Table 2.
Subtopic | Measure | Medical Domain | Articles | Summary of Findings |
---|---|---|---|---|
Documentation time (n = 20) | Mean document creation time | Radiology | Vorbeck et al (2000)13 | 5 studies11,13,18,21,23 reported decreases in mean documentation time after SR adoption, ranging from 19%13 to 92%21; 4 studies10,22,24,29 recorded increases, ranging from 13.4%22 to 50%24, and 3 studies26–28 reported no statistically significant difference |
Rana et al (2005)18 | ||||
Bhan et al (2008)22 | ||||
Pezzullo et al (2008)24 | ||||
Hawkins et al (2012)26 | ||||
Hanna et al (2016)28 | ||||
Segrelles et al (2017)29 | ||||
Anesthesiology | Alapetite et al (2008)21 | |||
Dentistry | Feldman and Stevens (1990)10 | |||
Emergency department | dela Cruz et al (2014)27 | |||
Pathology | Klatt (1991)11 | |||
Unspecified | Gonzalez Sanchez et al (2008)23 | |||
Mean dictation and/or correction time | Pediatrics | Borowitz (2001)14 | All reported increases after SR adoption, ranging from 13.9%14 to 200%,17 although 119 reported decreases if the SR error rate was ≤ 16% | |
Issenman and Jaffer (2004)17 | ||||
Multiple | Monnich and Wetter (2000)12 | |||
Otorhinolaryngology | Ilgner et al (2006)19 | |||
Pathology | Al-Aynati and Chorneyko (2003)15 | |||
Hours of secretary work per minute of dictation processed | Multiple | Mohr et al (2003)16 | Secretaries were 55.8%–87.3% less productive with SR vs conventional transcription | |
Total documentation time | Radiology | Ichikawa et al (2007)20 | Decreased by 32.7–71.3% across 4 transcriptionists | |
Users’ perceptions of SR impact on document creation time | Psychiatry | Derman et al (2010)25 | No perceived benefit with SR vs other methods | |
Turnaround time (n = 19) | Mean turnaround time | Radiology | Rosenthal et al (1998)30 | All reported decreased turnaround times, ranging from 50.3%33 to nearly 100%41 |
Chapman et al (2000)31 | ||||
Lemme and Morin (2000)32 | ||||
Ramaswamy et al (2000)33 | ||||
Callaway et al (2002)34 | ||||
Langer (2002)35 | ||||
Langer (2002)36 | ||||
Gopakumar et al (2008)37 | ||||
Koivikko et al (2008)38 | ||||
Hart et al (2010)39 | ||||
Krishnaraj et al (2010)40 | ||||
Strahan and Schneider-Kolsky (2010)41 | ||||
Pathology | Kang et al (2010)42 | |||
Singh and Pal (2011)43 | ||||
Emergency department | Zick and Olsen (2001)44 | |||
Median, 80th percentile, and/or 95th percentile turnaround time | Radiology | Andriole et al (2010)45 | All reported decreases, ranging from 50%47 to 95.8%46 (for median turnaround times) | |
Prevedello et al (2014)46 | ||||
Pathology | Kang et al (2010)42 | |||
Sports medicine | Ahlgrim et al (2016)47 | |||
Minimum turnaround time | Radiology | Pavlicek et al (1999)48 | Decreased by 91.7% | |
Documentation-associated cost(n = 8) | Change in cost over time | Radiology | Rosenthal et al (1998)30 | 5 studies30,33,34,50,51 overall decreases in documentation-associated costs following SR introduction; 217,24 reported increases; the remaining study49 involved the development of an econometric model for estimating the impact of SR and transcription on cost |
Ramaswamy et al (2000)33 | ||||
Callaway et al (2002)34 | ||||
Reinus (2007)49 | ||||
Pezzullo et al (2008)24 | ||||
Orthopedics | Corces et al (2004)50 | |||
Pathology | Henricks et al (2002)51 | |||
Pediatrics | Issenman and Jaffer (2004)17 | |||
Other(n = 7) | Reports completed per time period | Radiology | Strahan and Schneider-Kolsky (2010)41 | Ranged from a 41% increase52 to a 35% decrease41 |
Williams et al (2013)52 | ||||
Report availability | Radiology | Hayt and Alexander (2001)53 | Percentage of reports available within 12 h of dictation increased from 3% to 42% | |
Mean characters per minute | Multiple | Vogel et al (2015)54 | Increased from 173 to 217 with SR vs with typing | |
Mean length of stay | Emergency department | Lo et al (2015)55 | Temporarily increased by 9.3%, then settled to a new baseline of 4.3% longer | |
Mean report length | Radiology | Kauppinen et al (2013)56 | 433 characters and 11 character corrections per report for new SR users vs 298 and 6 character corrections characters per report for experienced users | |
Mean task completion time | Emergency department | Hodgson et al (2017)57 | 18.11% slower with SR vs keyboard and mouse; 16.95% slower for simple tasks, 18.40% slower for complex tasks |
: speech recognition.