News

AddToAny

Google+ Facebook Twitter Twitter

"AI research could pose risk for patients"

Many studies claiming that artificial intelligence (AI) is as good as, or better than, human experts at interpreting medical images are of poor quality and potentially exaggerated.

The claim is published in the BMJ, in a paper that argues this could pose a risk for the “safety of millions of patients”.

The findings raise concerns about the quality of evidence underpinning many of these studies and highlight the need to improve design and reporting standards.

AI is an innovative and fast-moving field with the potential to improve patient care and relieve overburdened health services.

Deep learning is a branch of AI that has shown particular promise in medical imaging.

The volume of published research on deep learning is growing, and some media headlines that claim superior performance to doctors have fuelled hype for rapid implementation.

However, the methods and risk of bias of studies behind these headlines have not been examined in detail, it is claimed.

To address this, a team of researchers reviewed the results of published studies over the past 10 years, comparing the performance of a deep-learning algorithm in medical imaging with expert clinicians.

They found just two eligible randomised clinical trials and 81 non-randomised studies. Of the non-randomised studies, only nine were prospective (tracking and collecting information about individuals over time) and just six were tested in a “real world” clinical setting.

The average number of human experts in the comparator group was just four, while access to raw data and code (for independent scrutiny of results) was limited.  

bit.ly/2JJbEfR

Picture Credit | Shutterstock

Related Articles

Digital Pathology group

The IBMS discussion group for digital pathology is looking for new members to attend and facilitate at virtual meetings.

The British Journal of Biomedical Science: Issue 2 2021, Synopsis

Deputy Editor Guy Orchard provides a brief glimpse of the articles on offer in the second issue of 2021.

3D skin imaging

A portable device has been developed that produces high-resolution 3D images of human skin within 
10 minutes.

Medical eponmys pt4: Hodgkin disease

This is the fourth is a series of short biographies of persons whose names are directly used for diseases, conditions or syndromes familiar to those in clinical pathology labs. Their names are most often used because they made highly significant contributions to the discovery and understanding of the disease. 

Top