We love technology and are inspired by the potential of large scale data to impact patient care. Data streams from wearable devices, medical imaging, electronic health records, and multi-omics are our favorites. We partner with companies like Apple, Google, and Samsung to promote precision health at scale.
Large language models to enhance patient care in cardiac disease
Large Language Models (LLMs) have emerged as a revolution in computational sciences, offering unprecedented insights into the complex relationship between genetics and disease. With the ability to process long contexts, these models are redefining our approach to DNA and protein analysis—taking into account biological processes such as splicing to enhance our understanding and treatment of diseases like cardiomyopathy. In addition, Large Protein Models are changing the field by their ability to generate novel functional proteins, with the promise of using them to improve gene therapy. By harnessing the power of LLMs, we also tailor personalized health coaching notifications to encourage increased physical activity. By integrating behavioral science frameworks into these models, we aim to effectively mitigate the risk of long-term cardiovascular diseases, thus bridging the gap between clinical research and practical, everyday health interventions.
Deep learning and genetic association
Our work in cardiac imaging extends to magnetic resonance imaging (cardiac MRI). We have developed an open-source software tool, DeepFlow, which uses a U-Net based segmentation model to extract aortic blood flow parameters, ranging from blood flow velocities to valve function. The deployment of DeepFlow on data from the UK Biobank, encompassing over 35,000 participants, has enabled insight into the genetic underpinnings of these cardiovascular traits. Causal inference through Mendelian randomization revealed that genes affecting aortic size may cause aortic valve insufficiency. These insights could lead to genetically-informed treatments.
ArtificiaI intelligence for electrocardiograms
We develop deep learning models to understand medical signals. We hope to build systems which improve physicians’ performance on everyday tasks like electrocardiogram interpretation, to discover new diagnostic abilities like distinguishing between hypertension and hypertrophic cardiomyopathy as causes of cardiac hypertrophy, and to develop new risk scores for understanding patients’ overall health like our SEER model. We also seek to better understand existing models, for example by investigating how they perform in different demographic groups and by trying to find the underlying features on which these techniques rely. Our group also develops methods for interpreting cardiac imaging, targeting well-understood as well as novel applications.
Deep learning for wearable data and telemetry
We use digital data to develop novel deep learning architectures for the detection of abnormal cardiac events. Monitoring and tracking of patients’ cardiovascular states are of particular interest and we have focused on two data streams in particular: wearable devices and in-hospital telemetry. We developed Deepbeat a novel deep learning method for the detection of atrial fibrillation from wearable device data. We are actively developing approaches to smart telemetry to improve in-hospital alarms.
My Heart Counts
The My Heart Counts Cardiovascular Health Study is one of the largest fully digital platforms to study how lifestyle patterns influence cardiovascular health. Our app was the platform for the first fully digital randomized clinical trial. Recently, we showed that personalized e-coaching prompts were more likely to increase physical activity. The next generation of the My Heart Counts Cardiovascular Health Study will leverage advances in artificial intelligence to deliver real-time insights and recommendations, tailored to a user’s unique physiology, routines, and situation, all while studying the impacts of physical activity on cardiovascular health and wellness as a whole.
