Innovation, News

UCL develops speech therapy smart app and AI that helps detect oesophageal cancer

University College London (UCL) has published updates on its research and development in two interesting areas of health technology – using artificial intelligence (AI) to help detect a type of cancer, and a smart app that provides speech therapy for stroke sufferers.

The iReadMore app from the Neurotherapeutics Group at UCL’s Queen Square Institute of Neurology provides smart device-based gamified therapy for those requiring speech rehabilitation support following a stroke or brain injury, including those with COVID-induced strokes. It can also be used by patients with other neurological diagnoses that cause reading impairments, such as certain types of dementia, according to the university.

The game-like therapy helps improve reading ability, with a focus on word-reading speed and accuracy, and involves using both written and spoken words, as well as pictures. As well as adapting the difficulty of the therapy for each user – to keep it ‘relevant’ and ‘challenging’ – it also gives users immediate feedback and tests, and enables self-tracking of progress.

Explaining that ‘stroke patients typically need around 100 hours of Speech and Language Therapy (SaLT)’, UCL says that during a time when NHS provisions could be limited or stretched due to the COVID-19 pandemic, the app has enabled stroke patients at the National Hospital for Neurology and Neuroscience (NHNN) in London, to have ‘limitless hours of SaLT’ at both the hospital and during home-based rehabilitation.

Professor Alex Leff of the UCL Institute of Cognitive Neuroscience and UCL Queen Square Institute of Neurology, who helped develop the app, said: “Reading ability is commonly affected in patients with strokes, brain injury or dementia that causes language loss. We know that the surviving brain networks can be retrained to improve reading ability, but it takes time and lots of specific practice. iReadMore provides this.

“Because the current version of the app was developed by patients, it should enable many more patients to be able to rack up the necessary practice time at their own pace and without supervision.”

In its latest update on the innovation, the university says that iReadMore is now available to the public through the Apple App and Google Play stores and is free for patients with primary progressive aphasia, a dementia related condition, but a paid-for service for those with other conditions.

Further information on iReadMore’s original randomised trial is available via the Brain journal of neurology.

Elsewhere at UCL, scientists have been collaborating with a spinout company called Odin Vision and clinicians from University College Hospitals London (UCLH), on a project that uses AI to help detect early signs of oesophageal cancer. The system – known as CADU – supports doctors to identify cancerous tissue.

After achieving regulatory approval earlier in 2021, the first procedure was performed at UCLH by Consultant Gastroenterologist, Dr Rehan Haidry, and it is believed that it’s the first medical device using AI for oesophageal cancer to be CE and UKCA approved for use on patients.

According to UCL, early signs of oesophageal cancer can be difficult to diagnose, with changes in tissue tough to spot during endoscopy procedures. Currently, only around 20 out of 100 people (around 20%) with stage 4 oesophageal cancer will survive their cancer for one year or more after diagnosis, as per Cancer Research UK.

However, the CADU artificial intelligence system – which has been shown ‘hundreds of thousands of images of diseased tissue’ – has learned to ‘classify tissue’ using the ‘visual patterns in images’. This means that, during an endoscopy, it can analyse the image from the video camera in real-time and provides information about the characteristics of the tissue to support doctors. If detected early, UCL says, the disease can be eradicated over 90% of the time with a ‘less invasive procedure’.

Peter Mountney, Odin Vision CEO and Honorary Associate Professor, UCL Computer Science, said: “AI has great potential to transform healthcare. We are very excited to achieve this landmark procedure and use our AI technology to support doctors in the fight against one of the most aggressive forms of cancer.”

Dr Haidry, who has been working with Odin Vision on the platform, explained: “Oesophageal cancer remains a very big challenge for us and carries a very high mortality compared to other solid organ cancers. It is imperative that we can detect changes early when we carry out routine endoscopic examinations, because we are now in an era where we can deliver early curative treatment that can improve the outlook for patients with oesophageal cancer.

“Despite the fantastic development of imaging and training there is still room for improvement and the new CADU system will allow us to improve early detection and streamline the care for these patients across the country…I am very excited to finally see it being used in routine clinical care on our patients and in our endoscopy unit at UCLH.”

CADU is also part of DigitalHealth.London’s Accelerator programme, which aims to speed up the adoption of technologies in the NHS.

Jenny Thomas, Programme Director for DigitalHealth.London, said: “This first use of Odin Vision’s technology in oesophageal cancer screening is a major milestone. We are very proud to be supporting Odin Vision as part of our Accelerator programme…Odin Vision’s work to-date in utilising cutting-edge AI technology to support early detection of colorectal cancer has been remarkable, so I’m looking forward to seeing the impact of this new AI system on oesophageal cancer.”

Last year, in May 2020, HTN spoke to DigitalHealth.London about its Accelerator programme –  find out more here.