Neurodegenerative diseases (NDD) such as Alzheimer's (AD) and Parkinson's (PD) are among the world’s most debilitating diseases, accompanied by devastating effects on the quality of life of patients and their loved ones. AD alone affects 45 million people worldwide, making neurodegenerative diseases a considerable public health problem (1). A recent study estimated that the global economic burden of AD and related dementias will reach $4.7 trillion by 2030 (2). With the significant healthcare and economic burden of neurodegenerative diseases, therapies to cure, or slow disease progression are in high demand. Unfortunately, decades of research and clinical trials for disease-modifying therapies have led to very few, often imperfect, options (1). This presents an urgent need to accelerate drug discovery and development.
Despite the tremendous resources spent on research, there are commonly recurring factors that contribute to the continued failure of clinical trials for neurodegenerative diseases. Finding and enrolling the right patients is one of the major challenges. Neurodegenerative diseases are complex disorders hard to identify and differentiate based on clinical symptoms alone. Alzheimer’s drug trials, in particular, suffer from inaccurate diagnoses, with approximately 15% of enrolled patients actually being false positives (3). Such misdiagnoses might encompass other forms of dementia and even conditions like depression and brain trauma. Relying solely on a clinical diagnosis for AD is not always conclusive and enrolling non-AD patients increases trial failure rates. Furthermore, eligibility criteria such as disease stage, age, and comorbidities often limit the pool of eligible participants. The intricacies of patient selection for such complex diseases make neurodegenerative disease trials particularly slow and expensive (1).
Besides accurate patient selection, frequent challenges within trials also include clinical outcome predictions and timing of therapeutic interventions. Clinical trial endpoints must be carefully chosen to ensure that they are the most appropriate and sensitive measurements for accurate treatment effectiveness in patients. The ADAS-Cog, a standard assessment for cognitive dysfunction in AD that was developed in the 1980s, has been used in AD trials for decades to determine patients’ treatment response levels (3). However, it was developed with what was known about the disease at the time and does not accurately measure patients in earlier stages of AD.
Moreover, the timing of therapeutical interventions is crucial. For instance, some therapies being developed for AD must be administered during the early stages of the disease, before extensive cognitive decline has occurred. This underscores the need for improved disease biomarkers, enabling the initiation of therapies at the right moment, often before pronounced cognitive decline occurs. Several ongoing studies are investigating novel biomarkers, with some utilizing digital health technologies (DHT) to detect deviations from the normal cognitive decline trajectory in the initial stages of the disease (4). These emerging biomarkers will play a pivotal role in defining meaningful endpoints, ensuring accurate assessments of treatment effectiveness (5).
To accelerate and de-risk clinical trials and drug development for neurodegenerative diseases researchers must focus on identifying novel biomarkers and their optimal contexts of use for each disease, these biomarkers can then be used as clinically relevant endpoints (6, 7). Integrating DHT alongside AI-driven analysis of the complex data generated by these technologies can lead to meaningful biomarkers and endpoints for clinical trials in neurodegenerative diseases (8).
AI can revolutionize patient recruitment and trial outcomes through its ability to analyze biomarkers efficiently. By leveraging various sources of real-world data, including large open research data sets or electronic health records, AI can help researchers identify potential patients more effectively. AI models developed on these data sources can predict disease progression or even how individuals might respond to certain interventions, supporting the identification of suitable candidates for therapy. This allows researchers to simulate different trial designs, optimizing treatment plans based on predicted success rates, resulting in cost and time savings (9).
In this new era of precision medicine, AICURA Medical is paving the way for innovation. By simplifying the data and AI journey, AICURA empowers healthcare professionals and biopharma to revolutionize patient screening, recruitment, and monitoring through multimodal, multipurpose, AI-based prediction models. These models prove to be very helpful in optimizing patient screening, which is especially important in the case of AD, where only one in three patients who undergo screening meet the eligibility criteria for clinical trials. Additionally, the models can help to identify relevant covariates that need to be adjusted. Choosing and adjusting the right covariates can reduce noise and increase the probability of success of clinical trials.
1. de Aquino CH., et al. Methodological Issues in Randomized Clinical Trials for Prodromal Alzheimer's and Parkinson's Disease. Front Neurol. 2021 Aug 6;12:694329. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8377160/
2. Nandi A., et al. Global and regional projections of the economic burden of Alzheimer's disease and related dementias from 2019 to 2050: A value of statistical life approach. The Lancet. 2022. https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(22)00310-8/fulltext
3. Kim CK., et al. Alzheimer's Disease: Key Insights from Two Decades of Clinical Trial Failures. J Alzheimers Dis. 2022. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9198803/
4. Kourtis LC., at al. Digital biomarkers for Alzheimer's disease: the mobile/ wearable devices opportunity. NPJ Digit Med. 2019. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6526279/
5. Osborne OM., et al. Anti-amyloid: An antibody to cure Alzheimer's or an attitude. iScience. 2023. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425904/
6. Subbiah, V. The next generation of evidence-based medicine. Nature Medicine. 2023. https://www.nature.com/articles/s41591-022-02160-z#citeas
7. Beach TG. A Review of Biomarkers for Neurodegenerative Disease: Will They Swing Us Across the Valley? Neurol Ther. 2017. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5520818/
8. Kourtis LC., et al. Digital biomarkers for Alzheimer's disease: the mobile/ wearable devices opportunity. NPJ Digit Med. 2019. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6526279/
9. Weissler EH., et al. The role of machine learning in clinical research: transforming the future of evidence generation. Trials 22. 2021. https://trialsjournal.biomedcentral.com/articles/10.1186/s13063-021-05489-x
