Identifying who benefits most from Alzheimer’s and related dementia treatments across multiple outcomes
Statistical methods to characterize patients who highly benefit across multifaceted clinical outcomes, from treatments in Alzheimers Disease and Related Dementias (ADRD)
This project develops new statistical tools to find people with Alzheimer’s or related dementias who are likely to get substantial benefits from treatments across several important outcomes.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Johns Hopkins University NIH-funded |
| Lab location | 1 site (Baltimore, United States) |
| Project ID | NIH-11260240 on NIH RePORTER |
What this research studies
From the patient's perspective, researchers will build prediction models that combine a person’s health information, symptoms, and biomarkers to forecast how they will do on multiple outcomes after a treatment. The approach has two steps: first creating outcome predictions using methods like regression and neural networks from large sets of patient features, and then synthesizing those predictions to identify groups likely to have large overall benefit. The team aims to explicitly link the clinical goal of finding multi-outcome benefit into the model-building process, which existing methods do not do. Work will use existing clinical trial and observational datasets and computational experiments at Johns Hopkins to produce tools that could later help guide treatment choices or trial enrollment.
Who could benefit from this research
Good fit: Adults diagnosed with Alzheimer disease or related dementias, especially those with available clinical, cognitive, or biomarker data or who are considering participation in treatment studies, would be most relevant.
Not a fit: People without Alzheimer’s or related dementias, or those with very advanced illness or no available clinical data, are less likely to benefit directly from these methods.
Why it matters
Potential benefit: If successful, these tools could help clinicians and families pick treatments that give a particular patient meaningful improvements across cognition, behavior, and daily function while avoiding therapies that cause net harm.
How similar studies have performed: Previous methods that target single outcomes have shown promise in matching patients to treatments, but linking multiple clinical goals into a single characterization is largely new and has not yet been widely tested in patient datasets.
Where this research is happening
Baltimore, United States
- Johns Hopkins University — Baltimore, United States (Active)
Researchers
- Principal investigator: Frangakis, Constantine E — Johns Hopkins University
- Study coordinator: Frangakis, Constantine E
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.