Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: the CADDementia challenge.

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimer's disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimer's Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Classification-Biased Apparent Brain Age for the Prediction of Alzheimer's Disease.

Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as "brain age". The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain age model as biomarker is the prediction of Alzheimer's disease (AD) from structural Magnetic Resonance Imaging (MRI). Many different machine learning approaches have been applied to this specific predictive task, some of which have achieved high accuracy at the expense of the descriptiveness of the model. This work investigates an appropriate combination of data science techniques and linear models to provide, at the same time, high accuracy and good descriptiveness. The proposed method is based on a data workflow that include typical data science methods, such as outliers detection, feature selection, linear regression, and logistic regression. In particular, a novel inductive bias is introduced in the regression model, which is aimed at improving the accuracy and the specificity of the classification task. The method is compared to other machine learning approaches for AD classification based on morphological brain data with and without the use of the brain age, including Support Vector Machines and Deep Neural Networks. This study adopts brain MRI scans of 1, 901 subjects which have been acquired from three repositories (ADNI, AIBL, and IXI). A predictive model based only on the proposed apparent brain age and the chronological age has an accuracy of 88% and 92%, respectively, for male and female subjects, in a repeated cross-validation analysis, thus achieving a comparable or superior performance than state of the art machine learning methods. The advantage of the proposed method is that it maintains the morphological semantics of the input space throughout the regression and classification tasks. The accurate predictive model is also highly descriptive and can be used to generate potentially useful insights on the predictions.

RAPIDSNPs: A new computational pipeline for rapidly identifying key genetic variants reveals previously unidentified SNPs that are significantly associated with individual platelet responses.

Advances in omics technologies have led to the discovery of genetic markers, or single nucleotide polymorphisms (SNPs), that are associated with particular diseases or complex traits. Although there have been significant improvements in the approaches used to analyse associations of SNPs with disease, further optimised and rapid techniques are needed to keep up with the rate of SNP discovery, which has exacerbated the 'missing heritability' problem. Here, we have devised a novel, integrated, heuristic-based, hybrid analytical computational pipeline, for rapidly detecting novel or key genetic variants that are associated with diseases or complex traits. Our pipeline is particularly useful in genetic association studies where the genotyped SNP data are highly dimensional, and the complex trait phenotype involved is continuous. In particular, the pipeline is more efficient for investigating small sets of genotyped SNPs defined in high dimensional spaces that may be associated with continuous phenotypes, rather than for the investigation of whole genome variants. The pipeline, which employs a consensus approach based on the random forest, was able to rapidly identify previously unseen key SNPs, that are significantly associated with the platelet response phenotype, which was used as our complex trait case study. Several of these SNPs, such as rs6141803 of COMMD7 and rs41316468 in PKT2B, have independently confirmed associations with cardiovascular diseases (CVDs) according to other unrelated studies, suggesting that our pipeline is robust in identifying key genetic variants. Our new pipeline provides an important step towards addressing the problem of 'missing heritability' through enhanced detection of key genetic variants (SNPs) that are associated with continuous complex traits/disease phenotypes.