Michael Sjoding
University of Michigan, MI·Medicine & Clinical Research
Shortness of breath, called acute dyspnea, is one of the most common reasons people come to emergency departments and are admitted to hospitals. Its usual causes, heart failure, pneumonia and chronic obstructive pulmonary disease (COPD), need different treatments.
- Fields
Medicine & Clinical Research
Computer Science
Biomedical Engineering
- Topics
artificial intelligence
machine learning
computer vision
- Grants
- 1 known grant, last ended Aug 2026
What they work on
- Evaluate computational strategies that make an AI tool for diagnosing acute dyspnea (shortness of breath) more robust and less biased when analyzing clinical and imaging data from different patients.
- Test strategies that improve how clinicians and AI tools collaborate, so that AI support raises rather than lowers diagnostic accuracy for causes such as heart failure, pneumonia and COPD.
- Prospectively evaluate the acute dyspnea AI tool in a clinical environment while testing ways to gather clinician feedback that supports ongoing model improvement.
More about the research
Yet symptoms, lab tests and imaging can be hard to read, especially in older or very sick patients, and the wrong diagnosis or treatment may occur in up to 30% of patients. Artificial intelligence (AI) tools could help doctors, but an inaccurate tool can make doctors perform worse, so simply keeping a clinician in the loop is not a reliable safeguard.
Why it matters
Patients hospitalized with shortness of breath need the right diagnosis, such as pneumonia versus heart failure, to receive the right treatment. A more robust AI tool that clinicians can use well could reduce diagnostic errors for these patients, and the lessons learned could help hospitals adopt AI tools more safely in other areas of care.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Sarah Miller
Medical University of South Carolina, SC·Medicine & Clinical Research
Test whether RESP-FIT, a home program of respiratory muscle strength training with a portable device and mobile health support, reduces shortness of breath in rural adults with COPD, using a randomized controlled trial against enhanced usual care.
Geoffrey Tison
University of California-San Francisco, CA·Computer Science·Early-career
Develop a deep neural network architecture that accepts multiple raw medical data modalities and incorporates prior physiological knowledge, so it can combine information the way physicians do.
Emily Henkle
Oregon Health & Science University, OR·Medicine & Clinical Research
Enroll three cohorts of patients with NTM lung disease, at diagnosis (NTM-WATCH), at treatment start (NTM-TREAT) and at treatment end (NTM-TRACK), and collect patient-reported outcomes and clinical data for up to 24 months.
The school
University of Michigan: 124 labs on PI Pages, $2.1B a year on research, 963 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.