Reports generated from automated speech recognition technology are associated with higher error rates than reports from conventional dictation transcription, according to a study published in American Journal of Roentgenology.
Researchers studied breast imaging reports that were reviewed for errors from Jan. 2009-April 2010 during multidisciplinary tumor board meetings at two hospitals. At least one major error was found in 23 percent of automated speech recognition reports but in only 4 percent of conventional dictation transcription reports.
After adjusting for academic rank, native language and imaging modality, results showed that reports generated with automated speech recognition were eight times more likely than conventional dictation transcription reports to contain major errors.
North Carolina Rep. Renee Ellmers Requests HHS Study Health IT Adoption, Medical Error Rates
Study: Duplicate Medical Errors Increased After Implementation of CPOE With Clinical Decision Support
Researchers studied breast imaging reports that were reviewed for errors from Jan. 2009-April 2010 during multidisciplinary tumor board meetings at two hospitals. At least one major error was found in 23 percent of automated speech recognition reports but in only 4 percent of conventional dictation transcription reports.
After adjusting for academic rank, native language and imaging modality, results showed that reports generated with automated speech recognition were eight times more likely than conventional dictation transcription reports to contain major errors.
Related Articles on Health IT and Errors:
Lack of Patient ID Standards Results in Patient Safety ExposuresNorth Carolina Rep. Renee Ellmers Requests HHS Study Health IT Adoption, Medical Error Rates
Study: Duplicate Medical Errors Increased After Implementation of CPOE With Clinical Decision Support
Study: Errors 8 Times More Likely in Automated Speech Recognition Reports
Reports generated from automated speech recognition technology are associated with higher error rates than reports from conventional dictation transcription, according to a study (pdf) published in American Journal of Roentgenology.
http://www.ajronline.org/content/197/4/923.full.pdf+html
Researchers studied breast imaging reports that were reviewed for errors from Jan. 2009-April 2010 during multidisciplinary tumor board meetings at two hospitals. At least one major error was found in 23 percent of automated speech recognition reports but in only 4 percent of conventional dictation transcription reports.
After adjusting for academic rank, native language and imaging modality, results showed that reports generated with automated speech recognition were eight times more likely than conventional dictation transcription reports to contain major errors.
Related Articles on Health IT and Errors:
Lack of Patient ID Standards Results in Patient Safety Exposures
https://www.beckershospitalreview.com/healthcare-information-technology/lack-of-patient-id-standards-results-in-patient-safety-exposures.html
North Carolina Rep. Renee Ellmers Requests HHS Study Health IT Adoption, Medical Error Rates
https://www.beckershospitalreview.com/healthcare-information-technology/north-carolina-rep-renee-ellmers-requests-hhs-study-health-it-adoption-medical-error-rates.html
Study: Duplicate Medical Errors Increased After Implementation of CPOE With Clinical Decision Support
https://www.beckershospitalreview.com/healthcare-information-technology/study-duplicate-medical-errors-increased-after-implementation-of-cpoe-with-clinical-decision-support.html
Reports generated from automated speech recognition technology are associated with higher error rates than reports from conventional dictation transcription, according to a study (pdf) published in American Journal of Roentgenology.
http://www.ajronline.org/content/197/4/923.full.pdf+html
Researchers studied breast imaging reports that were reviewed for errors from Jan. 2009-April 2010 during multidisciplinary tumor board meetings at two hospitals. At least one major error was found in 23 percent of automated speech recognition reports but in only 4 percent of conventional dictation transcription reports.
After adjusting for academic rank, native language and imaging modality, results showed that reports generated with automated speech recognition were eight times more likely than conventional dictation transcription reports to contain major errors.
Related Articles on Health IT and Errors:
Lack of Patient ID Standards Results in Patient Safety Exposures
https://www.beckershospitalreview.com/healthcare-information-technology/lack-of-patient-id-standards-results-in-patient-safety-exposures.html
North Carolina Rep. Renee Ellmers Requests HHS Study Health IT Adoption, Medical Error Rates
https://www.beckershospitalreview.com/healthcare-information-technology/north-carolina-rep-renee-ellmers-requests-hhs-study-health-it-adoption-medical-error-rates.html
Study: Duplicate Medical Errors Increased After Implementation of CPOE With Clinical Decision Support
https://www.beckershospitalreview.com/healthcare-information-technology/study-duplicate-medical-errors-increased-after-implementation-of-cpoe-with-clinical-decision-support.html