Oguz Akbilgic
Wake Forest University, NC·Medicine & Clinical Research
Heart failure affects more than 6 million US adults and shortens lives. Catching heart problems early lets doctors step in before damage builds.
- Fields
Medicine & Clinical Research
Computer Science
Biomedical Engineering
- Topics
artificial intelligence
machine learning
deep learning
- Grants
- 2 known grants, through May 2027
What they work on
- 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.
- Build an HFpEF risk model from large electronic health record datasets at three health systems and combine it with the NIH-data model through transfer learning, which adapts a model trained on one dataset to another.
- Use ECG data from patients who already have HFpEF, including HeartShare Study participants, to develop and test AI classification of HFpEF subtypes that might respond to different treatments.
- Refine and internally validate an AI tool that combines signal processing and deep learning on ECGs to predict cardiomyopathy within 3, 5 and 10 years among 3,731 childhood cancer survivors in the St. Jude Lifetime Cohort.
- Externally validate the cardiomyopathy tool in 343 survivors from the Amsterdam LATER cohort, and test whether smartwatch ECGs give risk predictions that agree with standard clinical ECGs.
More about the research
The electrocardiogram (ECG), a quick, cheap recording of the heart's electrical activity, is available almost everywhere. The lab's projects apply artificial intelligence (AI) to raw ECG signals to predict who will develop heart disease, aiming for tools that are low cost and easy to use widely.
Why it matters
Cheap, widely available ECGs analyzed by AI could flag people at high risk of heart failure with preserved ejection fraction, supporting earlier prevention and therapies matched to subtype. For childhood cancer survivors, such tools could identify who needs more frequent or advanced heart imaging. Smartwatch-based screening could eventually let survivors be monitored remotely.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Stefano Morotti
University of California-Davis, CA·Physiology
Identify key molecular and cellular changes in excitation-contraction coupling, the link between electrical signals and heartbeats, in a mouse model of heart failure with preserved ejection fraction (HFpEF), using functional and transcriptomic data.
Marat Fudim
Duke University, NC·Medicine & Clinical Research
Test whether intravenous iron, compared with placebo, reduces death and hospitalization and improves quality of life in 300 older adults with HFpEF and iron deficiency, using a double-blind randomized trial run within routine care at four health systems.
Nosheen Reza
University of Pennsylvania, PA·Medicine & Clinical Research·Early-career
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.
The school
Wake Forest University: 27 labs on PI Pages, $345M a year on research, 54 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.