Advertisement

A dynamic Bayesian network for estimating the risk of falls from real gait data

  • German CuayaEmail author
  • Angélica Muñoz-Meléndez
  • Lidia Nuñez Carrera
  • Eduardo F. Morales
  • Ivett Quiñones
  • Alberto I. Pérez
  • Aldo Alessi
Original Article

Abstract

Pathological and age-related changes may affect an individual’s gait, in turn raising the risk of falls. In elderly, falls are common and may eventuate in severe injuries, long-term disabilities, and even death. Thus, there is interest in estimating the risk of falls from gait analysis. Estimation of the risk of falls requires consideration of the longitudinal evolution of different variables derived from human gait. Bayesian networks are probabilistic models which graphically express dependencies among variables. Dynamic Bayesian networks (DBNs) are a type of BN adequate for modeling the dynamics of the statistical dependencies in a set of variables. In this work, a DBN model incorporates gait derived variables to predict the risk of falls in elderly within 6 months subsequent to gait assessment. Two DBNs were developed; the first (DBN1; expert-guided) was built using gait variables identified by domain experts, whereas the second (DBN2; strictly computational) was constructed utilizing gait variables picked out by a feature selection algorithm. The effectiveness of the second model to predict falls in the 6 months following assessment is 72.22 %. These results are encouraging and supply evidence regarding the usefulness of dynamic probabilistic models in the prediction of falls from pathological gait.

Keywords

Probabilistic models Dynamic Bayesian networks Elderly Gait analysis Risk of falls 

Notes

Acknowledgments

This research was supported by the National Institute for Astrophysics, Optics and Electronics (INAOE), and the Mexican National Council for Science and Technology (CONACyT), through the scholarship for doctoral studies 174498. The researchers of the Human Motion Analysis Laboratory of the National Institute of Rehabilitation in Mexico provided the gait data to develop the models presented in this work, under the research grant 01-042 of CONACyT-Health Sector Fund 2003.

