Contact us

If you’ve got a story or event for the GPSJ website, e-mail Stuart Littleford at

May 2021
« Apr    


Speech recognition technology is living up to its original promise

 Nick van Terheyden

Nick van Terheyden

49479F0116-LISTSpeech recognition technology is living up to its original promise, driving a dramatic cut in turnaround times in a struggling Histopathology Laboratory. Nick van Terheyden MD, Nuance Communications, explains how

When you combine a growing and ageing population and a healthcare system in desperate need of a makeover, you can understand why the NHS needs to make £20B of cost savings by 2015, and to move from paper to paperless records by 2018 to increase efficiency. But what role can speech technology play in driving efficiency and easing the transition to Electronic Health Records (EHRs), while putting the ‘care’ back into healthcare? In the case of Plymouth Hospital’s Histopathology laboratory, it is a significant one.

The backlog turnaround

The hospital’s Histopathology laboratory had a backlog of approximately 600 cases awaiting reporting. Turnaround times of more than ten weeks were typical, resulting in delays in the diagnosis of cancer, and there were many critical incidents in the Trust due to delays in cancer diagnosis.

To resolve these delays, it started by reviewing its internal workflow processes while evaluating technology that could reduce the build-up of histology backlogs; the sooner a histological diagnosis can be made, the sooner the patient can receive not only the next level of treatment, but also the right treatment. Therefore, the hospital introduced a streaming process that identified priority cases and set up a new workflow for cases, while scheduling tasks more efficiently. The final process involved the deployment of speech recognition solution Nuance Dragon Medical with TalkingPoint for Pathology.

Accurate and detailed reporting in real-time

Perhaps the most significant proof point that demonstrates the effectiveness of deploying speech solutions in conjunction with an improved workflow, is that the backlog was cleared completely. Additionally, the turnaround of new cases was boosted from the previous 40% within 10 days, to more than 80% in 10 days. This achievement exceeds the set national targets.

In daily use, pathologists benefit from speech recognition being time neutral; detailed reports are now created both accurately and in real-time, which make it convenient for the pathologist. Unlike previously, there are no delays waiting for a secretary to type up the report, preventing a typing backlog from building up. The secretary is then free to conduct tasks that ease the burden on the pathologist, allowing them to concentrate on the important issue of reporting of cases, rather than on administrative tasks.

Having also introduced speech recognition for Biomedical Scientist cut-up, the hospital is enjoying savings that equate to one assistant per session, or the equivalent of seven man-hours per day. Other time saving achievements result from the automatic entering of data into the hospital’s Laboratory Information System, saving pathologists approximately 45 minutes a day. These are quantifiable proof points that show when managed properly, speech recognition saves time and human resource while increasing efficiency. Therefore, it’s no surprise to hear many pathologists state, ‘Once you use it, you never go back.’

Best of breeds means best results

Despite this positive experience story, some people have had mixed experiences with older speech recognition systems. Just as there has been significant progress in medical knowledge in the last two decades, there have been significant strides in the accuracy and ease of use of today’s speech recognition applications. While speech recognition’s accuracy is not an issue – even with accents, if the success of heavily-accented medical professionals enjoy when using the technology is to go by – there are some issues to consider and to overcome when deploying speech recognition.

Unsuprisingly, the greatest of which is resistance to change and the fear of new technology. Fingers have possibly been burnt in the past through false starts, usually the result of a piecemeal introduction combined with a lack of adequate training. Others have faced integration problems with existing software. Plymouth’s experience proves that these challenges – whether they are change management or technology-related – can be overcome. In order to do so, and to make the deployment of speech as seamless as possible, the need to work with an experienced partner cannot be emphasised enough. In Plymouth’s case, it worked with TalkingPoint, which was experienced in speech, but also in integrating it with existing Healthcare IT systems. When done correctly, speech doesn’t just reward patient care; in this laboratory’s case, what it has achieved using speech recognition has been rewarded with a £50,000 NHS Innovation Award. Plymouth invested this money to further improve its department.

Healing healthcare with speech

As we move toward 2018 and the introduction of EHR, the future for Healthcare IT is exciting. In anticipation of this, we are starting to see what the future holds for speech in order to help medical professionals more quickly navigate the EHR, the data, diagnosis and prescription options using their voice. Virtual assistants – like Nuance’s Florence application developed for healthcare – will help medical professionals embrace this inevitable shift to a digital workflow. Most important of all, as Plymouth proves, speech is beginning to remove patients from backlogs and is putting them back where they should always be – at the centre of care.

Leave a Reply

You can use these HTML tags

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>




This site uses Akismet to reduce spam. Learn how your comment data is processed.