Journal of Neural Transmission

, Volume 119, Issue 7, pp 821–831

Monte Carlo feature selection and rule-based models to predict Alzheimer’s disease in mild cognitive impairment

Dementias - Original Article

DOI: 10.1007/s00702-012-0812-0

Cite this article as:
Kruczyk, M., Zetterberg, H., Hansson, O. et al. J Neural Transm (2012) 119: 821. doi:10.1007/s00702-012-0812-0


The objective of the present study was to evaluate a Monte Carlo feature selection (MCFS) and rough set Rosetta pipeline for generating rule-based models as a tool for comprehensive risk estimates for future Alzheimer’s disease (AD) in individual patients with mild cognitive impairment (MCI). Risk estimates were generated on the basis of age, gender, Mini-Mental State Examination scores, apolipoprotein E (APOE) genotype and the cerebrospinal fluid (CSF) biomarkers total tau (T-tau), phospho-tau181 (P-tau) and the 42 amino acid form of amyloid β (Aβ42) in two sets of longitudinally followed MCI patients (n = 217 in total). The predictive model was created in Rosetta, evaluated with the standard tenfold cross-validation approach and tested on an external set. Features were ranked and selected by the MCFS algorithm. Using the combined pipeline of MCFS and Rosetta, it was possible to predict AD among patients with MCI with an area under the receiver operating characteristics curve of 0.92. Risk estimates were produced for the individual patients and showed good correlation with actual diagnosis in cross validation, and on an external dataset from a new study. Analysis of the importance of attributes showed that the biochemical CSF markers contributed the most to the predictions, and that added value was gained by combining several biochemical markers. Despite a correlation with the biochemical markers, the genetic marker APOE ε4 did not contribute to the predictive power of the model.


Alzheimer’s disease Decision support Monte Carlo feature selection Rosetta Rough sets Biomarkers Cerebrospinal fluid 

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Marcin Kruczyk
    • 1
    • 2
    • 3
  • Henrik Zetterberg
    • 4
    • 5
  • Oskar Hansson
    • 6
    • 7
  • Sindre Rolstad
    • 4
  • Lennart Minthon
    • 6
    • 7
  • Anders Wallin
    • 4
  • Kaj Blennow
    • 4
  • Jan Komorowski
    • 2
    • 3
  • Mats Gunnar Andersson
    • 8
  1. 1.Postgraduate School for Molecular MedicineWarsawPoland
  2. 2.Department of Cell and Molecular Biology, The Linnaeus Centre for BioinformaticsUppsala UniversityUppsalaSweden
  3. 3.Interdisciplinary Centre for Mathematical and Computational ModellingWarsaw UniversityWarsawPoland
  4. 4.Department of Psychiatry and Neurochemistry, Institute of Neuroscience and PhysiologyThe Sahlgrenska Academy at the University of GothenburgMölndalSweden
  5. 5.UCL Institute of NeurologyLondonUK
  6. 6.Clinical Memory Research Unit, Department of Clinical SciencesLund UniversityMalmöSweden
  7. 7.The Neuropsychiatric ClinicMalmö University HospitalMalmöSweden
  8. 8.Department of Chemistry, Environment and Feed HygieneNational Veterinary Institute (SVA)UppsalaSweden

Personalised recommendations