AI speech recognition solution dramatically cuts medical reporting times

A new version of SpeechReport, a speech recognition tool, has been released, promising to make it simpler and quicker for health care professionals to dictate medial reporting notes.

SpeechReport 4.0, which provider G2 Speech says is its biggest technology upgrade in 25 years, is designed to be an end-to-end workflow management solution. By using a combination of neural networks, deep learning technologies and voice-based AI, it enables health care professionals to dictate medical reporting notes and to streamline the entire documentation process, from dictation to archiving.

The AI engine, Atlas, is able to:

• Reduce background noise
• Recognise user behaviour and dictation style
• Provide further improvements for non-native speakers
• Offer improved performance for use of different types of recording devices
• Provide more customisation options

The increased customisation means that users can enter their own words into their personalised dictionary, saving time when creating medical reports and removing the effort of having to ask the administrator to add the words, as in earlier versions of the software.

Peter Moors, the product manager at G2 Speech, said: “We’re extremely excited to launch SpeechReport 4.0 to new and existing customers – the biggest upgrade in 25 years.

“By implementing the new AI-powered engine – Atlas – which utilises neural networks and deep learning technology, alongside the already rich speech recognition application, we can give our users robust tools to deal with all day-to-day administrative tasks within just one platform while offering 99% accuracy.”

He added: “One of our favourite updates is the new customisation and personalisation features. With SpeechReport 4.0, all users can now create their own word lists for an easy-to-use and intuitive speech recognition experience.”

Integration with electronic patient records

G2 Speech said the benefits of SpeechReport 4.0 include:

• Complete, end-to-end workflow management. It streamlines the entire medical reporting workflow from dictation to archiving and exporting to various programs, all from a single platform. Workflows are highly adaptable and can be customised to the specific needs of diverse specialisms.
• Unrivalled speech recognition. The software includes specialised medical dictionaries and instantly recognises the user’s accent or dialect.
• Seamless integration with leading electronic patient records (EPRs). It is able to integrate with more than 100 electronic record systems, including EPRs, radiology information systems, picture archiving and communications systems and laboratory information management systems.
• Flexibility to work from anywhere. The availability of SpeechReport Mobile, along with a cloud-based solution, means it is possible to use SpeechReport anywhere.
• Robust encryption methods. Because safeguarding patient data is so important, SpeechReport 4.0 uses powerful encryption methods to ensure the best possible protection.
• Compatibility. SpeechReport 4.0 is compatible with barcode scanners, headsets and pedals, enabling people to produce medical reports on the go, hands-free.