Probabilistic prediction of neurological disorders with a statistical assessment of neuroimaging data modalities

TY - JOUR

T1 - Probabilistic prediction of neurological disorders with a statistical assessment of neuroimaging data modalities

AU - Filippone, M.

AU - Marquand, Andre

AU - Blain, C. R. V.

AU - Williams, S. C. R.

AU - Mourao-Miranda, J.

AU - Girolami, M.

PY - 2012/12

Y1 - 2012/12

N2 - For many neurological disorders, prediction of disease state is an important clinical aim. Neuroimaging provides detailed information about brain structure and function from which such predictions may be statistically derived. A multinomial logit model with Gaussian process priors is proposed to: (i) predict disease state based on whole-brain neuroimaging data and (ii) analyze the relative informativeness of different image modalities and brain regions. Advanced Markov chain Monte Carlo methods are employed to perform posterior inference over the model. This paper reports a statistical assessment of multiple neuroimaging modalities applied to the discrimination of three Parkinsonian neurological disorders from one another and healthy controls, showing promising predictive performance of disease states when compared to nonprobabilistic classifiers based on multiple modalities. The statistical analysis also quantifies the relative importance of different neuroimaging measures and brain regions in discriminating between these diseases and suggests that for prediction there is little benefit in acquiring multiple neuroimaging sequences. Finally, the predictive capability of different brain regions is found to be in accordance with the regional pathology of the diseases as reported in the clinical literature.

AB - For many neurological disorders, prediction of disease state is an important clinical aim. Neuroimaging provides detailed information about brain structure and function from which such predictions may be statistically derived. A multinomial logit model with Gaussian process priors is proposed to: (i) predict disease state based on whole-brain neuroimaging data and (ii) analyze the relative informativeness of different image modalities and brain regions. Advanced Markov chain Monte Carlo methods are employed to perform posterior inference over the model. This paper reports a statistical assessment of multiple neuroimaging modalities applied to the discrimination of three Parkinsonian neurological disorders from one another and healthy controls, showing promising predictive performance of disease states when compared to nonprobabilistic classifiers based on multiple modalities. The statistical analysis also quantifies the relative importance of different neuroimaging measures and brain regions in discriminating between these diseases and suggests that for prediction there is little benefit in acquiring multiple neuroimaging sequences. Finally, the predictive capability of different brain regions is found to be in accordance with the regional pathology of the diseases as reported in the clinical literature.

KW - CRITERIA

KW - high-dimensional data

KW - Gaussian process

KW - HIERARCHICAL-MODELS

KW - Multi-modality multinomial logit model

KW - CLASSIFICATION

KW - DIFFUSION-TENSOR MRI

KW - Parkinsonian diseases

KW - hierarchical model

KW - Markov chain Monte Carlo

KW - prediction of disease state

U2 - 10.1214/12-AOAS562

DO - 10.1214/12-AOAS562

M3 - Article

VL - 6

SP - 1883

EP - 1905

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

IS - 4

ER -