The health division of Wolters Kluwer, the legal publisher and technology provider, has launched its own NLP-driven document analysis and data extraction platform – but aimed at the medical sector.
They are calling it a ‘clinical natural language processing (cNLP) solution’ and its purpose is to analyse and collect patient data found in ‘free-text’ doctors’ notes and patients’ electronic health records.
The move, while clearly focused on the medical area, may well be of interest to lawyers working within pharma companies, hospital groups and also at insurance companies – given that this data extracted from unstructured medical notes could become part of the evidentiary basis for negligence defence and compliance disputes. At present this appears to be a US-centric offering.
The company, which is increasing its tech application output as it battles rivals such as Thomson Reuters and LexisNexis in the legal sector, stated that: ‘Unstructured data currently represent as much as 80% of documentation in patient records, creating notable challenges for healthcare organisations.’
Interestingly, they add: ‘Current estimates suggest that the amount of data the healthcare industry amasses doubles every three years, and by 2020, it is projected to double every 73 days. Found in a variety of forms captured throughout the care cycle, such as medical history, progress notes, imaging and laboratory narratives, critical information in free text form remains largely unused due to resource-intensive manual processes required to extract it.’
Let’s just repeat that bit – by 2020 – i.e. in one year’s time, the data collected in the healthcare sector will double every 73 days. This truly is exponential in nature, if the estimate is correct.
Coming back to the legal sector, it’s not known what a similar type of figure would be for all of the world’s legal teams and external legal advisers, but one can imagine there is also a rapidly scaling increase in total data volume, at least when looked at on a global scale.
As with medical data, how will lawyers inside companies be able to handle this? How will insights be made into this growing mass of information as it proliferates through the business and is shared around to external firms? Clearly there is a need to accelerate the adoption of legal AI tools by inhouse teams, from the KM, compliance and business operations side, to the transactional side.
Karen Kobelski, an executive at Wolters Kluwer, Health, said: ‘Over the last 10-plus years, we’ve worked with more than 300,000 clinicians … capturing how they search and document problems and diagnoses at the point-of-care and we’ve combined that expertise with common words associated with labs and drugs, all of which is now completely integrated within cNLP.’
Wolters Kluwer currently has customers across 180 countries and employs 19,000 people worldwide. In 2017, it reported annual revenues of €4.4 billion.