Challenge

Natural Language Processing Expertise

Data is at the heart of fighting cancer as it’s central to finding effective ways to prevent,  diagnose, and treat the disease. The challenge, however, is that much of the data is unstructured. Examples include clinical notes, surgical and lab reports, clinical trial data, and discharge notes.

A prominent US-based healthcare provider recognized the importance of unstructured data for all cancer-related activities – from research through treatment. However, given the volume and complexity of the work, they knew they needed assistance from a company that had Natural Language Processing expertise, experience with the applied tooling, and a deep understanding of medical terminology. For help, they turned to Klarrio US.

A second project where Klarrio was asked to apply its NLP expertise was the analysis of drug labels.

Every manufacturer submits a label for every drug they register with the United States Food and Drug Administration. The label is structured; however, the structure mostly defines the sections of the label, but the section itself may contain a lot of unstructured data in the form of free text. Extracting elements of interest from the text, such as a list of clinical studies, what arms they have, what adverse reactions each arm had, and the outcomes the adverse reactions resulted in, can enable a much deeper research across all the drugs dataset and correlate reactions and outcomes across the drugs, for example, connecting them to a common ingredient.