access icon openaccess Automatic classifier based on heart rate variability to identify fallers among hypertensive subjects

Accidental falls are a major problem of later life. Different technologies to predict falls have been investigated, but with limited success, mainly because of low specificity due to a high false positive rate. This Letter presents an automatic classifier based on heart rate variability (HRV) analysis with the goal to identify fallers automatically. HRV was used in this study as it is considered a good estimator of autonomic nervous system (ANS) states, which are responsible, among other things, for human balance control. Nominal 24 h electrocardiogram recordings from 168 cardiac patients (age 72 ± 8 years, 60 female), of which 47 were fallers, were investigated. Linear and nonlinear HRV properties were analysed in 30 min excerpts. Different data mining approaches were adopted and their performances were compared with a subject-based receiver operating characteristic analysis. The best performance was achieved by a hybrid algorithm, RUSBoost, integrated with feature selection method based on principal component analysis, which achieved satisfactory specificity and accuracy (80 and 72%, respectively), but low sensitivity (51%). These results suggested that ANS states causing falls could be reliably detected, but also that not all the falls were due to ANS states.

Inspec keywords: principal component analysis; sensitivity analysis; data mining; neurophysiology; electrocardiography; feature selection; medical signal processing; signal classification

Other keywords: RUSBoost; high false positive rate; feature selection method; accidental falls; electrocardiogram recordings; data mining; heart rate variability; cardiac patients; human balance control; principal component analysis; nonlinear HRV properties; autonomic nervous system states; hypertensive subjects; linear HRV properties; subject-based receiver operating characteristic analysis; time 30 min; automatic classifier

Subjects: Digital signal processing; Other topics in statistics; Bioelectric signals; Electrical activity in neurophysiological processes; Knowledge engineering techniques; Electrodiagnostics and other electrical measurement techniques; Probability theory, stochastic processes, and statistics; Other topics in statistics; Signal processing and detection; Biology and medical computing

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
      • 51. Jha, S.S., Das, P.K., Nair, S.B.: ‘Automatic facial expression recognition using extended Ar-Lbp’, in Venugopal, K.R., Patnaik, L.M. (Eds.): ‘Wireless networks and computational intelligence’ (Springer, 2012).
    5. 5)
      • 23. Kuncheva, L.I., Rodríguez, J.J.: ‘An experimental study on rotation forest ensembles’, in Haindl, M., Kittler, J., Roli, F. (Eds): ‘Multiple classifier systems’ (Springer, 2007).
    6. 6)
    7. 7)
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
    16. 16)
    17. 17)
    18. 18)
      • 40. Richman, J.S., Moorman, J.R.: ‘Physiological time-series analysis using approximate entropy and sample entropy'‘, Am. J. Physiol. Heart Circ. Physiol., 2000, 278, (6), pp. H2039H2049.
    19. 19)
      • 34. Zong, W., Moody, G., Jiang, D.: ‘A robust open-source algorithm to detect onset and duration of Qrs complexes’, in Murray,, A. (Ed.): ‘Computers in cardiology’ (IEEE, 2003).
    20. 20)
    21. 21)
    22. 22)
    23. 23)
      • 52. Ramshur, J.: ‘Design, evaluation and application of heart rate variability software’, The University of Memphis, Memphis, (2010)..
    24. 24)
    25. 25)
    26. 26)
    27. 27)
      • 54. Melillo, P., Scala, P., Crispino, F., Pecchia, L.: ‘Cloud-based remote processing and data-mining platform for automatic risk assessment in hypertensive patients’, in Pecchia, L., Chen, L., Nugent, C., Bravo, J. (Eds.): ‘Ambient assisted living and daily activities’ (Springer, 2014).
    28. 28)
      • 49. Breiman, L.: ‘Classification and regression trees’ (Chapman & Hall, 1993).
    29. 29)
    30. 30)
      • 48. Melillo, P., Pecchia, L., Ursino, M.: ‘Nonlinear analysis research in biomedical engineering’, in Padovani, G., Occhino, M. (Eds.): ‘Focus on nonlinear analysis research’ (Nova Science Publishers, 2013).
    31. 31)
    32. 32)
    33. 33)
    34. 34)
      • 11. Rubenstein, L.Z.: ‘Falls in older people: epidemiology, risk factors and strategies for prevention’, Age Ageing, 2006, 35, (Suppl 2), pp. ii37ii41.
    35. 35)
    36. 36)
    37. 37)
    38. 38)
    39. 39)
    40. 40)
    41. 41)
      • 22. Jović, A., Brkić, K., Bogunović, N.: ‘Decision tree ensembles in biomedical time-series classification’, LNCS (Lecture Notes in Computer Science) (Springer, 2012).
    42. 42)
    43. 43)
      • 46. Webber, C.L., Zbilut, J.P.: ‘Dynamical assessment of physiological systems and states using recurrence plot strategies’, J. Appl. Physiol., 1994, 76, (2), pp. 965973.
    44. 44)
      • 50. Quinlan, J.R.: ‘C4.5: programs for machine learning’ (Morgan Kaufmann Publishers, 1993).
    45. 45)
    46. 46)
    47. 47)
    48. 48)
    49. 49)
    50. 50)
    51. 51)
    52. 52)
    53. 53)
    54. 54)
http://iet.metastore.ingenta.com/content/journals/10.1049/htl.2015.0012
Loading

Related content

content/journals/10.1049/htl.2015.0012
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading