Do you know that every 40 seconds someone in the U.S. has a stroke? If a patient has a recurrent or additional stroke, they are 17 times more likely to die, which is why early detection and mitigation of recurrent strokes is critical to reducing the overall stroke fatality rate.
Through the Data to Knowledge (D2K) Lab, a team of students is working on a data science capstone project sponsored by UTHealth to predict recurrent strokes using machine learning. Members of team Stroke include six senior electrical and computer engineering students: Artun Bayer, Josue Casco-Rodriguez, Nick Glaze, Samantha Fuentes, Justin Cheung and Michael Sprintson.
The students leverage UTHealth’s comprehensive database of nearly 5,000 stroke patients that contains three different modalities of data: electronic health records (EHR), brain scan images and texts of clinical notes. Students combine these three modalities by using the graph framework.
In the first semester of their yearlong project, the team has converted the EHR data into a graph, started extracting features from the image and text data, and built graph learning models that can predict recurrent strokes. UTHealth can use this model to identify at-risk patients, give them the preventative care they need and ultimately save their lives.
The D2K Lab is a campus hub for innovative and interdisciplinary data science education, working with students from many disciplines across campus. Students at the lab solve real-world data science problems in partnership with companies and community organizations
— Shanna Jin
Communication and Marketing Specialist
Data to Knowledge Program