Predicting medication use in heart failure
Official title: Generalizable prediction of medication adherence in heart failure
Funded at New York University School of Medicine · NIH-11061379 · Data updated 2026-11-12
This project will use electronic health records and pharmacy refill data to build a computer model that predicts whether people with heart failure are likely to miss their medications.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | New York University School of Medicine NIH-funded |
| Lab location | 1 site (New York, United States) |
| Project start | March 15, 2021 |
| Project end | February 28, 2027 |
| Funding year | 2025 |
| Award (this year) | $751,005 |
| NIH project number | 5R01HL155149-05 |
| Project ID | NIH-11061379 on NIH RePORTER |
Who could benefit from this research
✓Could help
People diagnosed with heart failure who have medical records and linked pharmacy refill data in participating health systems would be the ideal candidates for this work.
✕Less likely to help
Patients without electronic records or linked pharmacy data, or whose care is entirely outside participating systems, are unlikely to be included or directly helped by this project.
What this research studies
Researchers will combine patients' electronic health record and linked pharmacy fill data to train machine learning models that recognize patterns tied to not taking medicines. The models will incorporate many patient-, provider-, and system-level factors and will be updated as new data arrive. Teams will test the models across large healthcare datasets and work to make the predictions accurate and fair across different hospitals. If reliable, these predictions could be shown to clinicians at the point of care to trigger timely support for patients.
Why it matters
Potential benefit: If successful, the tool could help clinicians spot patients at risk of not taking heart failure medicines so they can offer help sooner and potentially reduce hospital visits.
How similar studies have gone: Related machine-learning approaches using EHR and pharmacy data have shown promising results in other conditions, but this method is relatively new for predicting adherence in heart failure and needs validation.
Where this research is happening
-
New York University School of Medicine
New York, United States Active
Researchers
- Principal investigator: Blecker, Saul B. — New York University School of Medicine
- Study coordinator: Blecker, Saul B.
Related research
Other NIH-funded projects on the same topics.
-
Helping heart failure patients take their medications with family support and clear information
This project helps patients with heart failure and their family members work together to make sure medications are taken correctly, aiming to improve health and prevent hospital stays.
-
Improving how heart failure patients take their medications with family support and easy-to-understand strategies
This study is all about helping heart failure patients take their medications correctly by involving their families and using easy-to-understand methods, like fun sessions with nurses that include coaching and role-playing, to make sure everyone is on the same page and feels supported.
-
Helping older adults with heart failure stick to their medication plans.
This study is looking to help older adults with heart failure stick to their medication by connecting it to what really matters to them in life, making it feel more meaningful and motivating.
-
Helping older adults with heart failure stick to their medication during rehabilitation
This study is looking for ways to help older adults with heart failure stick to their medication while they go through cardiac rehab by helping them connect their medicine to what matters most to them in life.
-
AI-supported heart failure diagnosis and management in Rwanda
Aiming to help people with suspected heart failure in Rwanda get faster, more accurate diagnoses and better care using AI-guided ultrasound and care protocols.
-
AI-assisted heart failure diagnosis in Rwanda using focused ultrasound
An NIH-funded project will test whether AI-enhanced, easy-to-use heart ultrasound can help non-experts diagnose and manage heart failure in Rwanda.
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.