A small study found a significantly higher rate of transcription errors in women compared with men using a commercial voice recognition application. Causes of the discrepancy may include the differences in the volume and frequency of speech between sexes or more fundamental differences in how the application was tested at time of development.
A small study found a significantly higher rate of transcription errors in women compared with men using a commercial voice recognition application. Causes of the discrepancy may include the differences in the volume and frequency of speech between sexes or more fundamental differences in how the application was tested at time of development.
Dr. Syed Mahmood Ali, a radiology resident at the University of Maryland Medical Center, and colleagues trained five male and five female radiology residents on a speech recognition system. They asked each resident to dictate a standardized set of 10 radiology reports containing a total of 2123 words. The generated reports were compared with the original reports, and error rates were calculated. Researchers defined the error rate as the sum of the number of word insertions and deletions divided by the total word count for a given report.
Error rates in the male population ranged from 0.025 to 0.139, with a mean of 0.082. Error rates in the female population ranged from 0.015 to 0.206, with a mean of 0.100.
"These error rates may have significant negative impact on reporting accuracy and output, disproportionately affecting female radiologists," Ali reported at the American Roentgen Ray Society meeting.
Breast MRI and Background Parenchymal Enhancement: What a Meta-Analysis Reveals
May 29th 2025Moderate or marked background parenchymal enhancement (BPE) reduces the sensitivity and specificity of MRI for breast cancer detection by more than 10 percent in comparison to scans with minimal or mild BPE, according to a new meta-analysis.
Lunit Unveils Enhanced AI-Powered CXR Software Update
May 28th 2025The Lunit Insight CXR4 update reportedly offers new features such as current-prior comparison of chest X-rays (CXRs), acute bone fracture detection and a 99.5 percent negative predictive value (NPV) for identifying normal CXRs.