Electronic Health Records

Adoption & Implementation News

Does Speech Recognition Aid Clinical Documentation Improvement?

A review of literature on speech recognition shows mixed results for clinical documentation improvement.

By Kyle Murphy, PhD

- Despite the availability of speech recognition software and natural language processing over the past two decades, research shows limited evidence proving these technologies to have a clearly positive impact on clinical documentation improvement.

Speech recognition for clinical documentation improvement

That conclusion comes from a systematic review of literature on the risks and benefits of speech recognition for clinical documentation by Tobias Hodgson and Enrico Coiera published recently in the Journal of the American Medical Informatics Association.

"SR is a widely used input modality for modern computer devices and has a long pedigree in the clinical setting," Hodgson and Coiera write. "Surprisingly, our review revealed that the evidence base documenting the benefits and limitations of SR’s use for clinical documentation is limited, incomplete, and relatively neutral to its benefits. Recent studies, which would benefit from more modern SR technologies, are absent."

The team of researchers pared the number of studies down from 538 to 23, which comprise the focus of their quantitative and qualitative analysis, spanning from the efficiency and accuracy of speech recognition to errors introduced by speech recognition and the cost–benefit of speech recognition.

  • Why Prioritizing Usability Effects Better Ambulatory EHR Use
  • Telemedicine, remote monitoring set to hit $296.5M in 2019
  • Why do Medicaid providers struggle with meaningful use?
  • How does provider-developer collaboration improve health IT?
  • ICD-10 checkpoint: New codes are only one year away
  • Epic Systems Expands CVS Health Partnership to Lower Drug Costs
  • ONC: EHR Vendor Competition Will Lead to Interoperability
  • AMA continues ICD-10 opposition despite looming deadline
  • ONC explores Blue Button access for immunization records
  • Effects of Provider Consolidation on EHR Integration Efforts
  • Certified EHR: Breaking down the ONC fact sheet
  • Meaningful Use Hardship Exceptions Bill Signed into Law
  • The ‘Heart’ of Stage 3 Meaningful Use Requirements
  • Study highlights rise in US healthcare costs since 1980
  • How healthcare M&A push consumer-centric, value-based care
  • Health literacy level affects patients’ decision to use PHR technology
  • Ambulatory providers need better ambulatory EHR systems
  • Technology users remember their priorities during EHR implementation
  • ONC Embraces Industry-led Testing of Health IT Tools
  • Health IT Benchmarking Tool Gives New Insights to Providers
  • Microsoft Surface dives into mHealth, telehealth tablet market
  • ICD-10 Best Practices: Education and training
  • EHR implementation in a smaller hospital: A case study
  • New initiative aims at integrating EMS into healthcare IT
  • How Does Physician EHR Use Affect Doctor-Patient Relationship?
  • AMA Sees Trouble in Departures of DeSalvo, Reider from ONC
  • EHR best practices: Considering a new EHR vendor, system
  • HIMSS, EHRA add to the chorus of Stage 3 Meaningful Use comments
  • MO Coalition Selects Netsmart for Population Health Management
  • FDA Expands EHR Data Analytics with Active Surveillance System
  • Florida Blue, Baptist Health Quality Network expand ACO
  • Testing, Certification to Drive Healthcare Interoperability
  • Meaningful Measures Initiative to Focus on Care Quality Measures
  • How a Lack of EHR Interoperability Hinders Care Coordination
  • CMS Updates Electronic Clinical Quality Measure Value Sets
  • Mobile EHR: Four important considerations
  • 90% of WI patients may receive accountable care with new pact
  • ONC Chief Emphasizes Commitments Toward Connected Health IT
  • Is interoperability plagued by a lack of limits, pragmatism?
  • Should Patient-Reported Outcomes Be Incorporated in EHRs?
  • Most Challenging Stage 3 Meaningful Use Requirements
  • Slavitt Addresses How MACRA Implementation Supports Medicare
  • OIG report shows EHR use by physicians
  • Health IT Vendors Urge HELP Committee to Pass MEDTECH Act
  • mHealth, EHR startups win $100K prizes in Maryland
  • Health IT Standards Needed to Support Precision Medicine
  • DOD isn’t ready to let go of legacy EHR just yet
  • Kaiser Permanente links DNA with EHR to identify health trends
  • Maine to assist veterans through health information exchange
  • Can Human-Centered HIT Design Improve Patient Engagement?
  • Integration of Outsiders’ Data Highly Problematic for ACOs
  • CMS Approves ASCP for Qualified Clinical Data Registry Status
  • AMA continues protest against ICD-10 implementation
  • Phoenix VA subverts EHR system with secret waiting list
  • EHR and the VA: Part I - History
  • GAO Appoints 3 New Members to Health IT Policy Committee
  • Data breaches of EHRs underscore need to upgrade systems and adapt to changing times
  • E-Health Records Don’t Always Equal Reduced Costs
  • EHR Adoption Positively Impacts Nurses, Clinical Workflows
  • Virtual Clipboard Takes on Healthcare IT Interoperability
  • Hospital Stage 2 Meaningful Use Attestations Double Up
  • Recent Agreements to Extend Cerner EHR, RCM Technology
  • OSEHRA & EHR: Finding value in open source EHR
  • Allscripts Launches EHR-Integrated Lyft Transportation Service
  • Medium, small hospital EHR to benefit from Dell-Epic DRIVE
  • VA pilot brings together mHealth and EHRs for better care
  • Meaningful Use Hardship Exemptions Requests Approach 44,000
  • Telehealth law to create federal definition, provide guidance
  • AHA challenges proposed Stage 2 rule
  • Senators Request Timeline for VA Cerner EHR Implementation
  • States Make Connection for Health Information Exchange
  • E-prescribing rises dramatically as providers adopt EHRs
  • How Health IT Integration Can Help Reduce Diagnostic Errors
  • WPI Receives $5 million for Health IT Innovation Initiative
  • Army Upgrades EHR System; VA Hopes to Add More Telehealth
  • EHR open notes: Should parents have access to teens’ PHI?
  • Shulkin Details Planned 2018 VA EHR Modernization Activities
  • Hospitals must attest to meaningful use by November 30
  • Patient Engagement, mHealth among Top Health Issues in 2015
  • What will the Supreme Court’s ruling mean for your EHR initiative?
  • UConn retools med school to focus on EHRs, healthcare reforms
  • RECs have aided 100,000 providers with EHRs, meaningful use
  • EHR nightmares: When EHR adoption, implementation run awry
  • Medicare 30-day readmission penalties sting hospitals
  • 78% of physicians copy and paste significant portions of progress notes
  • Yale to Integrate State Prescription Drug Data into Epic EHR
  • Medical Data Exchange, Cloud Solutions Impact EHR Design
  • VT to spend $427M on health IT; won’t expect ROI for a decade
  • Verizon telehealth connects specialists to developing nations
  • Study: Showing lab costs in the EHR can save money
  • Is Penalty Phase Under Meaningful Use Requirements Fair?
  • Do EHR Systems Improve Doctor-Patient Relationship?
  • ICD-10 survey: Vendors, payers barely creep towards readiness
  • Epic EHR Replacement Success at Lovelace Health System
  • First Two Data Registries Accredited for Handling PHI
  • Surescripts saw 32% growth in e-prescriptions in 2013
  • 65% of patients think mHealth would keep them healthier
  • Half of Medical Providers Lack EHR Interoperability Roadmap
  • Study reveals prevailing lack of HIE sustainability
  • AMA supports SGR repeal, merit-based incentive system
  • The authors did note evidence supporting system-level benefits for improving clinical documentation speed in "dramatic reductions" to turnaround time (TAT) for report creation, but they exercise caution in divining the meaning of these findings:

