Close Server: KOPWWW05 | Not logged in

AHDI Track

Deploying Back-End Speech Recognition

AHDI releases best practices toolkit for healthcare organizations.

In August 2016, the Association for Healthcare Documentation Integrity (AHDI) released the Back-end Speech Recognition Implementation Best Practices Toolkit.  

According to the AHDI website, the toolkit outlines how successful implementation of BESR is dependent upon a carefully orchestrated plan of action from the start, with ongoing measurements being monitored in the post go-live environment so challenges can be addressed as soon as possible for continued best results.1

Wise implementation of BESR systems can lead to increased productivity, improved turnaround, decreased costs, and a satisfactory new production environment for the entire healthcare documentation team.

Patt King, manager of HIM Transcription for Tucson Medical Center, served as co-chair of the AHDI task force that created the BESR Implementation Best Practices Toolkit.  When asked what instigated the formation of the task force and the resulting toolkit, she explained that AHDI's BESR toolkit "was actually born out of AHDI's Compensation Best Practices Toolkit, which was rolled out in the summer of 2015.  

"During the many hours of discussion leading to the compensation toolkit, members spoke often and passionately about how speech recognition, when not implemented thoughtfully, had created numerous challenges for both healthcare documentation management and HDS (healthcare documentation specialist) staff," she added.
Another task force member, Dori Whittaker, Director of Solutions Management, Transcription Solutions, for M*Modal, agreed there was a need for this type of toolkit. "There have been a lot of questions related to industry standards on productivity when editing back-end speech-recognized text" she said. "It's no wonder this information has been hard to find as not all back-end speech systems are the same, and there was a need to provide education on the various aspects of evaluating these systems.

 "More importantly, though, it was the mixed reviews sometimes attributed to BESR platforms due to failed savings, low staff morale, and reduced quality in patients' healthcare records that inspired this undertaking," King added. "The purpose of the BESR Implementation Best Practices Toolkit is to help make organizations and businesses that want to invest in this technology aware of the complexities of such a project so they will have a successful outcome."  

In-Depth Information & Best Practices

This toolkit draws on the experiences of numerous healthcare organizations that have successfully implemented back-end speech recognition as well as some that were less successful but able to provide much-needed insight, solutions and workarounds. The toolkit provides in-depth information and best practices to guide healthcare organizations through the implementation of back-end speech recognition technology. What could be seen as a long and arduous process is made easier with detailed instructions to ensure organizational readiness and good implementation planning and execution, as well as steps to evaluate progress post-implementation.

The BESR toolkit can be helpful and used by more than transcription personnel, e.g., physicians, hospital administration, MTSOs, HIM managers, and Human Resources.  Whittaker said.  

"The information included in this toolkit will be very helpful in many ways including being able to make data-driven decisions about which system to go with so that the organization's cost reduction goals are achieved," she explained.  "Often it is not clear how to get to this level of detail and be knowledgeable enough about the different components that can drive the organization toward these goals. IT departments will also find this helpful from a perspective of knowing what system (hosted or premise-based) and support model would be the best fit for the organization."  

Added King: "Human Resources will likely be involved at some point during an implementation, if only because the job descriptions of the HDS staff may need to be adjusted to include editing of back-end speech-recognized draft text.  And, while it is not a practice that I believe maintains excellent quality in healthcare documentation, some organizations do choose to off-board their HDS staff as a part of, or subsequent to, implementation of BESR.  In this case, HR is a vital part of appropriately caring for one's staff."  

Achieving Successful Outcomes

The toolkit provides tips on how to use the materials provided to determine how best to approach speech recognition for a successful outcome.  Materials downloadable from the AHDI website ( include a sample RFP, sample project implementation plan, sample reference survey checklist, application and relevance whitepaper, sample scorecard, and more.1

When asked which aspect of the toolkit she considered most significant or helpful, Whittaker replied, "Especially helpful is the information on how editing of back-end speech-recognized text can vary so much between HDS resources from a productivity perspective.  It's not a one-metric-fits-all model.  It's so important to consider the impact on each staff member, as high producers may not necessarily have the same percentage gains when editing versus transcribing from scratch as others that may be low to moderate producers."  

King pointed out that what she considers "most beneficial about the toolkit is that it was compiled from many different perspectives so that virtually all elements of the healthcare documentation process are considered throughout.  The task force included a former director of corporate transcription, two transcription managers who had been HDSs themselves, QA and training staff (also HDSs), representatives from two leading vendors, tech support, and an AHDI Board liaison.  The goal was to create a toolkit that would benefit everyone who needs it, providing as much information as possible."  

Successful implementation of speech recognition technology requires in-depth study and careful consideration of overall goals and needs from C-suite to end user. AHDI's Back-end Speech Recognition Implementation Best Practices Toolkit helps achieve that success.

Lynette Shipp currently serves as an At-large Director on the AHDI National Leadership Board. She is a Medical Language Specialist IV and Transcription Team Lead for the University of Arkansas for Medical Sciences in Little Rock and has been in the healthcare documentation industry for more than 30 years.

1. Association for Healthcare Documentation Integrity. "Back-end Speech Recognition Implementation Best Practices." Accessed Aug. 7, 2016.

AHDI Track Archives


Email: *

Email, first name, comment and security code are required fields; all other fields are optional. With the exception of email, any information you provide will be displayed with your comment.

First * Last
Title Field Facility
City State

Comments: *
To prevent comment spam, please type the code you see below into the code field before submitting your comment. If you cannot read the numbers in the below image, reload the page to generate a new one.

Enter the security code below: *

Fields marked with an * are required.

View New Jobs, Events and More


Back to Top

© 2017 ADVANCE Healthcare, an Elite CE company