Nathan is in a Masters of Data Science program through Northwestern University. On October 3rd, he presented at their annual data science symposium in Chicago. The project uses machine learning to classify the type of heartbeat based on electrocardiogram (ECG) data. Nathan proposes integrating ECG testing with machine learning heartbeat classification into the pre-season physical exams for all athletes. This approach can help trainers and physicians identify abnormal cardiac patterns, leading to timely referrals and earlier intervention.

The model accurately classifies normal beat and premature ventricular contractions (PVCs). The hope is that the work helps create a clear path for those in similar situations, helping patients reach the correct diagnosis and treatments more easily. Given his background as a collegiate runner, Nathan recognizes the importance of heart screening and accurate interpretations of results for athletes. Nathan looks forward to continuing to improve the model and work with his sports cardiologist in Charlotte, NC. 

Nathan's work reminds us that innovation often comes from those who understand the stakes most deeply, and his research may one day help countless athletes receive the early diagnosis and care they need.