Data science provides excellent tools for health professionals to gain valuable knowledge from patient information and dataset. At the D2K Lab, students have the opportunity to work on projects sponsored by medical centers, researchers and health solution companies to tackle various topics of the industry, such as ECGs, preventive modeling, imaging analytics, and diagnostic accuracy, etc.
Exploring High Risk Factors in an Animal Model of SIDS
By experimentally inducing a hypothesized Sudden Infant Death Syndrome-like phenomenon in mice, the Russell Ray Lab in the Baylor College of Medicine is collecting ECG and breathing data from genetically engineered mice to explore potential risk factors that make the mice more susceptible to expiration. The goal of the student team "Breathe Easy" is to discover signatures in the cardiopulmonary data that can help uncover the factors that contribute to higher susceptibility towards expiration in the mice.
Students apply data science skills to understanding how the next coronavirus variant will affect us by studying the impact of vaccinations and government involvement on previous variant surges.
An Automated Early Warning System to Help Doctors Save Babies
Rice D2K Lab students working with Texas Children’s Hospital created machine-learning algorithms to increase detection time before cardiac arrest
Cardiac arrest events are often preceded by subtle, almost undetectable signs. What if doctors can detect early signals faster and more accurately with deep-learning algorithms?
Team Cardiac Signals, six senior electrical and computer engineering majors at Rice University, developed a metric to give an early warning for cardiac events by analyzing electrocardiogram (ECG) signals. “This metric can make life-saving treatments proactive instead of reactive,” said Frank Yang, a physics major.
The student team used auto-encoders, non-linear deep-learning algorithms to monitor the ECG heartbeats before cardiac arrest. “We learned the patterns of healthy heartbeats and compared other heartbeats to assess how well they followed these patterns,” Damaraju said. “Then, we ultimately detected when heartbeats began to deviate from healthy behavior which indicated cardiac electrical stability.”
Read the Full Story about Team Cardiac Signals' Project >>
D2K students develop a deep learning model to forecast stroke risk
Early detection and mitigation of recurrent stroke is critical to reducing the overall stroke fatality rate.
D2K student team "Stroke Risk" works on a data science capstone project sponsored by UTHealth to predict recurrent strokes using machine learning. UTHealth can use this model to identify at-risk patients, give them the preventative care they need, and ultimately save their lives.
COVID-19 Houston Response Projects
COVID-19 Houston Response Projects (CHRP) was a data science competition that the Rice DataSci Club and the D2K Lab hosted to encourage all Rice students, grad and undergrad, to get involved in the response to the COVID-19 pandemic. Students used their data science and computing skills to help solve a number of pressing local challenges. Five student teams from the CHRP competition presented their projects at the D2K Virtual Showcase.
The winning project of the CHRP competition is Mobility and Predictors of Movement During COVID-19
Learn more about the CHRP projects >
Beat-to-beat Classification of Unlabeled ECGs in Adult Populations
ECG machines collect hours of data on patient heart activity each day, and doctors often do not have time to analyze all the data. The goal of this project is to process all the data and tag abnormalities for doctors to review.
Pediatric Cardiac ICU Arrhythmias Detection
Student team developped a novel semi-supervised classification algorithm that detects JET, a lethal heart condition, in real-time by analyzing morphologies and features of the electrocardiogram and central venous pressure signals. This algorithm eliminates alarm fatigue and saves more children who suffer from arrhythmia.
Inferring Genomic Signatures in Age-Related Macular Degeneration Across Different Stages
Student team predicted the importance of certain genes that are responsible for AMD across different stages. Using those genes, we analyze gene networks to give better information to doctors to find an effective cure for AMD which currently does not exist.
Interested in working with Rice students and faculty on a real-world data science project? Send us an email at firstname.lastname@example.org.
Watch more health-related videos on the D2K YouTube Channel >