    This is mainly due to the virtually instant delivery of reports possible with SR based systems. This improvement hides an editing and document creation time cost that falls directly on the clinician. The effective clinical adoption of technologies often depends on local costs being offset by local benefits, and the relatively low uptake of SR to date might in part be due to an imbalance in cost over benefit for the clinician preparing reports.

    Improved accuracy was another win for speech recognition in the systematic literature review. Yet the margins for error in medicine make the less-than-100-percent accuracy of this technology still problematic, according to Hodgson and Coiera.

    "In fact many SR software developers now claim accuracy rates of up to 99%," they state. "However, high accuracy rates do not necessarily mean that SR is clinically safe, and several studies have reported a range of errors, some of which are clinically significant and could lead to patient harm."

    Numerous errors are listed in the review:

    • Creating documentation for the wrong patient
    • Wrong drug name or dosage
    • Wrong lab values
    • Left/right anatomical discrepancy
    • Medical discrepancy
    • Age or gender mismatch
    • Wrong doctor name
    • Wrong date
    • Made up words and acronyms
    • Irregular spacing
    • Spelling errors, omissions, or duplications

    In the review, the researchers also call attention to a lack of data identifying the numerous variables having an effect on speech recognition (e.g., user training, environmental conditions).

    "In the absence of such data, there is the need to cautiously generalize the performance reported in these studies to expected real world performance. In other words, good performance under controlled conditions may not be replicated in clinical settings," they maintain.

    Hodgson and Coiera list six areas for future research to focus on to evaluate the merits of using speech recognition for clinical documentation improvement:

    • Impact on clinical processes and outcomes
    • Impact on clinicians
    • Impact on patient safety
    • Comparative effectiveness
    • Effectiveness for non-documentation tasks
    • Alternate input platforms

    Recently, CHRISTUS Health in Texas shared details about its recent initiative to improve the quality of clinical documentation by implementing health IT from Nuance — both a quality reporting system for radiologists with speech recognition and natural language processing technology for providers in ambulatory and inpatient settings.

    According to CMIO Luke Webster, tangible benefits are already emerging in the form of reducing turnaround times and quality reporting such as reducing the duration for issuing an imaging order and receiving an official sign-off from providers. “That has improved substantially,” said Webster.

    And the health system is eagerly awaiting more.

    “One of the hopes (and obviously the plans that we have in place) is to leverage that foundational technology to improve clinical documentation real-time, such as prompting providers as they document,” added Webster.



    Sign up to continue reading and gain Free Access to all our resources.

    Sign up for our free newsletter and join 60,000 of
    your peers to stay up to date with tips and advice on:

    EHR Optimization
    EHR Interoperability
    EHR Replacement

    White Papers, Webcasts, Featured Articles and Exclusive Interviews

    Our privacy policy

    no, thanks

    Continue to site...