Credal Classification for Dementia Screening

  • Marco Zaffalon
  • Keith Wesnes
  • Orlando Petrini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2101)


Dementia is a very serious personal, medical and social problem. Early and accurate diagnoses seem to be the key to effectively cope with it. This paper presents a diagnostic tool that couples the most widely used computerized system of cognitive tests in dementia research, the Cognitive Drug Research system, with the naive credal classifier. Although the classifier is trained on an incomplete database, it provides unmatched predictive performance and reliability. The tool also proves to be very effective in discriminating between Alzheimer’s disease and dementia with Lewy bodies, which is a problem on the frontier of research on dementia.


Lewy Body Dementia With Lewy Body Vascular Dementia Choice Reaction Time Imprecise Probability 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    H. Allain, E. Neuman, M. Malbezin, V. Salzman, Guez D., K. Wesnes, and J. M. Gandon. Bridging study of S12024 in 53 in-patients with Alzheimer’s disease. J. Am. Geriatr. Soc., 45:125–126, 1997.Google Scholar
  2. 2.
    G. A. Ayre, A. Sahgal, I. G. McKeith, C. G. Ballard, K. Lowery, C. Pincock, M. P. Walker, and K. Wesnes. Distinct profiles of neuropsychological impairment in dementia with Lewy bodies and Alzheimer’s disease. Neurology. In press.Google Scholar
  3. 3.
    F. G. Cozman. Credal networks. Artificial Intelligence, 120:199–233, 2000.zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    P. Domingos. Machine learning. In W. Klosgen and J. Zytkow, editors, Handbook of data mining and knowledge discovery. Oxford University Press, New York. To appear.Google Scholar
  5. 5.
    P. Domingos and M. Pazzani. On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning, 29(2/3):103–130, 1997.zbMATHCrossRefGoogle Scholar
  6. 6.
    R. O. Duda and P. E. Hart. Pattern classification and scene analysis. Wiley, New York, 1973.zbMATHGoogle Scholar
  7. 7.
    R. O. Duda, P. E. Hart, and D. G. Stork. Pattern classification. Wiley, 2001. 2nd edition.Google Scholar
  8. 8.
    E. Fagiuoli and M. Zaffalon. 2U: an exact interval propagation algorithm for polytrees with binary variables. Artificial Intelligence, 106(1):77–107, 1998.zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    T. D. Fakouhi, Jhee S. S., J. J. Sramek, C. Benes, P. Schwartz, G. Hantsburger, R. Herting, E. A. Swabb, and N. R. Cutler. Evaluation of cycloserine in the treatment of Alzheimer’s disease. J. Geriatr. Psychiatry Neurol., 8:226–230, 1995.Google Scholar
  10. 10.
    S. Ferris, U. Lucca, R. Mohs, B. Dubois, K. Wesnes, H. Erzigkeit, D. Geldmacher, and N. Bodick. Objective psychometric tests in clinical trials of dementia drugs. Alzheimer Disease and Associated Disorders, 11(3):34–38, 1997. Position paper from the InternationalWorking Group on Harmonisation of Dementia Drug Guidelines.Google Scholar
  11. 11.
    R. Kohavi, G. John, R. Long, D. Manley, and K. Pfleger. MLC++: a machine learning library in C++. In Tools with Artificial Intelligence, pages 740–743. IEEE Computer Society Press, 1994.Google Scholar
  12. 12.
    S. Mani, M. B. Dick, M. J. Pazzani, E. L. Teng, D. Kempler, and I. M. Taussig. Refinement of neuro-psychological tests for dementia screening in a cross cultural population using machine learning. In W. Horn, Y. Shahar, G. Lindberg, S. Andreassen, and J. Wyatt, editors, Lecture Notes in Computer Science, volume 1620, pages 326–335. Springer, 1999. Proc. of the Joint European Conference on Artificial Intelligence in Medicine and Medical Decision Making, AIMDM’99, Aalborg, Denmark.Google Scholar
  13. 13.
    I. McKeith, T. Del Ser, F. Spano, K. Wesnes, R. Anand, A. Cicin-Sain, R. Ferrera, and R. Spiegel. Efficacy of rivastigmine in dementia with Lewy bodies: results of a randomised placebo-controlled international study. Lancet, 356:2031–2036, 2000.CrossRefGoogle Scholar
  14. 14.
    I. G. McKeith and G. A. Ayre. Consensus criteria for the clinical diagnosis of dementia with Lewy bodies. In K. Iqbal, B. Winblad, T. Nishimura, M. Takeda, and H. M. Wisnieswski, editors, Alzheimer’s Disease: Biology, Diagnosis and Therapeutics, pages 167–178. Wiley, 1997.Google Scholar
  15. 15.
