The health care industry is built on an awful lot of manual infrastructure, and the strain can grow even more with the adoption of standards such as the tenth revision of the World Health Organization’s International Statistical Classification of Diseases and Related Health Problems (ICD). In the U.S., the adoption deadline of ICD-10, which codes for diseases, signs and symptoms, abnormal findings, complaints, social circumstances, and external causes of injury or diseases, is set for October of 2014.
“The way the country is trying to address quality improvement in health care is requiring more information to be captured electronically in a system so it can be processed and used to improve care,” explains Dr. Daniel Riskin, MD, MBA, FACS, and CEO and co-founder of Health Fidelity. Earlier this year the company released the REVEAL cloud-based service for healthcare IT application companies and their healthcare organization customers. “The first step is for doctors to use electronic health records. The next is to drive increasing capture of useable information,” Riskin concludes.
Typing medical narratives is just text – it’s not useable information. Making it useable for standards such as ICD-10 – which is some five times as detailed as ICD-9 – can lead to situations where doctors and nurses have to do twice as much work tagging items within narratives, and where coding departments can grow to be twice as big. The aim to improve health care via such efforts is sound, but so too is relying more on technology and less on manual labor to get value out of the unstructured data.
The clinical NLP (natural language processing) technology in Health Fidelity’s REVEAL platform steps into the picture here, transforming huge volumes of unstructured clinical data (Big Data if ever there was any) into information that healthcare IT application vendors and their hospital customers can then make use of to improve care quality, safety and efficiency.