How Johnson & Johnson Are Analyzing Voice of the Customer Data Using Natural Language Processing (NLP)

Real world evidence provides significant insight into how a drug or drug class performs or is used in real world medical settings. Real world evidence (RWE) and real world data (RWD) can inform all phases of pharmaceutical drug development, commercialization, and drug use in healthcare settings. The ability to quickly transform real world data...
voice of the customer feedback valuable for patient reported outcomes for pharma

Real world evidence provides significant insight into how a drug or drug class performs or is used in real world medical settings. Real world evidence (RWE) and real world data (RWD) can inform all phases of pharmaceutical drug development, commercialization, and drug use in healthcare settings. The ability to quickly transform real world data sources (e.g. EHRs, or patient-reported outcome data from forums, social media) into evidence can improve health outcomes for patients by helping pharmaceutical companies be more efficient in drug development and smarter in commercialization.

Voice of the customer call feeds: a valuable source of real world data

One source of patient reported outcomes available to pharma companies are the feeds that come into the 1-800 call centers – calls from patients, carers, healthcare professionals or pharmacists, asking questions covering many different issues, such as:

  • Unexpected adverse events
  • Users splitting tablets and opening capsules
  • Contraindicated medications among concomitant drugs
  • Switching from one drug to another
  • Off label use
  • Lack of efficacy questions at particular dosages

Using Linguamatics NLP to transform call feeds into actionable insights at Johnson and Johnson

At Johnson & Johnson, the medical affairs team have developed a workflow to process the unstructured feed from call transcripts using Linguamatics I2E. Dr Smita Mitra (Principal Scientist, Data Sciences, Pharma IT, Janssen Pharmaceuticals) has talked at a Linguamatics seminar about the value of this real world “voice of the customer (VOC) project” and the real-time insight generation from VOC data. The workflow takes the call transcripts, and processes them using a broad range of tailored I2E queries to make sense of the unstructured feeds. Each VOC verbatim is tagged with topic categories, such as registering a complaint, requesting formulation information; or, reporting a side effect or drug-drug interaction. Structuring the unstructured VOC feeds with the key metadata enables easy and rapid search and visualization of these valuable data.

Dr Mitra said that this end-to-end VOC analysis solution has more than doubled the efficiency in the analysis of VOC, with a high accuracy (90%). In addition, they have created a centralized repository for all curated and analysed VOC data. These data are accessible to the broader team via an I2E web portal, enabling them to understand changing patient concerns, assess customer insights and make better commercial business decisions.

Read more about Linguamatics NLP text mining for transforming real world data in our application note.

Source: www.linguamatics.com