Qiuying Sha
Michigan Technological University, MI·Computer Science
Heart failure is common and deadly, and one standard treatment is cardiac resynchronization therapy (CRT): a pacemaker-like device that sends electrical pulses so the heart's left and right pumping chambers (ventricles) beat together again. Yet 30–40% of patients who receive CRT do not improve.
- Fields
Computer Science
Biomedical Engineering
Medicine & Clinical Research
- Topics
cardiac resynchronization therapy
heart failure
electrical dyssynchrony
- Grants
- 1 known grant, through Jul 2027
What they work on
- Identify subgroups of heart failure patients more likely to respond to cardiac resynchronization therapy by applying unsupervised machine learning to combined ECG electrical timing and gated SPECT mechanical timing measures.
- Optimize and explain the multi-stage clinical decision process for selecting CRT patients using reinforcement learning, an approach where an algorithm learns the best sequence of decisions.
- Develop a method that recommends left ventricular pacing sites by combining electrical dyssynchrony, myocardial viability (living heart muscle), and mechanical dyssynchrony from SPECT myocardial perfusion imaging.
- Rigorously validate the new algorithms and clinical knowledge for predicting and improving CRT response.
More about the research
According to the project, there are three reasons. Doctors pick patients mainly from the electrocardiogram (ECG), which only measures electrical timing problems. Mechanical timing problems, meaning how unevenly the heart wall actually moves, are underused. And the wire that paces the left ventricle is often placed in a poor spot.
Why it matters
Many patients with heart failure receive a CRT device and gain little benefit, while still bearing the risks of an implant. Better ways to choose who receives CRT, and where to place the pacing lead, could raise response rates. Clinicians would get interpretable decision support built from routine ECGs and nuclear heart scans. That could help them avoid procedures unlikely to help some patients and improve heart function in others.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Alexandra Thomas
Duke University, NC·Medicine & Clinical Research
Characterize and quantify small-vessel (microvascular) injury and changes in heart blood flow during early near-complete estrogen deprivation, using serial cardiac MRI stress studies over two years.
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.
Lisa Rong
Weill Medical College of Cornell University, NY·Medicine & Clinical Research·Early-career
Compare how single versus multiple arterial grafting during bypass surgery changes heart function, measured as echo strain by transesophageal echocardiography, and whether changes relate to blood pressure-support drug use.
The school
Michigan Technological University: 9 labs on PI Pages, $107M a year on research, 86 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.