A precision medicine approach for the diagnosis and prognosis of preclinical Alzheimer´s disease with implications for clinical trials

Alzheimer’s disease (AD) has a major impact on patients and societies, with at least 50 million persons affected.

There is currently no disease modifying treatment, which can be attributed to important knowledge gaps and suboptimal design of clinical trials.

To accelerate development of new treatments, we need algorithms for personalized diagnosis and prognosis, based on non-invasive, and time- and cost-effective tests like blood-based biomarkers and digital cognitive tests.

Such algorithms would optimize the screening procedure by accurately identifying individuals with AD in pre-symptomatic stages and predict progression rates at an individual level.

Longitudinal data from easily accessible biomarkers may also be used as outcome measures in trials, to improve power and shorten trial duration compared to standard cognitive or clinical measures. I will leverage data from cohorts that are deeply phenotyped and have long-term follow-up data available.

Using state-of-the-art machine learning approaches, I will define, validate and implement accessible and cost-effective AD biomarkers for personalized diagnostic and prognostic work-up to facilitate development of disease modifying treatments in AD.

By revolutionizing the participant selection and monitoring procedures for clinical trials, the personalized medicine approach developed in this project will meet important unmet medical needs, and facilitate development of effective treatment and prevention of AD.