    E. Mohr, V. Knott, M. Sampson, K. Wesnes, R. Herting, and T. Mendis. Cognitive and quantified electroencephalographic correlates of cycloserine treatment in Alzheimer’s disease. Clinical Neuropsychopharmacology, 18:23–38, 1995.CrossRefGoogle Scholar
  16. 16.
    E. Mohr, D. Walker, C. Randolph, M. Sampson, and T. Mendis. The utility of clinical trial batteries in the measurement of Alzheimer’s and Huntington’s dementia. International Psychogeriatrics, 3:397–411, 1996.CrossRefGoogle Scholar
  17. 17.
    C. G. Nicholl, S. Lynch, C. A. Kelly, L. White, L. Simpson, P. M. Simpson, K. Wesnes, and B. M. N. Pitt. The cognitive drug research computerised assessment system in the evaluation of early dementia — is speed of the essence? International Journal of Geriatric Psychiatry, 10:199–206, 1995.CrossRefGoogle Scholar
  18. 18.
    M. Ramoni and P. Sebastiani. Robust Bayes classifiers. Artificial Intelligence, 125(1-2):209–226, 2001.zbMATHCrossRefMathSciNetGoogle Scholar
  19. 19.
    K. R. Siegfried. Pharmacodynamic and early clinical studies with velnacrine. Acta Neurol. Scand., 149(10):26–28, 1993.Google Scholar
  20. 20.
    P. M. Simpson, D. J. Surmon, K. A. Wesnes, and G. R. Wilcock. The cognitive drug research computerised assessment system for demented patients: a validation study. International Journal of Geriatric Psychiatry, 6:95–102, 1991.CrossRefGoogle Scholar
  21. 21.
    L. Templeton, A. Barker, K. Wesnes, and D. Wilkinson. A double-blind, placebo-controlled trial of intravenous flumazenil in Alzheimer’s disease. Human Psychopharmacology, 14:239–245, 1999.CrossRefGoogle Scholar
  22. 22.
    M. P. Walker, G. A. Ayre, C. H. Ashton, V. R. Marsh, K. Wesnes, E. K. Perry, J. T. O’Brien, I. G. McKeith, and C. G. Ballard. A psychophysiological investigation of fluctuating consciousness in neurodegenerative dementias. Human Psychopharmacology, 14:483–489, 1999.CrossRefGoogle Scholar
  23. 23.
    M. P. Walker, G. A. Ayre, J. L. Cummings, K. Wesnes, I. G. McKeith, J. T. O’Brien, and C. G. Ballard. Quantifying fluctuation in dementia with Lewy bodies, Alzheimer’s disease and vascular dementia. Neurology, 54:1616–1625, 2000.Google Scholar
  24. 24.
    M. P. Walker, G. A. Ayre, J. L. Cummings, K. Wesnes, I. G. McKeith, J. T. O’Brien, and C. G. Ballard. The clinician assessment of fluctuation and the one day fluctuation assessment scale. British Journal of Psychiatry, 177:252–256, 2000.CrossRefGoogle Scholar
  25. 25.
    M. P. Walker, G. A. Ayre, E. K. Perry, K. Wesnes, I. G. McKeith, M. Tovee, J. A. Edwardson, and C. G. Ballard. Quantification and characterisation of fluctuating cognition in dementia with Lewy bodies and Alzheimer’s disease. Dementia and Geriatric Cognitive Disorders, 11:327–335, 2000.CrossRefGoogle Scholar
  26. 26.
    P. Walley. Statistical Reasoning with Imprecise Probabilities. Chapman and Hall, New York, 1991.zbMATHGoogle Scholar
  27. 27.
    K. Wesnes. Predicting, assessing, differentiating and treating the dementias: experience in MCI and various dementias using the CDR computerised cognitive assessment system. In B. Vellas and L. J. Fitten, editors, Research and practice in Alzheimer’s disease, volume 3, pages 59–65. Serdi, Paris, 2000.Google Scholar
  28. 28.
    K. Wesnes, K. Hildebrand, and E. Mohr. Computerised cognitive assessment. In G. W. Wilcock, R. S. Bucks, and K. Rocked, editors, Diagnosis and management of dementia: a manual for memory disorders teams, pages 124–136. Oxford Univ. Press, Oxford, 1999.Google Scholar
  29. 29.
    M. Zaffalon. Exact credal treatment of missing data. Journal of Statistical Planning and Inference. To appear.Google Scholar
  30. 30.
    M. Zaffalon. The naive credal classifier. Journal of Statistical Planning and Inference. To appear.Google Scholar
  31. 31.
    M. Zaffalon. Statistical inference of the naive credal classifier. In G. de Cooman, F. Cozman, T. Fine, and S. Moral, editors, ISIPTA’01, Univ. of Gent, Belgium, 2001. The Imprecise Probabilities Project. Accepted for publication.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Marco Zaffalon
    • 1
  • Keith Wesnes
    • 2
  • Orlando Petrini
    • 3
  1. 1.IDSIAMannoSwitzerland
  2. 2.Cognitive Drug Research Ltd.ReadingUK
  3. 3.BioggioSwitzerland

Personalised recommendations