Project Machine-Learning enabled Genotype-Phenotype Correlation in Pediatric Thoracic Aortic Aneurysms Program DUIRI - Discovery Undergraduate Interdisciplinary Research Internship Term Summer 2026 Status Accepted Research Area Global Health Description According to the World Health Organization, cardiovascular disease is the leading cause of death worldwide, with over 75% of deaths resulting from cardiovascular disease being in lower- and middle-income countries. One type of cardiovascular disease is the development of aortic aneurysms. Aortic aneurysms result from weakness in the aortic wall that leads to wall expansion and ballooning. Aortic wall dissection can follow this expansion, ultimately leading to rupture of the aorta, which has a very high mortality rate. The goal of this project is to test the hypothesis: distinct genetic and clinical etiologies of aortic root (the portion of the aorta originating from the heart) dilation, namely Marfan Syndrome (MFS), bicuspid aortic valve (BAV), and idiopathic, present with unique biomechanical phenotypes of the aortic root. Comparing patients within these groups provides an opportunity to identify mechanistic differences that current standard approaches do not reveal. Echocardiograms obtained from pediatric patients at Riley Hospital for Children will be used to develop and train machine learning models to test the hypothesis, that will eventually affect the clinical diagnosis and monitoring of pediatric ATAAs, based on the American Heart Association (AHA) guidelines. Supervisor Craig J Goergen Mentor Shubh Parag Mehta Type of work required Students selected for this project would be expected to assist with extracting phenotypical data from echocardiograms using previously developed deep learning models, performing linear mixed-effects regression to evaluate genotype-phenotype associations while adjusting for age, sex, and body surface area, and the development and validation of unsupervised clustering algorithms to test these correlations within and between the clinical groups. They will also have the opportunity to conduct comparative statistical analyses of the quantified metrics obtained from deep learning models and board-certified pediatric cardiologists (for example, Dr. Landis, a collaborator on this project). Websites https://engineering.purdue.edu/cvirl
https://pubmed.ncbi.nlm.nih.gov/39299353/
Paik, Joshua; Mehta, Shubh P.; Sivakumar, Samskrithi; Dinklage, Felix; Lee, Ahhyun; Landis, Benjamin J.; and Goergen, Craig J., "Improving Echocardiographic Aortic Aneurysm Assessment in Marfan Syndrome Patients" (2025). Discovery Undergraduate Interdisciplinary Research Internship. Paper 60.
https://docs.lib.purdue.edu/duri/60 Qualifications Students should be highly interested in medical imaging. Previous coding experience is required in Python and/or MATLAB. A basic understanding of cardiovascular anatomy will be helpful but not required. Credit Hours 0 Weekly Hours 40 (estimated)