rss
J Am Med Inform Assoc 10:85-93 doi:10.1197/jamia.M1130
  • Original Investigation

Speech Recognition as a Transcription Aid: A Randomized Comparison With Standard Transcription

Table 1

Productivity for Speech Recognition Versus Standard Transcription in Three Groups and Selected Subsets

Endocrinology secretaries Psychiatry transcriptionists Psychiatry secretaries
Variable n1 n2 Productivity (95% CI), %* n1 n2 Productivity (95% CI), %* n1 n2 Productivity (95% CI), %*
All dictation jobs 1,301 1,053 87.3 (83.3, 92.3) 220 123 63.3 (54.0, 74.0) 244 111 55.8 (44.6, 68.0)
Work type
 1 169 134 84.2 (75.0, 94.8) NA NA NA NA NA NA
 2 142 138 89.2 (79.8, 99.1) NA NA NA NA NA NA
 3 362 328 102.5 (93.5, 115.6) NA NA NA NA NA NA
 4 326 210 82.5 (73.3, 92.4) NA NA NA NA NA NA
 14 302 243 73.2 (65.4, 80.5) NA NA NA NA NA NA
Slow secretaries or transcriptionists 645 522 104.6 (100.0, 109.4) 138 63 93.6 (85.4, 101.0) 114 27 88.6 (73.6, 102.3)
Selected authors only 981 796 86.6 (81.7, 93.0) 172 93 61.6 (50.9, 73.6) 200 88 52.6 (39.3, 65.0)
Jobs > 3 min in dictation length 706 625 97.1 (90.1, 105.1) 190 106 52.8 (41.7, 64.1) 178 86 60.5 (46.6, 74.7)
  • CI, confidence interval; n1, number of dictated jobs using speech recognition; n2, number of dictated jobs using standard transcription; NA, not applicable.

  • * Productivity for speech recognition as a percentage of productivity for standard transcription.

This Article

Access policy for JAMIA

All content published in JAMIA is deposited with PubMed Central by the publisher with a 12 month embargo. Authors/funders may pay an Unlocked fee of $2,000 to make the article free on the JAMIA website and PMC immediately on publication.

All content older than 12 months is freely available on this website.

AMIA members can log in with their JAMIA user name (email address) and password or via the AMIA website.