{ Voice Recognition Efficiency in Internal Medicine Documentation Internal Medicine Noon Conference – Samuel Ash, MD Resident, Department of Internal Medicine University of Washington Medical Center
Problem Technology Experience Conclusions/Discussion References Demonstration Other Strategies Outline
Saturday call… 30 hours 10 patient 7 admits 3 forms per admit Untold number of pages… Problem
Technology An early 20th century transcribing pool at Sears, Roebuck and Co. The women are using cylinder dictation machines, and listening to the recordings with ear-tubes (David Morton, the history of Sound Recording History,
Technology
Technology
Outpatient Pediatric Specialty Practice 2 hours of training + 30 “training” notes 42 “test” notes Endpoints: time and accuracy Experience
Experience
Experience
Additional Results 600 new consultations and 1200 repeat visits per year Average letter/note length 225 words Experience
Advantages Average turnaround time 1 day vs. 1 week Disadvantages 66% less efficient in total time VRS cost twice as much as traditional transcription (based on attending hourly rate) Experience
Surgical Pathology Decreased turnaround times (by ~81%) Decreased error rate (by ~48%) Experience
Conclusions/Discussion
Davis KH, Biddulph R and Balashek S, Automatic recognition of spoken digits. J. Acoust. Soc. Am. 1952; 24: Issenman RM and Jaffer IH. Use of voice recognition software in an outpatient pediatric specialty service. Pediatrics 2004; 114:e290-e293. Juang BH and Rabiner LR. Automatic Speech Recognition – A Brief History of the Technology Development. Kang HP, Sirintrapun J, Nestler RJ and Parwani AV. Experience with voice recognition in surgical pathology at a large academic multi-institutional center. Anatomic Pathology 2010; 133: References
Demonstration
Other Strategies