‍

Unstructured EHR data in clinical notes is a rich source of clinical information and can be used alongside structured data to offer deeper patient characterization. Previously, this information was standardized and made available for research only through time-consuming, manual extraction that is nearly impossible to perform at scale.

Holmusk has developed novel natural language processing (NLP) models specific to behavioral health to extract essential information from unstructured notes. These NLP models are applied to unstructured data, and the resulting insights are made available in NeuroBlu, a powerful analytics tool built to explore the world’s richest real-world database for behavioral health.

Holmusk previously developed a depressive disorders model, which identified the presence or absence of anhedonia and suicidality, and has now developed a psychotic disorders model. The psychotic disorders model identifies a selected set of positive symptoms associated with psychotic disorders, and negative symptoms associated with a subset of these disorders. These symptoms are identified within unstructured data in the form of clinical notes and transformed into structured, analyzable data.

Applying NeuroBlu NLP to unstructured notes for patients diagnosed with a psychotic disorder results in substantial increases in cohort sizes. Read the use case to learn more about how our newest NeuroBlu NLP model amplifies patient profiles, enhances data density, and increases cohort sizes.

{{cta}}

‍

Interested in learning more? Contact us to schedule a demo.