Natural Language Processing
Typical methods for aggregating encounters or surgical cases do not result in red apples to red apples comparisons. For example, primary Electronic Medical Record (EMR) fields are used to group encounters based on billing codes. These groupings often include sicker or more complicated cases. Cohorts define comparable procedures exactly the way physicians want to see them.
In order to identify and interpret detailed Operative Notes from the surgeon, Empiric utilizes Natural Language Processing (NLP) to draw upon specifics only documented in the operative note to group cases based on clinically meaningful concepts.
Empiric Health has over 40,000 algorithms using both structured and unstructured data. We apply combinations of data science techniques, including Natural Language Processing and Machine Learning, to ensure that cohorts are clean, clinically relevant groupings of data that make sense to physicians.
We believe our NLP and Machine Learning capabilities create a powerful platform to drive physician change through clinically meaningful data analytics.