Gallacher, John

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

AbstractBackgroundLate‐onset Alzheimer's disease (AD) is heritable with 20 genes showing genome‐wide association in the International Genomics of Alzheimer's Project (IGAP). To identify the biology underlying the disease, we extended these genetic data in a pathway analysis.MethodsThe ALIGATOR and GSEA algorithms were used in the IGAP data to identify associated functional pathways and correlated gene expression networks in human brain.ResultsALIGATOR identified an excess of curated biological pathways showing enrichment of association. Enriched areas of biology included the immune response (P = 3.27 × 10−12 after multiple testing correction for pathways), regulation of endocytosis (P = 1.31 × 10−11), cholesterol transport (P = 2.96 × 10−9), and proteasome‐ubiquitin activity (P = 1.34 × 10−6). Correlated gene expression analysis identified four significant network modules, all related to the immune response (corrected P = .002–.05).ConclusionsThe immune response, regulation of endocytosis, cholesterol transport, and protein ubiquitination represent prime targets for AD therapeutics.