Re: 'frequency and spectrum of errors in final radiology reports generated with automatic speech recognition technology'.

摘要

Peter Marcovici, MD, [1], a resident at the University of California; San Diego, is to be complimented on his letter to the editor in the April issue of JACR. In his analysis of the use of voice recognition in the dictation of radiologic reports: Dr Marcovici found numerous reasons not to endorse this form oi dictation. However, I do have several unanswered questions for him, First, considering that he found errors in 90% of voice-generated reports, is it possible that the system in use at his institution is less than optimal?