Artificial intelligence can accurately detect signs of tuberculosis in chest X-rays, according to new research.
The findings of a study in Denmark suggest that computer-aided diagnosis programmes are equally or more accurate than trained radiologists, and could be deployed in areas where there is a shortage of qualified staff.
Tuberculosis (TB) remains the 13th leading cause of death globally, claiming around 1.6 million lives a year.
After Covid, it is the second biggest infectious killer.
READ MORE: The robots are coming - what does it mean for healthcare, and being human?
Chest X-rays can play an important role in diagnosing the disease, particularly among patients unable to produce good quality sputum samples for microbiological analysis.
Scientists set about examining whether the use of computer-aided detection - or artificial intelligence (AI) software - could assist in analysing medical images areas where radiologists are in short supply.
To date, there is a lack of good quality studies assessing AI's diagnostic accuracy.
The findings are being presented at the European Congress of Clinical Microbiology & Infectious Diseases (ECCMID) in Copenhagen.
In research led by Dr Frauke Rudolf, an expert in infectious diseases at Aarhus University Hospital in Denmark, scientists compared the performance of qXr, a deep learning technology developed for automated chest X-ray readings, against two Ethiopian radiologists with different levels of experience.
READ MORE: NHS Glasgow in world first AI trial for for COPD patients
The AI programme was given mobile phone photographs of non-digital chest X-rays, to replicate the kind of scenario that would play out in parts of the world with comparatively low medical resources.
Chest X-rays from 498 patients were analysed retrospectively.
Of these, 57 had been diagnosed with TB - 16 as a result of PCR tests, and 41 by clinicians.
In the case of the PCR-diagnosed cases, the AI software correctly identified 75% of the positive cases and was 85.7% accurate in returning a negative reading in the cases of patients who did not have TB.
This compared to 62.5% and 91.7% respectively for the less experienced radiologist.
The more experienced of the two radiologists was 75% accurate in identifying the PCR-positive cases, and 82% accurate in identifying the negative cases.
READ MORE: Fears over a rise in UK tuberculosis cases
Diagnostic accuracy is split into two categories - sensitivity and specificity.
The sensitivity of a test - or the person or programme interpreting scans - refers to the ability to correctly identify positive cases of the disease.
A highly sensitive rating means there are fewer false negatives - in other words, genuine cases being missed.
Specificity relates to the accuracy of identifying negative cases, meaning that there are fewer false positives.
This is important to ensuring that resources are not wasted on needless treatment and investigation that could also be harmful to a patient.
Dr Rudolf said: “With an estimated three million undiagnosed patients in 2021, there is an urgent need to develop novel strategies and technologies aimed at improving TB detection in low-resource, high-incidence settings.
“We’ve shown that AI software is at least as good at detecting TB as a trained radiologist and that a simple mobile phone photograph is sufficient for analysis.
“In low resource areas with a high incidence of TB but a shortage of radiologists, chest X-rays could be photographed with a mobile phone and the image sent to be analysed remotely by the AI.
“This would allow more chest X-rays to be read properly and, crucially, allow more cases of TB to be diagnosed.”
Why are you making commenting on The Herald only available to subscribers?
It should have been a safe space for informed debate, somewhere for readers to discuss issues around the biggest stories of the day, but all too often the below the line comments on most websites have become bogged down by off-topic discussions and abuse.
heraldscotland.com is tackling this problem by allowing only subscribers to comment.
We are doing this to improve the experience for our loyal readers and we believe it will reduce the ability of trolls and troublemakers, who occasionally find their way onto our site, to abuse our journalists and readers. We also hope it will help the comments section fulfil its promise as a part of Scotland's conversation with itself.
We are lucky at The Herald. We are read by an informed, educated readership who can add their knowledge and insights to our stories.
That is invaluable.
We are making the subscriber-only change to support our valued readers, who tell us they don't want the site cluttered up with irrelevant comments, untruths and abuse.
In the past, the journalist’s job was to collect and distribute information to the audience. Technology means that readers can shape a discussion. We look forward to hearing from you on heraldscotland.com
Comments & Moderation
Readers’ comments: You are personally liable for the content of any comments you upload to this website, so please act responsibly. We do not pre-moderate or monitor readers’ comments appearing on our websites, but we do post-moderate in response to complaints we receive or otherwise when a potential problem comes to our attention. You can make a complaint by using the ‘report this post’ link . We may then apply our discretion under the user terms to amend or delete comments.
Post moderation is undertaken full-time 9am-6pm on weekdays, and on a part-time basis outwith those hours.
Read the rules here