Blog
About

  • Record: found
  • Abstract: found
  • Article: found
Is Open Access

Accurate multimodal probabilistic prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment☆

Read this article at

Bookmark
      There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

      Abstract

      Accurately identifying the patients that have mild cognitive impairment (MCI) who will go on to develop Alzheimer's disease (AD) will become essential as new treatments will require identification of AD patients at earlier stages in the disease process. Most previous work in this area has centred around the same automated techniques used to diagnose AD patients from healthy controls, by coupling high dimensional brain image data or other relevant biomarker data to modern machine learning techniques. Such studies can now distinguish between AD patients and controls as accurately as an experienced clinician. Models trained on patients with AD and control subjects can also distinguish between MCI patients that will convert to AD within a given timeframe (MCI-c) and those that remain stable (MCI-s), although differences between these groups are smaller and thus, the corresponding accuracy is lower. The most common type of classifier used in these studies is the support vector machine, which gives categorical class decisions. In this paper, we introduce Gaussian process (GP) classification to the problem. This fully Bayesian method produces naturally probabilistic predictions, which we show correlate well with the actual chances of converting to AD within 3 years in a population of 96 MCI-s and 47 MCI-c subjects. Furthermore, we show that GPs can integrate multimodal data (in this study volumetric MRI, FDG-PET, cerebrospinal fluid, and APOE genotype with the classification process through the use of a mixed kernel). The GP approach aids combination of different data sources by learning parameters automatically from training data via type-II maximum likelihood, which we compare to a more conventional method based on cross validation and an SVM classifier. When the resulting probabilities from the GP are dichotomised to produce a binary classification, the results for predicting MCI conversion based on the combination of all three types of data show a balanced accuracy of 74%. This is a substantially higher accuracy than could be obtained using any individual modality or using a multikernel SVM, and is competitive with the highest accuracy yet achieved for predicting conversion within three years on the widely used ADNI dataset.

      Highlights

      • Prediction of MCI to AD conversion using ADNI data and Gaussian processes.
      • 74% accuracy, 0.795 area under ROC curve for predicting conversion within 3 years.
      • Gaussian processes allow automatic parameter tuning including multimodal weights.
      • Statistically significant improvement for multimodal vs best unimodal prediction.
      • Probabilistic interpretation of results to better reflect continuum of disease.

      Related collections

      Most cited references 67

      • Record: found
      • Abstract: found
      • Article: not found

      Voxel-based morphometry--the methods.

      At its simplest, voxel-based morphometry (VBM) involves a voxel-wise comparison of the local concentration of gray matter between two groups of subjects. The procedure is relatively straightforward and involves spatially normalizing high-resolution images from all the subjects in the study into the same stereotactic space. This is followed by segmenting the gray matter from the spatially normalized images and smoothing the gray-matter segments. Voxel-wise parametric statistical tests which compare the smoothed gray-matter images from the two groups are performed. Corrections for multiple comparisons are made using the theory of Gaussian random fields. This paper describes the steps involved in VBM, with particular emphasis on segmenting gray matter from MR images with nonuniformity artifact. We provide evaluations of the assumptions that underpin the method, including the accuracy of the segmentation and the assumptions made about the statistical distribution of the data. Copyright 2000 Academic Press.
        Bookmark
        • Record: found
        • Abstract: found
        • Article: not found

        Global prevalence of dementia: a Delphi consensus study.

        100 years after the first description, Alzheimer's disease is one of the most disabling and burdensome health conditions worldwide. We used the Delphi consensus method to determine dementia prevalence for each world region. 12 international experts were provided with a systematic review of published studies on dementia and were asked to provide prevalence estimates for every WHO world region, for men and women combined, in 5-year age bands from 60 to 84 years, and for those aged 85 years and older. UN population estimates and projections were used to estimate numbers of people with dementia in 2001, 2020, and 2040. We estimated incidence rates from prevalence, remission, and mortality. Evidence from well-planned, representative epidemiological surveys is scarce in many regions. We estimate that 24.3 million people have dementia today, with 4.6 million new cases of dementia every year (one new case every 7 seconds). The number of people affected will double every 20 years to 81.1 million by 2040. Most people with dementia live in developing countries (60% in 2001, rising to 71% by 2040). Rates of increase are not uniform; numbers in developed countries are forecast to increase by 100% between 2001 and 2040, but by more than 300% in India, China, and their south Asian and western Pacific neighbours. We believe that the detailed estimates in this paper constitute the best currently available basis for policymaking, planning, and allocation of health and welfare resources.
          Bookmark
          • Record: found
          • Abstract: found
          • Article: not found

          Mild cognitive impairment: clinical characterization and outcome.

          Subjects with a mild cognitive impairment (MCI) have a memory impairment beyond that expected for age and education yet are not demented. These subjects are becoming the focus of many prediction studies and early intervention trials. To characterize clinically subjects with MCI cross-sectionally and longitudinally. A prospective, longitudinal inception cohort. General community clinic. A sample of 76 consecutively evaluated subjects with MCI were compared with 234 healthy control subjects and 106 patients with mild Alzheimer disease (AD), all from a community setting as part of the Mayo Clinic Alzheimer's Disease Center/Alzheimer's Disease Patient Registry, Rochester, Minn. The 3 groups of individuals were compared on demographic factors and measures of cognitive function including the Mini-Mental State Examination, Wechsler Adult Intelligence Scale-Revised, Wechsler Memory Scale-Revised, Dementia Rating Scale, Free and Cued Selective Reminding Test, and Auditory Verbal Learning Test. Clinical classifications of dementia and AD were determined according to the Diagnostic and Statistical Manual of Mental Disorders, Revised Third Edition and the National Institute of Neurological and Communicative Disorders and Stroke-Alzheimer's Disease and Related Disorders Association criteria, respectively. The primary distinction between control subjects and subjects with MCI was in the area of memory, while other cognitive functions were comparable. However, when the subjects with MCI were compared with the patients with very mild AD, memory performance was similar, but patients with AD were more impaired in other cognitive domains as well. Longitudinal performance demonstrated that the subjects with MCI declined at a rate greater than that of the controls but less rapidly than the patients with mild AD. Patients who meet the criteria for MCI can be differentiated from healthy control subjects and those with very mild AD. They appear to constitute a clinical entity that can be characterized for treatment interventions.
            Bookmark

            Author and article information

            Affiliations
            [a ]Centre for Medical Image Computing, University College London, UK
            [b ]Dementia Research Centre, Institute of Neurology, University College London, UK
            Author notes
            [* ]Corresponding author at: UCL Department of Medical Physics and Bioengineering — Centre for Medical Image Computing, Gower Street, London, WC1E 6BT, UK. Tel.: + 44 2076790485; fax: + 44 2076790255. jonathan.young@ 123456ucl.ac.uk
            [1]

            Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.ucla.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.ucla.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf.

            Contributors
            Journal
            Neuroimage (Amst)
            Neuroimage (Amst)
            NeuroImage : Clinical
            Elsevier
            2213-1582
            19 May 2013
            19 May 2013
            2013
            : 2
            : 735-745
            24179825 3777690 S2213-1582(13)00060-0 10.1016/j.nicl.2013.05.004
            © 2013 The Authors

            This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial-No Derivative Works License, which permits non-commercial use, distribution, and reproduction in any medium, provided the original author and source are credited.

            Categories
            Article

            Comments

            Comment on this article