Using machine learning to improve treatment for patients with shortness of breath
Official title: SCH: Leveraging Clinical Time Series to Learn Optimal Treatment of Acute Dyspnea
Funded at University of Michigan at Ann Arbor · NIH-10458527 · Data updated 2026-11-12
This study is exploring a new way to help doctors treat patients who are having trouble breathing by using smart technology to find out which treatments work best for them in real-time.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | University of Michigan at Ann Arbor NIH-funded |
| Lab location | 1 site (Ann Arbor, United States) |
| Project start | September 10, 2019 |
| Project end | July 31, 2025 |
| Funding year | 2022 |
| Award (this year) | $228,618 |
| NIH project number | 5R01LM013325-04 |
| Project ID | NIH-10458527 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are patients hospitalized with acute dyspnea and signs of respiratory failure.
✕Less likely to help
Patients with chronic, stable respiratory conditions who do not experience acute episodes may not benefit from this research.
What this research studies
This research focuses on enhancing the treatment of patients experiencing acute dyspnea, or shortness of breath, by utilizing a novel machine learning approach known as reinforcement learning. Instead of merely diagnosing conditions, this method analyzes clinical time-series data from electronic health records to determine how different treatments affect patient outcomes. By simulating various treatment strategies, the framework aims to provide physicians with real-time insights into the most effective interventions for their patients. This approach is particularly beneficial for patients whose symptoms may arise from multiple overlapping conditions, making treatment decisions complex.
Why it matters
Potential benefit: If successful, this research could lead to more personalized and effective treatment strategies for patients suffering from acute dyspnea.
How similar studies have gone: Other research has shown promise in using machine learning approaches for treatment optimization, indicating potential success for this novel application.
Where this research is happening
-
University of Michigan at Ann Arbor
Ann Arbor, United States Active
Researchers
- Principal investigator: Wiens, Jenna — University of Michigan at Ann Arbor
- Study coordinator: Wiens, Jenna
Related research
Other NIH-funded projects on the same topics.
-
Patient-centered risk profiling to tailor breathlessness care
A study from UCLA aims to use AI to identify why a smoker experiences shortness of breath and tailor care to each person.
-
Understanding how the brain shapes breathing to help people with persistent breathlessness
Researchers are studying how higher brain regions influence breathing and the feeling of breathlessness in people with conditions like COPD and asthma, with the goal of safer, non-ventilation-impairing treatments.
-
Predicting and continuously monitoring breathlessness with noninvasive signals
A study to create a machine-learning tool that uses easy-to-measure body signals to predict when patients feel breathless, even if they can’t communicate.
-
Personalized oxygen and breathing support for cancer-related breathlessness
This trial compares a respiratory-therapist-led program that tailors oxygen and other breathing supports to help hospitalized patients with advanced cancer who are bothered by breathlessness.
-
How the brain creates ongoing breathlessness
Researchers are recording brain signals from people who already have implanted epilepsy electrodes to understand how higher brain regions produce ongoing breathlessness in conditions like COPD, asthma, heart or neuromuscular disease.
-
Brief behavioral support to help breathlessness in advanced lung cancer
A multi-site study tests a short behavioral program delivered by nurses to help adults with advanced lung cancer feel less breathless and more able to do daily activities.
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.