At the HIMSS17 conference in Orlando, the nonprofit Regenstrief Institute announced a partnership with analytics vendor Health Catalyst involving Regenstrief's artificial intelligence-powered text analytics technology.
Regenstrief's nDepth technology, developed at Regenstrief within the Indiana Health Information Exchange, has been fine-tuned through extensive and repeated use searching over 230 million text records from more than 17 million patients. The Indianapolis-based organization said it promises to unlock the vast troves of unstructured data hidden within electronic health records (EHRs). As a commercialization partner, Health Catalyst will incorporate the nDepth solution into the Health Catalyst data analytics platform used by health systems serving 85 million patients across the United States.
"Eighty percent of clinical data is locked away in unstructured physician notes that can't be read by an EHR and so can't be accessed by advanced decision support and quality improvement applications," said Peter J. Embi, M.D., M.S., president and CEO of Regenstrief, in a prepared statement. "By combining Health Catalyst's analytics market leadership and data platform with our text analytics and expertise, we will help millions of patients benefit from the untapped potential hidden within unstructured data."
Memorial Hospital at Gulfport, in Gulfport, Miss., served as the co-development partner and first deployment site for Health Catalyst's integration of nDepth. The 445-bed not-for-profit health system deployed the Health Catalyst data and analytics platform in 2014.
"I believe it is important for community health systems like Memorial that have made significant investments in electronic health records to take the next step in care by unlocking the value in the EHR's unstructured data," said Gene Thomas, CIO of Memorial Hospital at Gulfport, in a prepared statement. "Our partnership with Health Catalyst and their incorporation of nDepth is enabling that value to impact the front lines of care for the first time."
The nDepth solution uses Natural Language Processing (NLP)—a combination of linguistics, pattern recognition, and machine learning—to derive meaning from text. nDepth enhances these foundational technologies with clinical domain expertise and rich phenotype libraries built and curated by clinicians.
Some recent applications of nDepth include:
- Finding patients with metastatic melanoma
- Identifying pre-diabetic patients for clinical trials
- Capturing hypoglycemic events
- Identifying patients with family history of lung cancers
- Mapping patient trajectory following cancer treatment
- Detecting treatment failure in insomnia
- Finding reasons for refusal of osteoporosis medications
- Identifying "triple negative" breast cancers
