• News New Blog Banner

  • Study: EHR Interoperability Necessary for Evaluating Quality Improvement

    Electronic health records (EHRs) are effective for improving patient care and clinical decision making, and the transition to value-based care and the increasing focus on population health also makes them a promising tool for comparing quality data across the board. But with so many different EHR vendors out there, increased standardization is essential, according to a new study from the Netherlands published in BMC Medical Informatics and Decision Making.

    In the study, authors examined whether data extracted from EHRs was as complete and correct as data from 5,960 physical therapist (PT) surveys describing patient cases for calculating quality indicators. There were 160,000 patient cases in the survey and 90,000 from EHRs.

    After identifying 8 quality indicators based on current practice guidelines, authors found that 3 could not be extracted from the EHRs at all, and another could not be compared with the survey data due to errors in the extraction software. Of the remaining 4, EHR data turned out to be both more complete for 3, and more correct for all 4, than survey data.

    “Data extraction from EHRs based on routine data collection of clinicians and patients provides the best opportunity for providing real-time feedback on process and outcomes of care,” according to co-author Philip van der Wees, PT, PhD, who is also a member of the Scientific Advisory Panel (SAP) for APTA’s Physical Therapy Outcomes Registry (Registry).

    He notes, “This interoperability between EHRs and national registries and other such possibilities are moving swiftly, as with APTA's Registry.” The Registry has completed its pilot testing phase, and is set to debut in early 2017.

    Operationalizing data extraction has its challenges. Authors of the study describe how they had to exclude some quality indicators because 2 of the EHR software vendors deviated from the uniform extraction algorithm, causing “errors in data extraction that further limited comparability” and blocking extraction of correct data.

    Authors also noted that differences in data completeness between 2 different vendors may be due to difference in user interface design, such as whether or not the software identifies missing values for the clinician.

    Another significant hurdle: extracting data from text boxes. Problems in this area highlight the need for “effective natural language processing tools” that can mine the text using a “dictionary” of common clinical terms, according to the study's authors (an example of a uniform dataset is the Registry’s lexicon in the Logical Observation Identifiers Names and Codes [LOINC] database). van der Wees explains that natural language processing technology can be valuable “for in-depth analysis of narrative text,” which is critical to understanding clinical reasoning.

    “Manual data entry is not sustainable,” says James J. Irrgang, PT, PhD, ATC, chair of the Registry's SAP. “Computer algorithms to extract and analyze quality improvement data may be a viable alternative to manual documentation and calculation of the quality indicators. This has the potential to broaden the adoption of the use of registries for quality improvement efforts, which in turn could lead to initiatives to improve the quality of care."

    Authors acknowledge that more needs to be done to "bridge the needs" of both clinicians using EHRs and the researchers hoping to analyze EHR data, but they believe standardization is key.

    "Standardization of the format of EHRs, the use of standardized coding and exploring text mining tools require a considerable effort from the physiotherapy community, researchers, and EHR developers," authors admit, but they assert that the payoff is considerable, allowing "continuous measurement of the quality of care, and for providing real-time feedback to all stakeholders."

    Research-related stories featured in PT in Motion News are intended to highlight a topic of interest only and do not constitute an endorsement by APTA. For synthesized research and evidence-based practice information, visit the association's PTNow website.


    • If you are experiencing these issues or if you have questions on how to improve your therapists productivity and/or your front desk efficiency contact me directly and I will be happy to discuss how we have been helping PT owners get ahead of the game. Marco Tosoni Director of Sales at Clinicient

      Posted by Marco Tosoni on 11/23/2016 6:44 PM

    Leave a comment
    Name *
    Email *