Nav: Home

Concerns over 'exaggerated' study claims of AI outperforming doctors

March 25, 2020

Many studies claiming that artificial intelligence is as good as (or better than) human experts at interpreting medical images are of poor quality and are arguably exaggerated, posing a risk for the safety of 'millions of patients' warn researchers in The BMJ today.

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

Artificial intelligence (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. But the methods and risk of bias of studies behind these headlines have not been examined in detail.

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 (to allow independent scrutiny of results) was severely limited.

More than two thirds (58 of 81) studies were judged to be at high risk of bias (problems in study design that can influence results), and adherence to recognised reporting standards was often poor.

Three quarters (61 studies) stated that performance of AI was at least comparable to (or better than) that of clinicians, and only 31 (38%) stated that further prospective studies or trials were needed.

The researchers point to some limitations, such as the possibility of missed studies and the focus on deep learning medical imaging studies so results may not apply to other types of AI.

Nevertheless, they say that at present, "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."

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," they warn.

"Maximising patient safety will be best served by ensuring that we develop a high quality and transparently reported evidence base moving forward," they conclude.
-end-
Peer-reviewed? Yes
Evidence type: Systematic review
Subjects: Deep learning studies

BMJ

Related Medical Imaging Articles:

Advanced medical imaging combined with genomic analysis could help treat cancer patients
Melding the genetic and cellular analysis of tumors with how they appear in medical images could give physicians new insights into how to best treat patients, especially those with brain cancer, according to a new study led by TGen.
Low doses of radiation used in medical imaging lead to mutations in cell cultures
Common medical imaging procedures use low doses of radiation that are believed to be safe.
Use of medical imaging
This observational study looked at patterns of use for computed tomography (CT), magnetic resonance imaging (MRI), ultrasound and nuclear medicine imaging in the United States and in Ontario, Canada, from 2000 to 2016.
Medical imaging rates continue to rise despite push to reduce their use
The rates of use of CT, MRI and other scans have continued to increase in both the US and Ontario, Canada, according to a new study of more than 135 million imaging exams conducted by researchers at UC Davis, UC San Francisco and Kaiser Permanente.
Two-in-one contrast agent for medical imaging
Magnetic resonance imaging (MRI) visualizes internal body structures, often with the help of contrast agents to enhance sensitivity.
Medical imaging rates during pregnancy
Researchers looked at rates of medical imaging (CT, MRI, conventional x-rays, angiography, fluoroscopy and nuclear medicine) during pregnancy in this observational study that included nearly 3.5 million pregnant women in the United States and Canada from 1996 to 2016.
Scientists discover new method for developing tracers used for medical imaging
University of North Carolina researchers discovered a method for creating radioactive tracers to better track pharmaceuticals in the body as well as image diseases, such as cancer, and other medical conditions.
Radiology publishes roadmap for AI in medical imaging
In August 2018, a workshop was held at the National Institutes of Health (NIH) in Bethesda, Md., to explore the future of artificial intelligence (AI) in medical imaging.
Study could lead to safer and cheaper 3D medical imaging
A new study led by The Australian National University (ANU) has discovered a promising way to significantly lower doses of X-rays that has the potential to revolutionise 3D medical imaging and make screening for early signs of disease much cheaper and safer.
Researchers aim to prevent medical imaging cyberattacks
Researchers and cybersecurity experts have begun to examine ways to mitigate the risk of cyberattacks in medical imaging before they become a real danger.
More Medical Imaging News and Medical Imaging Current Events

Trending Science News

Current Coronavirus (COVID-19) News

Top Science Podcasts

We have hand picked the top science podcasts of 2020.
Now Playing: TED Radio Hour

Uncharted
There's so much we've yet to explore–from outer space to the deep ocean to our own brains. This hour, Manoush goes on a journey through those uncharted places, led by TED Science Curator David Biello.
Now Playing: Science for the People

#555 Coronavirus
It's everywhere, and it felt disingenuous for us here at Science for the People to avoid it, so here is our episode on Coronavirus. It's ok to give this one a skip if this isn't what you want to listen to right now. Check out the links below for other great podcasts mentioned in the intro. Host Rachelle Saunders gets us up to date on what the Coronavirus is, how it spreads, and what we know and don't know with Dr Jason Kindrachuk, Assistant Professor in the Department of Medical Microbiology and infectious diseases at the University of Manitoba. And...
Now Playing: Radiolab

Dispatch 1: Numbers
In a recent Radiolab group huddle, with coronavirus unraveling around us, the team found themselves grappling with all the numbers connected to COVID-19. Our new found 6 foot bubbles of personal space. Three percent mortality rate (or 1, or 2, or 4). 7,000 cases (now, much much more). So in the wake of that meeting, we reflect on the onslaught of numbers - what they reveal, and what they hide.  Support Radiolab today at Radiolab.org/donate.