JPND: Early Detection of Alzheimer's Disease Subtypes

Lead Research Organisation: University College London
Department Name: Computer Science

Abstract

Alzheimer's disease (AD) is a global health and economic burden with currently about 47 million affected individuals worldwide. No provably disease-modifying treatments exist. Delaying disease onset in dementia patients by five years can reduce care costs by 36% about 88B euro per year across the EU. A key confound preventing successful outcomes in most treatment trials to date has been AD's high variation in onset, mechanism, and clinical expression. E-DADS aims to untangle this heterogeneity by defining data-driven subtypes of the clinical manifestation of AD based on brain imaging, cognitive markers, and fluid biomarkers that are robustly identifiable from predictive risk factors (genetics, co-morbidities, physiological and lifestyle factors) years before disease onset. To achieve this we develop a novel multi-view learning strategies that relates end-stage disease manifestations observable in clinical cohorts to features of early-stage or at-risk individuals in preclinical cohorts and the general pre-affected population from population or aging studies. This approach is only possible now due to the availability of large population data, richly phenotyped AD cohorts and advances in machine learning. E-DADS uniquely assembles the necessary data and expertise. The ability to identify AD subtypes and predict them years before onset will significantly advance AD research and clinical management via precision medicine. First, it identifies distinct homogeneous groups, shedding new light on that nature and variability of disease mechanisms ultimately pinpointing effective drug targets. Second, it enables enrichment of future clinical trials for specific groups of patients likely to benefit from a particular intervention. Third, it highlights potential lifestyle interventions that may affect or delay disease onset at very early stages. E-DADS delivers the underpinning technology to achieve this through machine learning and big-data analytics together with a prototype software tool enabling future translation and uptake.

Technical Summary

We develop a novel multi-view learning strategies that relates end-stage disease manifestations observable in clinical cohorts to features of early-stage or at-risk individuals in preclinical cohorts and the general pre-affected population from population or aging studies. This approach is only possible now due to the availability of large population data, richly phenotyped AD cohorts and advances in machine learning. E-DADS uniquely assembles the necessary data and expertise. The ability to identify AD subtypes and predict them years before onset will significantly advance AD research and clinical management via precision medicine. First, it identifies distinct homogeneous groups, shedding new light on that nature and variability of disease mechanisms ultimately pinpointing effective drug targets. Second, it enables enrichment of future clinical trials for specific groups of patients likely to benefit from a particular intervention. Third, it highlights potential lifestyle interventions that may affect or delay disease onset at very early stages. E-DADS delivers the underpinning technology to achieve this through machine learning and big-data analytics together with a prototype software tool enabling future translation and uptake.

Planned Impact

AD is a global health and economic burden with currently about 47 million affected individuals worldwide and annual care costs of around 880 billion euro. However, variability in onset, mechanism and clinical expression has been a key confound preventing successful outcomes in most treatment trials to date. Delaying disease onset in dementia patients by five years can reduce care costs by 36% saving about 88B euro per year across the EU. This may come from a combination of a) better understanding of disease aetiology helping avoid lifestyle/behaviour that puts individuals at risk and b) current intense activity on widely-varying treatment prospects. What is clear is that no single solution will suit all. Strong ability to stratify by disease trajectory will: a) identify lifestyle interventions for specific individuals that can reduce risk; b) enable treatments effective on small proportions of patients to come to market through enriched trials; c) identify patients most likely to benefit from particular interventions (once identified) or treatments (once available); d) enhance understanding of disease onset and mechanism expediting future additional treatments. Treatments for neurological conditions, e.g. those available for multiple sclerosis, typically market at around 50K euro per patient per year. Thus, a treatment effective for only 10% of AD patients could add 50B euro per year to the EU economy. Early clinical AD subtyping can thus underpin a revolution in care options for people at risk of developing AD and put Europe in a world-wide leading role in precision medicine in AD.

Publications

10 25 50