Nosheen Reza
University of Pennsylvania, PA·Medicine & Clinical Research·Early-career
Hypertrophic cardiomyopathy is the most common inherited disease of the heart muscle, in which the heart wall becomes abnormally thick. It affects an estimated 750,000 people in the United States, but only about 100,000 have been diagnosed.
- Fields
Medicine & Clinical Research
Computer Science
Public Health & Epidemiology
- Topics
hypertrophic cardiomyopathy
inherited heart disease
machine learning
- Grants
- 1 known grant, through Aug 2028
What they work on
- Build and validate a machine learning model that detects hypertrophic cardiomyopathy from electrocardiograms in Penn Medicine electronic health record data, and test whether adding other EHR-derived traits improves detection.
- Test the best-performing EHR-based models in two large independent health systems to confirm that they work across different patient populations.
- Use implementation science methods to identify clinician barriers to and facilitators of timely hypertrophic cardiomyopathy diagnosis, and assess clinicians' attitudes toward an EHR-based diagnostic model.
More about the research
Missed diagnoses matter because the disease can lead to heart failure, irregular heart rhythms, stroke and sudden death. Patients' at-risk relatives may also go unchecked. This project asks whether machine learning applied to the routine data in electronic health records (EHRs) can flag people who should be evaluated for the disease.
Why it matters
Most people with hypertrophic cardiomyopathy are never diagnosed, which puts them at risk of heart failure, arrhythmias, stroke and sudden death. An EHR-based screening model could help doctors spot these patients and their at-risk relatives earlier, so they can receive targeted treatment. Understanding clinicians' barriers to diagnosis could also guide how such tools are adopted in practice.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Oguz Akbilgic
Wake Forest University, NC·Medicine & Clinical Research
Develop an AI model that predicts future heart failure with preserved ejection fraction (HFpEF) from ECG data, using carefully verified data from NIH-funded studies.
Theodore Abraham
University of California-San Francisco, CA·Medicine & Clinical Research
Determine how heart muscle function limits exercise in non-obstructive HCM by measuring regional and global myocardial strain with echocardiography at rest and at peak exercise, and relating it to exercise capacity.
Michael Rosenberg
University of Colorado Denver/Anschutz Medical Campus, CO·Medicine & Clinical Research
Develop and test a cloud-based deep-learning model that predicts risk of drug-induced long QT syndrome from electronic health record data on hospitalized and outpatient patients, without requiring a prior electrocardiogram.
The school
University of Pennsylvania: 90 labs on PI Pages, $2.2B a year on research, 750 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.