NEWS
ETHNICITY DATA FROM HEALTH RECORDS OF OVER 61 MILLION PEOPLE STUDIED IN DETAIL FOR FIRST TIME
In research published in Nature Scientific Data , ethnicity data from general practice and hospital records of more than 61 million people in England has been studied in detail in for the first time . Researchers assessed the available details of ethnicity data from different sources of NHS records in England . They showed that much more detailed classification of ethnicity is possible than health researchers typically use . They also highlighted that ethnicity information was missing for almost one in 10 patients , while around 12 % of patients had conflicting ethnicity codes in their patient records .
The study was led by researchers at the University of Oxford , University College London and the Centre for Ethnic Health Research , and made possible through the support of Health Data Research UK ( HDR UK ) and the British Heart Foundation ( BHF ) Data Science Centre . The researchers analysed de-identified data on ethnicity and other characteristics from general practice and hospital health records , accessed safely within NHS England ’ s Secure Data Environment ( SDE ). It is the first part of a three-phase project aiming to reduce bias in AI health prediction models .
Sara Khalid , Associate Professor of Health Informatics and Biomedical Data Science at NDORMS , said : “ Because AIbased healthcare technology depends on the data that is fed into it , a lack of representative data can lead to biased models that ultimately produce incorrect health assessments . Better data from real-world settings , such as the data we have collected , can lead to better technology and ultimately better health for all .”
DIGITAL APP IMPROVES SPEECH IN STROKE PATIENTS
A new digital platform significantly improves speech for people with a language disorder . This is according to an NIHR-supported study . The app , iTalkBetter , has been designed for users with the language disorder , aphasia . It analyses speech in real time and provides feedback for the person using it . It allows them to practise over 200 commonly used words in their own time and without limits .
It has been developed by the Neurotherapeutics Group at University College of London ’ s Queen Square Institute of Neurology . It was also supported by Wellcome Trust . Aphasia occurs when a person suffers brain damage . This can lead to speech or language difficulties . The most common causes are stroke , severe head injury and brain tumours .
Symptoms vary widely from person to person . Most people have trouble with their speaking . They may also experience issues with writing , reading and listening . The study found that using the app over a six-week period for around 90 minutes a day improved users ’ ability to name 200 commonly used items by 13 %. These gains were maintained 12 weeks after the therapy ended . Spontaneous speech was also found to improve .
Currently , the NHS provides around 12 hours of speech and language therapy for each patient . Further face-to-face therapy is available via some charities or privately .
NIHR Research Professor Alex Leff , Professor of Cognitive Neurology at UCL Institute of Cognitive Neuroscience and UCL Queen Square Institute of Neurology , said : “ Most health care systems massively under dose people with aphasia in terms of the hours of speech and language therapy that they are provided with . App delivered therapy is one solution to this problem .
“ This is the first randomised controlled trial of an app designed to improve speaking that transfers to a naturalistic speaking task and show an effect on connected speech .”
10 www . intelligenthealth . tech