viernes, 16 de septiembre de 2016

AHRQ Study Estimates Frequency of Errors When Speech Recognition Technology Is Used To Enter Patient Data

Critical errors were found in 15 percent of data entered into patients’ electronic health records by physicians using computerized speech recognition technology, according to a pilot study funded by AHRQ. The study evaluated front-end speech recognition technology that allows dictation and editing in an electronic record’s text field. The study examined speech recognition errors based on 100 patient notes by attending emergency department physicians in Boston from January to June 2012. Findings showed that there were 128 errors, or 1.3 errors per note, and that of the 71 percent of notes that contained errors, 15 percent contained one or more critical errors that could potentially lead to miscommunication affecting patient care. Annunciation errors were most common, followed by deletions and added words. Study findings represent the first estimates of speech recognition errors in dictated emergency department notes, researchers said. The study, “Incidence of Speech Recognition Errors in the Emergency Department,” andabstract were published in the International Journal of Medical Informatics.

Incidence of speech recognition errors in the emergency department. - PubMed - NCBI

2016 Sep;93:70-3. doi: 10.1016/j.ijmedinf.2016.05.005. Epub 2016 May 26.

Incidence of speech recognition errors in the emergency department.

Goss FR1, Zhou L2, Weiner SG3.

Author information

Abstract

BACKGROUND:

Physician use of computerized speech recognition (SR) technology has risen in recent years due to its ease of use and efficiency at the point of care. However, error rates between 10 and 23% have been observed, raising concern about the number of errors being entered into the permanent medical record, their impact on quality of care and medical liability that may arise. Our aim was to determine theincidence and types of SR errors introduced by this technology in the emergency department (ED).

SETTING:

Level 1 emergency department with 42,000 visits/year in a tertiary academic teaching hospital.

METHODS:

A random sample of 100 notes dictated by attending emergency physicians (EPs) using SR software was collected from the ED electronic health record between January and June 2012. Two board-certified EPs annotated the notes and conducted error analysis independently. An existing classification schema was adopted to classify errors into eight errors types. Critical errors deemed to potentially impact patient care were identified.

RESULTS:

There were 128 errors in total or 1.3 errors per note, and 14.8% (n=19) errors were judged to be critical. 71% of notes contained errors, and 15% contained one or more critical errors. Annunciation errors were the highest at 53.9% (n=69), followed by deletions at 18.0% (n=23) and added words at 11.7% (n=15). Nonsense errors, homonyms and spelling errors were present in 10.9% (n=14), 4.7% (n=6), and 0.8% (n=1) of notes, respectively. There were no suffix or dictionary errors. Inter-annotator agreement was 97.8%.

CONCLUSIONS:

This is the first estimate at classifying speech recognition errors in dictated emergency department notes. Speech recognitionerrors occur commonly with annunciation errors being the most frequent. Error rates were comparable if not lower than previous studies. 15% oferrors were deemed critical, potentially leading to miscommunication that could affect patient care.