Page 34 - Part Two Risk Reduction Series - Documentation

SVMIC Risk Reduction Series: Documentation

health care organizations using Dragon Medical 360 | eScription

(Nuance). Errors were annotated in the SR engine–generated

document (SR), the medical transcriptionist–edited document
(MT), and the physician’s signed note (SN). Each document was

compared with a criterion standard created from the original audio

recordings and medical record review.

The error rate was 7.4% in the version generated by speech

recognition software, 0.4% after transcriptionist review, and 0.3%
in the final version signed by physicians.

Among the errors at each stage, 15.8%, 26.9%, and 25.9% involved

clinical information, and 5.7%, 8.9%, and 6.4% were clinically

significant, respectively. An observed error rate of more than 7% in

speech recognition– generated clinical documents demonstrates

the importance of manual editing and review. The study concluded
that “…Seven in 100 words in SR-generated documents contain

errors; many errors involve clinical information. That most errors

are corrected before notes are signed demonstrates the

importance of manual review, quality assurance, and auditing.”

A disclaimer as to the accuracy of the note should never replace a

thorough review of the record. Some clinicians desire to warn

subsequent providers about the potential for inaccuracy when

using speech recognition software or other engine-generated

transcription tools by including a “disclaimer” with the note such
as:

 “Dictated but not read”

 “Signed but not read”

Page | 34