Clinical Notes Mining

CareCentra’s Natural Language Processing (NLP) tool automatically sifts through huge volumes of unstructured and semi-structured clinical content and derives concepts, structure, and relationships from it.



Unlock the value of your unstructured Clinical data


  • As much as 80% of all health record data is locked in unstructured text (e.g.: physicians’ and nurses’ notes, lab reports, pharmacy systems, discharge summaries, scanned documents, e-faxes, and e-mail messages.).
  • You can’t report on it, you can’t graph patient progress or decline, and you can’t easily compare data from different sources (e.g.: hospitals, clinics, referring physicians, etc.).
  • New text mining tools have emerged that can extract and connect information from various information sources across the health continuum at large scale.  
  • Natural Language Processing (NLP) technologies can extract and connect information – structured and unstructured – from various data sources and make them actionable for analytics.  


ScripTAS Text Analytics FROM CareCentra

  • ScripTAS, the text analytics platform from CareCentra, employs a flexible, ontology-driven, knowledge extraction framework to aggregate clinical data from diverse sources for rapid and powerful search.
  • The underlying ScripTAS framework is based on cTAKES, an open-source clinical ontology developed as a collaborative by the Mayo Clinic and Children’s Hospital Boston.
  • ScripTAS uses machine learning and NLP techniques to map written words to medical concepts based on standardized medical ontologies, linguistic and context analysis and semantics tagging.
  • Through a combination of statistical modeling and NLP processing (NLP), ScripTAS can sift through huge volumes of unstructured clinical content and derive concepts, structure and relationships from it.

Information Flows from Many Sources



ScripTAS Capabilities Include:


  • Aggregation – Capture all content types – regardless of source, location or format ( XML, PDF, Fax, Image, Email, Voice) into a structured, codified patient centric dashboard – from within your organization and across the continuum of care.
  • Analytics – Use NLP to populate a data warehouse and access a range of algorithms to identify at-risk patients for falls, hospital borne infections and other conditions. Identify potential gaps in care and/or clinical documentation to proactively engage patients and minimize potential readmissions.
  • Quality Measures – Mine and extract data from within the clinical narrative and classify patients according to established quality initiatives such as PQRS AND HQI Initiatives to automatically generate core measures for reporting to CMS and JCAHO.
  • Knowledge Extraction – A sophisticated use of NLP, Knowledge Extraction understands and interprets input to produce useable information as its output (e.g.: Extract and compare clinical note data with social media activity to reveal previously unseen relationships.

Log in