References

  1. 1.
    Allan LM., Ballard CG, Rowan EN, Kenny RA (2009) Incidence and prediction of falls in dementia: a prospective study in older people. Public Libr Sci 4(5):e5521Google Scholar
  2. 2.
    Armitage P, Berry G, Matthews JNS (2001) Statistical methods in medical research, 4th edn. Wiley-Blackwell, New York, pp 88–89Google Scholar
  3. 3.
    Arroyo-Figueroa G, Sucar LE (2005) Temporal bayesian network of events for diagnosis and prediction in dynamic domains. Appl Intell 23(2):77-86CrossRefGoogle Scholar
  4. 4.
    BenAbdelkader C, Cutler R, Davis LS (2006) View-invariant estimation of height and stride for gait recognition. Biometric Authentication 2359:155-167CrossRefGoogle Scholar
  5. 5.
    Bhatt T, Espy D, Yang F, Pai YC (2011) Dynamic gait stability, clinical correlates, and prognosis of falls among community-dwelling older adults. Arch Phys Med Rehabil 92(5):799–805PubMedCrossRefGoogle Scholar
  6. 6.
    Bilney B, Morris M, Webster K (2003) Concurrent related validity of the gaitrite walkway system for quantification of the spatial and temporal parameters of gait. Gait Posture 17(1):68–74PubMedCrossRefGoogle Scholar
  7. 7.
    Borsuk ME, Stow CA, Reckhow KH (2004) A Bayesian network of eutrophication models for synthesis, prediction, and uncertainty analysis. Ecol Model 173(2–3):219 - 239CrossRefGoogle Scholar
  8. 8.
    Box GE, Hunter WG, Hunter JS (2005) Statistics for experimenters: design, innovation, and discovery, 2nd edn. Wiley-Interscience, New York, pp 19–43Google Scholar
  9. 9.
    Callisaya ML, Blizzard L, Schmidt MD, Martin KL, McGinley JL, Sanders LM, Srikanth VK (2011) Gait, gait variability and the risk of multiple incident falls in older people: a population-based study. Age Ageing 40(4):481–487PubMedCrossRefGoogle Scholar
  10. 10.
    Charitos T, Gaag L, Visscher S, Schurink K, Lucas P (2009) A dynamic bayesian network for diagnosing ventilator-associated pneumonia in ICU patients. Expert Syst Appl 36(2):1249–1258CrossRefGoogle Scholar
  11. 11.
    Cooper GF, Herskovits E (1992) A bayesian method for the induction of probabilistic networks from data. Mach Learn 9(4):309–347Google Scholar
  12. 12.
    Dabiri F, Vahdatpour A, Noshadi H, Hagopian H, Sarrafzadeh M (2008) Ubiquitous personal assistive system for neuropathy. In: Proceedings of the 2nd international workshop on systems and networking support for health care and assisted living environments. Breckenridge, pp 171–176Google Scholar
  13. 13.
    Dean T, Kanazawa K (1989) Persistence and probabilistic inference. IEEE Trans Syst Man Cybern 19(3):574–585CrossRefGoogle Scholar
  14. 14.
    Devore JL (1999) Probability and statistics for engineering and the sciences, 5th edn. Duxbury Pr, pp 155–182 Google Scholar
  15. 15.
    Galán SF, Arroyo-Figueroa G, Dez FJ, Sucar LE (2007) Comparison of two types of event bayesian networks: a case study. Appl Artif Intell 21(3):185–209CrossRefGoogle Scholar
  16. 16.
    Gu T, Pung HK, Zhang DQ, Pung HK, Zhang DQ (2004) A bayesian approach for dealing with uncertain contexts. In: Proceedings of the 2nd international conference on pervasive computing, vol 176, ViennaGoogle Scholar
  17. 17.
    Hahn ME, Chou LS (2005) A model for detecting balance impairment and estimating falls risk in the elderly. Ann Biomed Eng 33:811–820PubMedCrossRefGoogle Scholar
  18. 18.
    Haworth JM (2008) Gait, aging and dementia. Rev Clin Gerontol 18(1):39–52CrossRefGoogle Scholar
  19. 19.
    Kale A, Sundaresan A, Rajagopalan AN, Cuntoor NP, Roy-Chowdhury AK, Kruger V, Chellappa R (2004) Identification of humans using gait. Image Process 13:1163–1173CrossRefGoogle Scholar
  20. 20.
    Kangasa M, Konttilaab A, Lindgren P, Winbladad I, Jamsa T (2008) Comparison of low-complexity fall detection algorithms for body attached accelerometers. Gait Posture 28(2):285–291CrossRefGoogle Scholar
  21. 21.
    Kohavi JG (1997) Wrappers for feature subset selection. Artif Intell 97(1–2):272-324Google Scholar
  22. 22.
    Lam T, Lee R, Zhang D (2007) Human gait recognition by the fusion of motion and static spatio-temporal templates. Pattern Recognit 40(9):2563–2573CrossRefGoogle Scholar
  23. 23.
    Lee HJ, Chou LS (2006) Detection of gait instability using the center of mass and center of pressure inclination angles. Arch Phys Med Rehabil 87(4):569–575PubMedCrossRefGoogle Scholar
  24. 24.
    Lopez-Meyer P, Fulk GD, Sazonov ES (2011) Automatic detection of temporal gait parameters in poststroke individuals. Inf Technol Biomed 15(4):594–601CrossRefGoogle Scholar
  25. 25.
    López-Nava IH, Muñoz-Meléndez A (2010) Towards ubiquitous acquisition and processing of gait parameters. In: Proceedings of the 9th Mexican international conference on artificial intelligence, Pachuca, pp 410–421Google Scholar
  26. 26.
    Madsen AL, Lang M, Kjrulff UB, Jensen F (2003) The Hugin tool for learning bayesian networks. In: Proceedings of the 7th European conference on symbolic and quantitative approaches to reasoning with uncertainty, Aalborg, pp 594–605Google Scholar
  27. 27.
    Madu EO, Stalbovskaya V, Hamadicharef B, Ifeachor EC, Van S, Timmerman D (2005) Preoperative ovarian cancer diagnosis using neuro-fuzzy approach. In: Proceedings of the European conference on emergent aspects in clinical data analysis, Italy, pp 1–8Google Scholar
  28. 28.
    Maki BE (1997) Gait changes in older adults: predictors of falls or indicators of fear. J Am Geriatr Soc 45(3):313–320PubMedGoogle Scholar
  29. 29.
    Menz HB, Lord SR, Fitzpatrick RC (2003) Age-related differences in walking stability. Age Ageing 32(2):137–142PubMedCrossRefGoogle Scholar
  30. 30.
    Meyer D (1997) Human gait classification based on hidden markov models. In: Proceedings of the 3D image analysis and synthesis conference, Erlangen, pp 139–146Google Scholar
  31. 31.
    Papageorgiou EI, Papandrianos NI, Karagianni G, Kyriazopoulos G, Sfyras D (2009) Fuzzy cognitive map based approach for assessing pulmonary infections. In: Proceedings of the 18th international symposium on methodologies for intelligent systems, Prague, pp 109–118Google Scholar
  32. 32.
    Phillips PJ, Sarkar S, Robledo I, Grother P, Bowyer K (2002) The gait identification challenge problem: data sets and baseline algorithm. In: Proceedings of the 16th international conference on pattern recognition, Qubec, pp 385–388Google Scholar
  33. 33.
    Rogers ME, Rogers NL, Takeshima N, Islam MM (2003) Methods to assess and improve the physical parameters associated with fall risk in older adults. Prev Med 36(3):255–264PubMedCrossRefGoogle Scholar
  34. 34.
    Romero-Moreno M, Martínez-Trinidad JF, Carrasco-Ochoa JA (2008) Gait recognition based on silhouette, contour and classifier ensembles. In: Proceedings of the 13th Iberoamerican congress on pattern recognition. Havana, pp 527–534Google Scholar
  35. 35.
    Saboune J, Charpillet F (2005) Markerless human motion capture for gait analysis. In: Proceedings of the 3rd European medical and biological engineering conference, PragueGoogle Scholar
  36. 36.
    Whittle MW (2001) Gait analysis: an introduction, 3rd edn. Butterworth-Heinemann, pp 127–160Google Scholar
  37. 37.
    Winter DA, Patla AE, Frank JS, Walt SE (1990) Biomechanical pattern changes in the fit and healthy elderly. Phys Therapy 70:340–347Google Scholar
  38. 38.
    Yang F, Bhatt T, Pai YC (2009) Role of stability and limb support in recovery against a fall following a novel slip induced in different daily activities. Biomechanics 42:1903–1908CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2012

Authors and Affiliations

  • German Cuaya
    • 1
    Email author
  • Angélica Muñoz-Meléndez
    • 1
  • Lidia Nuñez Carrera
    • 2
  • Eduardo F. Morales
    • 1
  • Ivett Quiñones
    • 2
  • Alberto I. Pérez
    • 2
  • Aldo Alessi
    • 2
  1. 1.Computer Science DepartmentInstituto Nacional de Astrofsica ptica y ElctroniaTonantzintlaMexico
  2. 2.National Institute of RehabilitationHuman Motion Analysis LaboratoryMexico, D.F.Mexico

Personalised recommendations