human locomotion: a review of current measures, Journal of the Royal Society Interface, 10, 83, 2013, doi: 10.1098/rsif.2012.0999.
• [4] Callisaya M.L., Blizzard L., McGinley J.L., Srikanth V.K., Risk of falls in older people during fast-walking - The TASCOG study, Gait and Posture, 36, 3, 2012, 510-515, doi:10.1016/j.gaitpost.2012.05.003.
• [5] Cuaya G., Muñoz-Meléndez A., Morales E.F. A minority class feature selection method, in: C. San Martin, S. W. Kim (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2011, Springer, Berlin, 2011, 417-424.
• [6] Cuaya G., Muñoz-Meléndez A., Carrera L.N., Morales E.F., Quiñones I., Pérez A.I., Alessi A., A dynamic Bayesian network for estimating the risk of falls from real gait data, Medical and Biological Engineering and Computing, 51, 1-2, 2013, 29-37, doi:10.1007/s11517-012-0960-2.
• [7] Drover D., Howcroft J., Kofman J., Lemaire E.D., Faller Classification in Older Adults Using Wearable Sensors Based on Turn and Straight-Walking Accelerometer-Based Features, Sensors, 17, 6, 2017, 13-21, doi:10.3390/s17061321.
• [8] Gervásio F.M., Santos G.A., Ribeiro D.M., Menezes R., Falls risk detection based on spatiotemporal parameters of three-dimensional gait analysis in healthy adult women from 50 to 70 years old, Fisioterapia e Pesquisa, 23, 4, 2016, 358-364, https://dx.doi.org/10.1590/1809-2950/15661923042016.
• [9] Hamacher D., Schega L., Towards the importance of minimum toe clearance in level ground walking in a healthy elderly population, Gait & Posture, 40, 4, 2014, 727-729, doi:10.1016/j.gaitpost.2014.07.016.
• [10] Hamacher D., Hamacher D., Taylor W.R., Singh N.B., Schega L., Towards clinical application: Repetitive sensor position recalibration for improved reliability of gait parameters, Gait & Posture, 39, 4, 2014, 1146-1148, doi:10.1016/j.gaitpost.2014.01.020.
• [11] Hassoun M., Fundamentals of Artificial Neural Networks, MIT Press, Cambridge, MA, United States, 1999.
• [12] Howcroft J., Kofman J., Lemaire E.D., Review of fall risk assessment in geriatric populations using inertial sensors, Journal of NeuroEngineering and Rehabilitation, 10, 1, 2013, 1-12, doi:Artn 91\nDoi 10.1186/1743-0003-10-91.
• [13] Kabeshova A., Launay C.P., Gromov V.A., Annweiler C., Fantino B., Beauchet O., Artificial Neural Network and Falls in Community-Dwellers: A New Approach to Identify the Risk of Recurrent Falling?, Journal of the American Medical Directors Association, 16, 4, 2015, 277-281.
• [14] Kelsey J.L., Procter-Gray E., Berry S.D., Hannan M.T., Kiel D.P., Lipsitz L. a., Li W., Reevaluating the implications of recurrent falls in older adults: Location changes the inference, Journal of the American Geriatrics Society, 60, 3, 2012, 517-524, doi:10.1111/j.1532-5415.2011.03834.x.
• [15] Lai D.T.H., Begg R.K., Palaniswami M., SVM Models for Diagnosing Balance Problems Using Statistical Features of the Mtc Signal, International Journal of Computational Intelligence and Applications, 7, 3, 2008, 317-331, doi: 10.1142/S1469026808002314.
• [16] Lindsey C., Brownbill R.A., Bohannon R.A., Ilich J.Z., Association of physical performance measures with bone mineral density in postmenopausal women, Archives of Physical Medicine and Rehabilitation, 86, 6, 2005, 1102-1107, doi:10.1016/j.apmr.2004.09.028.
• [17] Livingston F., Implementation of Breiman's Random Forest Machine Learning Algorithm, Machine Learning, 2005, 1-13.
• [18] McGough E.L., Logsdon R.G., Kelly V.E., Teri L., Functional Mobility Limitations and Falls in Assisted Living Residents with Dementia, Journal of Geriatric Physical Therapy, 36, 1, 2012, doi:10.1519/JPT.0b013e318268de7f.
• [19] Nait A., Englebienne G., van Schooten K.S., Pijnappels M., Krose B., Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry, Sensors, 18, 2018, 1-14.
• [20] Perera S., Mody S.H., Woodman R.C., Studenski S.A., Meaningful change and responsiveness in common physical performance measures in older adults, Journal of the American Geriatrics Society, 54, 5, 2006, 743-749, doi:10.1111/j.1532- 5415.2006.00701.x.
• [21] Pfortmueller C., Reducing fall risk in the elderly: risk factors and fall prevention. Minerva Med, 105, 2014, 275-281.
• [22] Phelan E.A., Mahoney J.E., Voit J.C., Stevens J.A., Assessment and Management of Fall Risk in Primary Care Settings, Medical Clinics of North America, 99, 2, 2015, 281-293, doi:10.1016/j.mcna.2014.11.004.
• [23] Rong-En F., Pai-Hsuen C., Chih-Jen L., Working Set Selection Using Second Order Information for Training Support Vector Machines, Journal Machine Learning Research, 6, 2005, 1889-1918.
• [24] Smith M.I., de Lusignan S., Mullett D., Correa A., Tickner J., Jones S., Predicting Falls and when to Intervene in Older People: A Multilevel Logistical Regression Model and Cost Analysis, PloS one, 11, 7, 2016, doi:10.1371/journal.pone.0159365.
• [25] Webster K.E., Wittwer J.E., Feller, J.A., Validity of the GAITRite?? walkway system for the measurement of averaged and individual step parameters of gait, Gait & Posture, 22, 4, 2005, 317-321, doi:10.1016/j.gaitpost.2004.10.005.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).