pharmatechoutlook

Clinithink: Transforming Unstructured Clinical Narrative into Structured Patient Information

CIO VendorChris Tackaberry, CEO
Globally, healthcare is undergoing profound changes primarily driven by the increasingly challenging economics of conventional healthcare delivery. Healthcare providers are progressively adopting new technologies to analyze vast amounts of data. It has become critical to have the ability to use the available data within healthcare and life sciences.

“Transforming unstructured clinical narrative into structured patient information helps to make better clinical decisions to improve patient outcomes, more accurate population health management and faster subject recruitment for clinical trials,” says Chris Tackaberry, CEO, Clinithink. Clinical information systems typically capture data in structured formats, derived from template-driven user input. “But unstructured narrative within progress notes, discharge summaries, consults, referrals and reports are also increasingly available electronically. Using conventional approaches, this data is not easy to exploit,” says Tackaberry.

Though common structuring techniques, such as manual tagging with metadata or text mining are being used, companies find it ineffective while extracting information, particularly when the text data has been captured at the point of care, containing synonyms, acronyms and mis-spellings typical of operational healthcare delivery. Headquartered in Alpharetta, GA, Clinithink provides Natural Language Processing (NLP) applications that can interpret unstructured clinicians notes using specialized linguistic algorithms, extracting the clinical information for better health management and faster subject recruitment for clinical trials.

To provide this capability, Clinithink has developed CLiX its Clinical Natural Language Processing (CNLP) engine. Using sophisticated clinical language models and algorithms, CLiX CNLP transforms the unstructured data’s clinical meaning into standardized terminology to use across a broad range of healthcare technology applications.

Furthermore, Clinithink has developed CLiX ENRICH, a data query platform that turns the unstructured data into a valuable, consumable data stream for analytics.
One of the UK’s leading healthcare providing organizations, Barts Health NHS Trust, deployed Clinithink’s CLiX ENRICH platform as a part of their solution to support the analysis of e-health record information linked to other routinely connected clinical data in order to learn more about vulnerable patient groups.

Using CLiX ENRICH, the customer was able to access and “light up” the relevant unstructured clinical data extracted from their EMR. CLiX ENRICH helped them to interrogate the unstructured data and combine it with structured data to enable them to identify high risk groups that can then be proactively managed to improve outcomes and reduce cost.

According to Markets and Markets, the NLP market for healthcare and life sciences industry is estimated to grow to $2.67 Billion from $1.10 Billion in 2015. To address this rapidly evolving market, Clinithink is focusing on developing solutions which enable life science companies and their partners to explore unstructured data and exploit this untapped asset.

We believe our solution can have a significant impact on the patient identification stage of the recruitment process in clinical trials


“In the life sciences space, we believe our solution can have a significant impact on the patient identification stage of the recruitment process. It is well known that manual chart review is an expensive and time-consuming process needed to assess eligibility against the more complex inclusion and exclusion criteria for a protocol. This step is required because structured EMR data is not usually sufficiently granular to enable assessment against these criteria. Using CLiX ENRICH, we can largely automate the manual chart review step in patient identification for recruitment, delivering potentially significant savings in the cost and time taken to identify high quality patients for screening. Early proof point work we have done in the field supports our belief that the overall impact this approach can have on patient enrolment is substantial, especially for those trials with complex clinical inclusion and exclusion criteria.” shares Tackaberry.