Oxtoby, Neil P.

Abstract Recent clinical trials on slowing dementia progression have led to renewed focus on finding safer, more effective treatments. One approach to identify plausible candidates is to assess whether existing medications for other conditions may affect dementia risk. We conducted a systematic review to identify studies adopting a data‐driven approach to investigate the association between a wide range of prescribed medications and dementia risk. We included 14 studies using administrative or medical records data for more than 130 million individuals and 1 million dementia cases. Despite inconsistencies in identifying specific drugs that may modify Alzheimer's or dementia risk, some themes emerged for drug classes with biological plausibility. Antimicrobials, vaccinations, and anti‐inflammatories were associated with reduced risk, while diabetes drugs, vitamins and supplements, and antipsychotics were associated with increased risk. We found conflicting evidence for antihypertensives and antidepressants. Drug repurposing for use in dementia is an urgent priority. Our findings offer a basis for prioritizing candidates and exploring underlying mechanisms. Highlights We present a systematic review of studies reporting association between drugs prescribed for other conditions and risk of dementia including 139 million people and 1 million cases of dementia. Our work supports some previously reported associations, for example, showing decreased risk of dementia with drugs to treat inflammatory disease and increased risk with antipsychotic treatment. Antimicrobial treatment was perhaps more surprisingly associated with decreased risk, supportive of recent increased interest in this potential therapeutic avenue. Our work should help prioritize drugs for entry into adaptive platform trials in Alzheimer's disease and will serve as a useful resource for those investigating drugs or classes of drugs and risk of dementia.

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.