Medical Coding of Patient Records
Break the productivity barriers, transforming the raw patient data into structured knowledge in your role as a pharmaceutical company, clinical trial professional or medical device manufacturer. Our solution helps process automatically large volumes of patient records and extract and semantically index data about patient diagnoses, treatments, medications, adverse events and medical history.
How You’ll Benefit
Enhance your (medical) coding workflows
- Save time searching for relevant codes and locating patient data;
- Eliminate ambiguity within your data.
Get actionable insights from you data
- Easily find hidden relationships between entities and trends in patient data;
- Enrich your data with more meaning – store all application concepts, their text definition, labels and full semantic context.
Adopt FAIR data principles
- Standardize medical terminology by mapping your data to MedDRA, WHODrug, SNOMED CT, MeSH, etc.;
- Improve data interoperability and inexpensively integrate internal data with publicly available open data.
Customize to your needs
- Tailor as per your requirements – pre-populate your data with pharmaceutical products;
- Integrate internal data with publicly available open data.
How It Works
Semantic medical coding of patient records applies text analysis pipelines to extract structured medical information and enriches the extracted data with the available structured knowledge to provide innovative approaches for semantic data exploration and search.
Process patient narrative information with the help of text mining pipelines.
Apply ontology-based text analysis to detect concepts and disambiguate meaning using biomedical ontologies that rely on the background knowledge from the
Extract structured format diagnosis, medication and other important clinical data.
Model the extracted facts in RDF using the concept’s original identifiers provided by the ontologies.
Load the extracted and normalized information in the medical Knowledge Graph.
Semantically fuse the data with all the background knowledge available in the Knowledge Graph, where it could be used for defining new inference rules and generating new insights.
Develop custom patient classifications specific to the different therapeutic areas using a high-level semantic query language.