Real world evidence (RWE) and Real World Data (RWD) can inform all phases of pharmaceutical drug development, commercialization, and drug use in healthcare settings. Many sources of real world data contain large amounts of unstructured text (e.g. EHRs; patient-reported outcomes such as forums, social media). Linguamatics I2E extracts the key facts, using relevant ontologies and focused queries, transforming real world data into actionable intelligence for decision making.
Understanding the real world (i.e., outside of clinical trials) impact of therapies on patients is critical for pharmaceutical and biotech companies. However, many RWD sources contain unstructured text, which prevents easy analysis. I2E text analytics can unlock the value from real world sources such as medical records, claims data, adverse event reports, and customer call transcripts. By using NLP to extract key facts from these diverse data sources, pharmaceutical companies, healthcare providers and payers can determine medication effectiveness, safety and cost benefits.
The Real World Challenge
There are many challenges in creating value from real world data (RWD). These include:
- Data access (which may involve patient privacy issues)
- Data quality (e.g. missing data, coding errors)
- Data structure (e.g. complex grammar for twitter or customer calls)
- Data extraction and integration of structured and unstructured fields, and mapping to standards (e.g. medical codes, vocabularies, formats).
The NLP-based text mining Solution
Linguamatics NLP text mining addresses these challenges to get value out of RWD - extracting the key facts from these unstructured documents, using relevant ontologies and focused queries –transforming real world data into real world evidence, and actionable intelligence for decision making.
Organizations can use Linguamatics I2E to extract information on treatment patterns e.g. drug switching, discontinuation; or numerics such as lab values, dosage information; or patient information such as history of disease, problem list, demographics, social factors and lifestyle. The agile iterative nature of query development in I2E means that business rules can be encoded to suit the particular data set, whether that be sentiments from tweets or treatment pattern choices and resulting outcomes from EHRs.