An Oblique Approach to Prediction of Conversion to Alzheimer's Disease with Multikernel Gaussian Processes

  title={An Oblique Approach to Prediction of Conversion to Alzheimer's Disease with Multikernel Gaussian Processes},
  author={Jonathan Young and Marc Modat and Manuel Jorge Cardoso and John Ashburner and S{\'e}bastien Ourselin},
Machine learning approaches have had some success in predicting conversion to Alzheimer’s Disease (AD) in subjects with mild cognitive impairment (MCI), a less serious condition that nonetheless is a risk factor for AD. Predicting conversion is clinically important as because novel drugs currently being developed require administration early in the disease process to be effective. Traditionally training data are labelled with discrete disease states; which may explain the limited accuracies… 

Probabilistic prediction of Alzheimer's disease from multimodal image data with Gaussian processes

The task of early diagnosis is tackled by borrowing modern machine learning techniques, and applying them to image data, and using Gaussian processes, a previously neglected tool, and showing they can be used in place of the more widely used support vector machine (SVM).

Multikernel Gaussian Processes for patient stratification from imaging biomarkers with heterogeneous patterns

This paper focuses on the development of a novel framework based on Gaussian Process (GP) to stratify subjects with the inherited human form of Prion disease, which tackles the small number of training data as well as the presence of heterogeneity among subjects’ biomarkers.

Learning from multimodal data for classification and prediction of Alzheimer's disease. (Apprentissage à partir de données multimodales pour la classification et la prédiction de la maladie d'Alzheimer)

Assessment of the potential and to integrate multiple modalities using machine learning methods, in order to automatically classify patients with AD and predict the development of the disease from the earliest stages and the added value of neuroimaging over clinical/cognitive data only.

Predicting the Progression of Mild Cognitive Impairment Using Machine Learning: A Systematic, Quantitative and Critical Review

A systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalographic variables significantly improved predictive performance, whereas including other modalities did not show a significant effect.

Multiple Kernel Learning and Automatic Subspace Relevance Determination for High-dimensional Neuroimaging Data

The research results demonstrate that the Gaussian Process models are competitive with or better than the well-known Support Vector Machine in terms of classification performance even in the cases of single kernel learning.

Design of data driven decision support systems for the early detection of subjects at risk to develop Alzheimer's disease. (Création de systèmes d'aide à la décision pour la détection précoce de sujets à risque de développer la maladie d'Alzheimer)

Nous les utilisons pour predire si un patient va developper la maladie d'Alzheimer dans les 5 ou 10 annees a venir, notamment a travers la cohorte d’etude, les types of donnees, and l’interpretabilite of the methode.



BrainAGE in Mild Cognitive Impaired Patients: Predicting the Conversion to Alzheimer’s Disease

A novel magnetic resonance imaging (MRI)-based biomarker that predicts the individual progression of mild cognitive impairment to AD on the basis of pathological brain aging patterns is presented and can be exploited as a tool for screening as well as for monitoring treatment options.

An MRI-Derived Definition of MCI-to-AD Conversion for Long-Term, Automatic Prognosis of MCI Patients

This work proposes an innovative definition, wherein an MCI is a converter if any of the patient's brain scans are classified “AD” by a Control-AD classifier, and predicts whether an AD-Control classifier will predict that a patient has AD.

Accuracy of the Clinical Diagnosis of Alzheimer Disease at National Institute on Aging Alzheimer Disease Centers, 2005–2010

To determine the accuracy of currently used clinical diagnostic methods, clinical and neuropathologic data from the National Alzheimer’s Coordinating Center, which gathers information from the network of National Institute on Aging (NIA)-sponsored Alzheimer Disease Centers (ADCs), were collected between 2005 and 2010.

Mild cognitive impairment: clinical characterization and outcome.

Patients who meet the criteria for MCI can be differentiated from healthy control subjects and those with very mild AD, and appear to constitute a clinical entity that can be characterized for treatment interventions.

Staging of alzheimer's disease-related neurofibrillary changes

Engineered antibody approaches for Alzheimer's disease immunotherapy.