Speech recognition for clinical documentation from 1990 to 2018: a systematic review.

OBJECTIVE: The study sought to review recent literature regarding use of speech recognition (SR) technology for clinical documentation and to understand the impact of SR on document accuracy, provider efficiency, institutional cost, and more. MATERIALS AND METHODS: We searched 10 scientific and medical literature databases to find articles about clinician use of SR for documentation published between January 1, 1990, and October 15, 2018. We annotated included articles with their research topic(s), medical domain(s), and SR system(s) evaluated and analyzed the results. RESULTS: One hundred twenty-two articles were included. Forty-eight (39.3%) involved the radiology department exclusively and 10 (8.2%) involved emergency medicine; 10 (8.2%) mentioned multiple departments. Forty-eight (39.3%) articles studied productivity; 20 (16.4%) studied the effect of SR on documentation time, with mixed findings. Decreased turnaround time was reported in all 19 (15.6%) studies in which it was evaluated. Twenty-nine (23.8%) studies conducted error analyses, though various evaluation metrics were used. Reported percentage of documents with errors ranged from 4.8% to 71%; reported word error rates ranged from 7.4% to 38.7%. Seven (5.7%) studies assessed documentation-associated costs; 5 reported decreases and 2 reported increases. Many studies (44.3%) used products by Nuance Communications. Other vendors included IBM (9.0%) and Philips (6.6%); 7 (5.7%) used self-developed systems. CONCLUSION: Despite widespread use of SR for clinical documentation, research on this topic remains largely heterogeneous, often using different evaluation metrics with mixed findings. Further, that SR-assisted documentation has become increasingly common in clinical settings beyond radiology warrants further investigation of its use and effectiveness in these settings.

The use of an automated interactive voice response system to manage medication identification calls to a poison center.

INTRODUCTION: In 2007, medication identification requests (MIRs) accounted for 26.2% of all calls to U.S. poison centers. MIRs are documented with minimal information, but they still require an inordinate amount of work by specialists in poison information (SPI). An analysis was undertaken to identify options to reduce the impact of MIRs on both human and financial resources. METHODS: All MIRs (2003-2007) to a certified regional poison information center were analyzed to determine call patterns and staffing. The data were used to justify an efficient and cost-effective solution. RESULTS: MIRs represented 42.3% of the 2007 call volume. Optimal staffing would require hiring an additional four full-time equivalent SPI. An interactive voice response (IVR) system was developed to respond to the MIRs. DISCUSSION: The IVR was used to develop the Medication Identification System that allowed the diversion of up to 50% of the MIRs, enhancing surge capacity and allowing specialists to address the more emergent poison exposure calls. This technology is an entirely voice-activated response call management system that collects zip code, age, gender and drug data and stores all responses as .csv files for reporting purposes. The query bank includes the 200 most common MIRs, and the system features text-to-voice synthesis that allows easy modification of the drug identification menu. Callers always have the option of engaging a SPI at any time during the IVR call flow. CONCLUSIONS: The IVR is an efficient and effective alternative that creates better staff utilization.

[Digital speech recognition in dermatology: a pilot study with regard to medical and economic aspects]. / Digitale Spracherkennung in der Dermatologie: Eine Pilotuntersuchung unter medizinisch-ökonomischen Gesichtspunkten.

BACKGROUND: Economic factors dominate more and more the healthcare systems; modern technologies advance every day and offer opportunities for savings. MATERIAL AND METHODS: In a pilot study, digital speech recognition based on Dragon NaturallySpeaking, Version 7 was compared with common dictation in dermatology. RESULTS: The conventional method took 24.1 minutes per page and reports could be sent out after 16.8 days; in sharp contrast, the reports dictated by digital speech recognition took 15.8 minutes per page and were sent out after 3.2 days. CONCLUSION: Digital Speech recognition in dermatology has advantages compared to ordinary dictation, if the dictating person is trained with the software and it is implemented in a digital patient documentation system.

Use of voice recognition software in an outpatient pediatric specialty practice.

BACKGROUND: Voice recognition software (VRS), with specialized medical vocabulary, is being promoted to enhance physician efficiency, decrease costs, and improve patient safety. This study reports the experience of a pediatric subspecialist (pediatric gastroenterology) physician with the use of Dragon Naturally Speaking (version 6; ScanSoft Inc, Peabody, MA), incorporated for use with a proprietary electronic medical record, in a large university medical center ambulatory care service. METHODS: After 2 hours of group orientation and 2 hours of individual VRS instruction, the physician trained the software for 1 month (30 letters) during a hospital slowdown. Set-up, dictation, and correction times for the physician and medical transcriptionist were recorded for these training sessions, as well as for 42 subsequently dictated letters. Figures were extrapolated to the yearly clinic volume for the physician, to estimate costs (physician: 110 dollars per hour; transcriptionist: 11 dollars per hour, US dollars). RESULTS: The use of VRS required an additional 200% of physician dictation and correction time (9 minutes vs 3 minutes), compared with the use of electronic signatures for letters typed by an experienced transcriptionist and imported into the electronic medical record. When the cost of the license agreement and the costs of physician and transcriptionist time were included, the use of the software cost 100% more, for the amount of dictation performed annually by the physician. CONCLUSIONS: VRS is an intriguing technology. It holds the possibility of streamlining medical practice. However, the learning curve and accuracy of the tested version of the software limit broad physician acceptance at this time.