GraphConnect 2018

The transition to electronic health record systems promised the goal of standardizing health information for clinical research, aggregate decision support, and interoperability. But, despite investing billions of dollars on modernizing health information infrastructure, the impact on healthcare outcome has been relatively modest. Patient care remains fragmented, costs continue to rise and medical professionals remain frustrated and dissatisfied. The proximate cause is the electronic medical record’s failure to meet the complex data needs of the industry.

MEDICUS is a graph-powered solution which offers an improved method of information capture between patient and provider. Our guiding principle is that computers should be designed to increase human control rather than optimizing computer processing at the expense of human effort.
Rather than emulating the paper chart, the MEDICUS knowledge graph models the corpus of medicine itself. The graph incorporates concepts from multiple medical terminology systems (CPT, ICD, SNOMED, NPI, Medical taxonomy) into a composite data store. Instead of free-text definitions, a seed pattern of clinically-relevant relationships defines concepts in a formal way to reflect the semantics of the concept. A common schema supports a uniform user interface and enables efficient documentation by way of semantic navigation: click and discover, rather than search and retrieval.
The solution saves time for the physician, returns the focus back to the patient, and creates computable medical records for healthcare payers to make informed coverage decisions.