Usefulness of Bayesian graphical models for early prediction of disease progression in multiple sclerosis

R. Bergamaschi, A. Romani, S. Tonietti, A. Citterio, C. Berzuini, V. Cosi

Research output: Contribution to journalArticle

Abstract

Previous studies of possible prognostic indicators for multiple sclerosis have been based on "classic" Cox's proportional hazards regression model, as well as on equivalent or simpler approaches, restricting their attention to variables measured either at disease onset or at a few points during follow-up. The aim of our study was to analyse the risk of reaching secondary progression in MS patients with a relapsing-remitting initial course, using two different statistical approaches: a Cox's proportional-hazards model and a Bayesian latent-variable model with Markov chain Monte Carlo methods of computation. In comparison with a standard statistical approach, our model is advantageous because, exploiting all the information gleaned from the patient as it is gradually made available, it is capable to detect even small prognostic effects.

Original languageEnglish
JournalNeurological Sciences
Volume21
Issue number8
Publication statusPublished - 2000

Fingerprint

Proportional Hazards Models
Multiple Sclerosis
Disease Progression
Monte Carlo Method
Markov Chains

Keywords

  • Bayesian approach
  • Markov chain Monte Carlo method
  • Multiple sclerosis
  • Prognostic factors
  • Secondary progressive course

ASJC Scopus subject areas

  • Clinical Neurology
  • Neuroscience(all)
  • Psychiatry and Mental health
  • Dermatology

Cite this

Usefulness of Bayesian graphical models for early prediction of disease progression in multiple sclerosis. / Bergamaschi, R.; Romani, A.; Tonietti, S.; Citterio, A.; Berzuini, C.; Cosi, V.

In: Neurological Sciences, Vol. 21, No. 8, 2000.

Research output: Contribution to journalArticle

Bergamaschi, R. ; Romani, A. ; Tonietti, S. ; Citterio, A. ; Berzuini, C. ; Cosi, V. / Usefulness of Bayesian graphical models for early prediction of disease progression in multiple sclerosis. In: Neurological Sciences. 2000 ; Vol. 21, No. 8.
@article{b1b808a2a9464db3a25021fd24c08800,
title = "Usefulness of Bayesian graphical models for early prediction of disease progression in multiple sclerosis",
abstract = "Previous studies of possible prognostic indicators for multiple sclerosis have been based on {"}classic{"} Cox's proportional hazards regression model, as well as on equivalent or simpler approaches, restricting their attention to variables measured either at disease onset or at a few points during follow-up. The aim of our study was to analyse the risk of reaching secondary progression in MS patients with a relapsing-remitting initial course, using two different statistical approaches: a Cox's proportional-hazards model and a Bayesian latent-variable model with Markov chain Monte Carlo methods of computation. In comparison with a standard statistical approach, our model is advantageous because, exploiting all the information gleaned from the patient as it is gradually made available, it is capable to detect even small prognostic effects.",
keywords = "Bayesian approach, Markov chain Monte Carlo method, Multiple sclerosis, Prognostic factors, Secondary progressive course",
author = "R. Bergamaschi and A. Romani and S. Tonietti and A. Citterio and C. Berzuini and V. Cosi",
year = "2000",
language = "English",
volume = "21",
journal = "Neurological Sciences",
issn = "1590-1874",
publisher = "Springer-Verlag Italia s.r.l.",
number = "8",

}

TY - JOUR

T1 - Usefulness of Bayesian graphical models for early prediction of disease progression in multiple sclerosis

AU - Bergamaschi, R.

AU - Romani, A.

AU - Tonietti, S.

AU - Citterio, A.

AU - Berzuini, C.

AU - Cosi, V.

PY - 2000

Y1 - 2000

N2 - Previous studies of possible prognostic indicators for multiple sclerosis have been based on "classic" Cox's proportional hazards regression model, as well as on equivalent or simpler approaches, restricting their attention to variables measured either at disease onset or at a few points during follow-up. The aim of our study was to analyse the risk of reaching secondary progression in MS patients with a relapsing-remitting initial course, using two different statistical approaches: a Cox's proportional-hazards model and a Bayesian latent-variable model with Markov chain Monte Carlo methods of computation. In comparison with a standard statistical approach, our model is advantageous because, exploiting all the information gleaned from the patient as it is gradually made available, it is capable to detect even small prognostic effects.

AB - Previous studies of possible prognostic indicators for multiple sclerosis have been based on "classic" Cox's proportional hazards regression model, as well as on equivalent or simpler approaches, restricting their attention to variables measured either at disease onset or at a few points during follow-up. The aim of our study was to analyse the risk of reaching secondary progression in MS patients with a relapsing-remitting initial course, using two different statistical approaches: a Cox's proportional-hazards model and a Bayesian latent-variable model with Markov chain Monte Carlo methods of computation. In comparison with a standard statistical approach, our model is advantageous because, exploiting all the information gleaned from the patient as it is gradually made available, it is capable to detect even small prognostic effects.

KW - Bayesian approach

KW - Markov chain Monte Carlo method

KW - Multiple sclerosis

KW - Prognostic factors

KW - Secondary progressive course

UR - http://www.scopus.com/inward/record.url?scp=0034564732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034564732&partnerID=8YFLogxK

M3 - Article

C2 - 11205356

AN - SCOPUS:0034564732

VL - 21

JO - Neurological Sciences

JF - Neurological Sciences

SN - 1590-1874

IS - 8

ER -