Clinical Data Management Quality Solutions: Hiding in Plain Sight
Eric Rosow, Chief Executive Officer and Jonathan Niloff, MD, MBA Chief Medical Officer
In a recent article in Health Data Management, “Why Clinical Document Architecture Doesn’t Solve Data Quality Issues” author Mohammed Hussain commented on the limitations of the Clinical Document Architecture (CCD). We agree that the CCD presents challenges to accurate transmission of clinical data due to the laxity of the standard and the inconsistent manner by which clinicians perform documentation in their EHRs. However, with the ever-growing numbers of CCDs being exchanged – now in the hundreds of millions annually – technology to process CCDs at scale is required to maximize the value of this clinical data resource.
Notwithstanding the author’s assertions, “Furthermore, there is currently nothing in the third-party software market that could truly and properly parse a CCD for the information needed to resolve this kind of issue. Although plenty of products can create and send CCDs, almost nothing can parse them out into a model with which a data analyst can work”, there is an emerging group of companies with technology solutions to address this problem, including our firm, Diameter Health.
These solutions parse, normalize and de-duplicate CCDs at scale solving for the challenges presented by the laxity of the standard and heterogeneous documentation practices among clinicians. Some of the required functions these solutions provide include:
- Extraction and Parsing
- A context-sensitive information model to extract clinical data elements from both machine readable and human readable content
- Normalization and De-duplication
- Automated terminology management for standard vocabularies
- Normalization of data for major clinical domains (Allergies, Encounters, Medications, Immunizations, Payers, Problems, Procedures, Results & Vital Signs)
- Automated correction of common vocabulary and syntax mistakes
- Use of Natural Language Processing (NLP) for multiple medical concepts
- Regrouping of inbound data into appropriate clinical categories
- Data Enrichment
- Automated ontology and category assignment and inference of missing medical concepts
Technology solutions with these capabilities enable the meaningful exchange of clinical data and the creation of robust clinical data sets ready for analytics.
Diameter Health’s solution, Fusion, may be implemented with any certified EHR without the need to create custom interfaces. It is currently being used by multiple Health Information Exchanges to support high quality clinical information exchange, and to produce a consolidated patient view from multiple data sources. This provides substrate data to enable population health and other analytics, including quality measurement. In fact, NCQA has launched a certification program for technology using CCDs to produce accurate and robust quality measurement (http://www.ncqa.org/hedis-quality-measurement/certified-survey-vendors-auditors-software-vendors/emeasure-certification ).
While the variable implementation and challenges of the CCD are many, the wealth of clinical data they contain cannot be overlooked while future standards, such as FHIR, take time to mature and become widely adopted. Technology provided by Diameter Health allow clinicians and analysts to harvest the value in CCDs.