What We Do
Roam enables healthcare experts to observe and understand real-world medical treatment trends in novel, nuanced, and comprehensive ways. Our technologies unlock the value of patient data and drive decisions that improve health outcomes.
Roam makes this possible by using machine learning and natural language processing applied to patient/provider interactions to reveal information about lifestyle, rationale, disease progression, and treatment choice. These insights, often buried in unstructured data, are otherwise undetectable and far too labor-intensive to extract with current tools.
How We Do It
Purpose-driven data ingestion and integration
Health data is inherently heterogeneous and often incomplete; Roam Health Knowledge Graph enables rapid ingestion and more complete context formation for data.
Natural language extraction
Structured data captures limited information about patients, but Roam’s natural language framework extracts complex concepts from free text and semi-structured data to surface valuable attributes that don’t exist in structured data alone.
Advanced patient modeling
Roam’s machine learning framework allows featurizing patient data to form a more contextually complete view of a patient. It also automates the statistical best practices required to responsibly work with large, complex healthcare datasets.
Chief Executive Officer
Chief Executive Officer | Co-Founder
Alex is the Co-Founder and Chief Executive of Roam. Before Roam, Alex co-founded and served as Chief Executive of Frontier Strategy Group (FSG), a venture-backed data and analytics company focused on emerging markets that currently serves more than 250 leading multinationals.
Alex and his family immigrated to the United States from the Soviet Union in 1988. He holds B.A. and M.A. degrees in International Relations from Stanford University and a J.D. from the Yale Law School.
Co-Chief Scientist | Co-Founder
Andrew recently completed his Ph.D. in Computer Science from Stanford University, where he was advised by Andrew Ng. His research focuses on large scale deep learning to solve some of the most challenging problems in data analytics and forecasting, speech recognition, natural language processing, and computer vision.
Andrew developed machine learning systems in industry for Coursera, where he built biometric classifiers; and IBM Research, where he built speech recognition systems capable of learning new languages quickly. Andrew received his B.Sc. from Carnegie Mellon in 2009 in Computer Science and Cognitive Science.
Chris Potts is Professor of Linguistics and, by courtesy, of Computer Science at Stanford University. He is also Director of the Center for the Study of Language and Information (CSLI) at Stanford. In his research, Chris develops computational models of linguistic reasoning, emotional expression, and dialogue. He is author of the book The Logic of Conventional Implicatures as well as numerous scholarly papers in linguistics and natural language processing.
Chris received his B.A. in Linguistics from New York University and his Ph.D. in Linguistics from the University of California, Santa Cruz.
195 E. 4th Avenue
San Mateo, CA 94401
Data-driven healthcare insights. Passion-driven team. Join Us.