Artificial Intelligence / Digital Health

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.

My Heart Counts

The My Heart Counts Cardiovascular Health Study was among the first ResearchKit apps developed in collaboration with Apple. It provides a digital research platform for a large-scale study of how genetics, physical activity, sleep patterns, and other lifestyle factors influence cardiovascular health. We completed the first fully digital randomized clinical trial on the platform.

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.

chart

AI approaches to medical data

Multi-modal data is central to cardiology. We are developing deep learning approaches to precision phenotyping of the heart and studying its performance through the complex interplay of human and computer merging human intelligence and artificial intelligence, We have publicly released data including over ten thousand echocardiogram videos for use by computer scientists, data scientists, and cardiologists. Most recently, we are excited to take advantage of the power of language models at multiple scales from the molecular to cellular to whole human.

chart