Sign up for Englemed updates from TwitterSign up for Englemed updates from Facebook
Contact Englemed
Our contact email address.
We can provide a specialist, tailored health and medical news service for your site.
Click here for more information
RSS graphic XML Graphic Add to Google
About Englemed news services - services and policies.
Englemed News Blog - Ten years and counting.
Diary of a reluctant allergy sufferer - How the British National Health Service deals with allergy.
BookshopFor books on women's health, healthy eating ideas, mental health issues, diabetes, etc click here
Copyright Notice. All reports, text and layout copyright Englemed Ltd, 52 Perry Avenue, Birmingham UK B42 2NE. Co Registered in England No 7053778 Some photos copyright Englemed Ltd, others may be used with permission of copyright owners.
Disclaimer: Englemed is a news service and does not provide health advice. Advice should be taken from a medical professional or appropriate health professional about any course of treatment or therapy.
Study to look at Covid-19 impact on blood cancer patients
Fri May 22nd - A new UK study is to be launched that will examine how patients who receive stem cell transplants for blood cancers and blood disorders react to severe Covid-19 infection. More
'Focus on blood clotting in Covid-19 patients'
Fri May 22nd - There is an urgent need to focus on medications that address dangerous blood clotting in Covid-19 patients, according to a leading haematologist. More
Immunotherapy hope for elimination of leukaemia stem cells
Fri May 22nd - Hematopoietic stem cells can be selectively eliminated using immunotherapy instead of chemotherapy, a new Swiss study has revealed. More
On 08/02/2018 David Kelly wrote:
Would you like to write a piece about this to be i... on Researchers unveil new pain re...
On 23/10/2017 Cristina Pereira wrote: on HIV breakthrough - MRC...
On 12/09/2017 Aparna srikantam wrote:
Brilliant finding! indeed a break through in under... on Leprosy research breakthrough...
On 01/07/2017 Annetta wrote:
I have been diagnosed with COPD for over 12 years.... on Seaweed plan for antimicrobial...
On 12/03/2017 Steph wrote:
The photo you have paired with this article is its... on 'Fat shaming' limits...

Concern over 'exaggerated' AI studies

Thursday March 26th, 2020

Millions of patients could be at risk because of “poor quality” and “exaggerated” studies that claim artificial intelligence (AI) is as good as – or better than – human experts at interpreting medical images, according to an analysis published today.

Writing in The BMJ, researchers from Imperial College London say their review of published studies over the past ten years, comparing the performance of a deep learning algorithm in medical imaging with expert clinicians, found methods and risk of bias that have not been examined.

The team found two eligible randomised clinical trials and 81 non-randomised studies. Of the non-randomised studies, nine were prospective and six were tested in a “real world” clinical setting.

They found that the average number of human experts in the comparator group was four, while access to raw data and code, which allows independent scrutiny of results, was severely limited.

Out of the 81 non-randomised studies, 58 were categorised as high risk of bias and the team also highlighted often poor adherence to recognised reporting standards.

Sixty-one of the studies stated that performance of AI was at least comparable to, or better than, that of clinicians, and 31 said further prospective studies or trials were needed.

While the team says there were some limitations, such as the possibility of missed studies and the focus on deep learning medical imaging studies, nevertheless, they say “many arguably exaggerated claims exist about equivalence with (or superiority over) clinicians, which presents a potential risk for patient safety and population health at the societal level”.

They also warned that overpromising language “leaves studies susceptible to being misinterpreted by the media and the public, and as a result the possible provision of inappropriate care that does not necessarily align with patients’ best interests”.

The researchers conclude by saying that having a high quality and transparently reported evidence base will maximise patient safety.

Nagendran M, Chen Y, Lovejoy CA et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies in medical imaging. BMJ 26 March 2020.

Tags: General Health | UK News

Printer friendly page Printer friendly page

Comment on this article:

<a>,<b> & <p> tags allowed
Please enter the letters displayed:
(not case sensitive)