Managing Clinical Documentation
Dr Nick van Terheyden
Chief Medical Officer, Philips Speech Recognition Systems
Documentation is the lifeblood of healthcare; without it, there is no accurate communication between the various members of a healthcare team. However, it’s a familiar story throughout the healthcare institutions in the UK – essential medical reports delayed for days and in some cases weeks, awaiting transcription by overworked medical secretaries.
Medicine used to be all about patients seeing their local GP and getting the treatment they needed. But the number of specialties and sub-specialties has mushroomed and we now need to see several different doctors for a diagnosis and to obtain the best possible treatment. This requires more documentation.
Cassette-based dictation has served doctors well for many years. But with accurate healthcare speech recognition now available, that model is changing, driven by the need to accelerate document turnaround times.
“Best use of e-health to improve efficiency”
This was the motivation behind integrating speech recognition in the Radiology Management System (RMS) at the Diana Princess of Wales Hospital in Grimsby, Humberside. Radiologists now dictate, edit and sign-off the reports themselves - without the need for secretarial assistance. Average time from examination to report authorisation has been reduced from 17.66 days to 4.56 days – an efficiency increase of 74%.
This achievement prompted E-Health Insider to award Diana Princess of Wales hospital an “E-Health Innovation Award 2005” in the category “Best use of e-health to improve efficiency”.
Efficiency beyond accuracy
Speech recognition engines today achieve high accuracy rates of up to 100%. Still an accurately recognised text needs significant correction by the author or medical secretary. While medical dictations are typically not dictated in structured format, the final medical report must adhere to certain standards. What’s more, many authors insert additional phrases and superfluous content that must be removed from the final report.
In the traditional model, medical secretaries do much more than simply transcribe what was dictated. They leave out the ‘um’s and ‘err’s, ignore dialogue that is not part of the dictation, implement corrections that are dictated as part of the text, enter the information into forms and even rephrase sentences. They format and organise text, adding section headings, numbered lists and standard blocks of content. In short, they ensure that the final document communicates what was meant, rather than just what was said. Ideally, speech recognition engines should be able to do just this. SpeechMagic therefore boasts Intelligent Speech Interpretation (ISI) technology, which produces high-quality documents with the minimum of human intervention.
ISI emulates the capabilities of a good medical secretary in to reduce manual typing as well as the need for significant formatting and correction. This includes punctuation assistance that eliminates the need to dictate commas and full-stops. ISI greatly increases acceptance among clinicians and improves usage rates by those doctors who have hitherto been dissatisfied with other speech recognition solutions, which they found to be disruptive to their current habits and less responsive to their individual needs.
With SpeechMagic, doctors can dictate, edit and sign off reports within minutes, thus eliminating backlogs in the delivery of medical information. Consequently, waiting times for patients and referring physicians are reduced and the quality of patient care is improved.
a friend