AI-based chest X-ray diagnosis tech approved

AI-based chest X-ray diagnosis tech approved

behold.ai has been issued with a CE Mark Class lla certification in the UK and EU for its AI-based technology that can diagnose chest X-rays as ‘normal’. This is believed to be the world’s first such approval and has the potential to make up to £100m in cost savings for the UK NHS, the Company estimates.

The algorithm’s high level of accuracy in identifying normal chest x-rays exams means that the red dot platform can be used to speed up the detection of those suspected with COVID-19.

behold.ai and Wellbeing Software recently announced a collaboration to fast-track the diagnosis of COVID-19 in NHS hospitals using artificial intelligence analysis of chest X-rays. A national roll-out would enable a large number of hospitals to triage suspected COVID-19 patients inside and outside of the hospital setting using chest X-rays. This is currently being used as the key diagnostic test for triage of COVID-19 patients. This solution is also useful in dealing with the backlog of radiology cases, such as suspected lung cancer patients.

The CE Mark approval, issued to the company by the British Standards Institute, relates to the full quality assurance system for behold.ai’s AI technology and to the design, development and manufacture of its red dot platform.

“This is a great result for the company and for our team of quality leaders, AI engineers and clinicians who have worked for years to develop a system that meets the highest quality standards,” said Simon Rasalingham, Chairman and CEO of behold.ai. “There is, quite rightly, a big focus on ensuring that the relatively new technology of artificial intelligence produces solutions that have a high degree of accuracy, reliability and scalability. This first in-kind regulatory approval is a key achievement for companies in this sector, the first autonomous AI algorithm to rule out normal chest X-rays.”

“Crucially, at a time when NHS radiologists are increasingly reporting images from home, our technology is fast, safe and effective both inside and outside the hospital setting. For examinations identified by our algorithm as normal, with a high degree of confidence, our results can be automatically accepted as being as accurate as an experienced consultant radiologist, and much faster,” said Dr Thomas Naunton Morgan, Chief Medical Officer of behold.ai.

The Company estimates that being able to ‘rule out normal’ could save the NHS over £100m per annum through a reduction in outsourcing costs. Earlier this year, behold.ai received FDA clearance for its red dot algorithm ‘instant triage’ system in relation to the life-threatening condition of pneumothorax (collapsed lung).

Subscribe to our newsletter

Related articles

AI accurately detects COVID-19 on chest x-rays

AI accurately detects COVID-19 on chest x-rays

Researchers have developed a new AI platform that detects COVID-19 by analyzing X-ray images of the lungs.

Using machine learning to detect COVID-19 in X-rays

Using machine learning to detect COVID-19 in X-rays

Students at Cranfield University have designed computer models that can identify COVID-19 in X-rays.

AI enables rapid ultrasound COVID-19 testing

AI enables rapid ultrasound COVID-19 testing

Establishing whether a patient is suffering from COVID-19 within a few minutes is possible using ultrasound machines that are enhanced with artificial intelligence.

AI could serve as backup to radiologists' eyes

AI could serve as backup to radiologists' eyes

A study showed that an AI algorithm provides results comparable with lung function tests, which measure how forcefully a person can exhale.

“CheXNeXt” outperformed radiologists in evaluating chest X-rays

“CheXNeXt” outperformed radiologists in evaluating chest X-rays

In a matter of seconds, a new algorithm read chest X-rays for 14 pathologies, performing as well as radiologists in most cases, a Stanford-led study says.

Microfluidics and AI microscopy measure hemoglobin

Microfluidics and AI microscopy measure hemoglobin

Researchers at the Indian Institute of Science and SigTuple Technologies have developed a method to measure hemoglobin levels in small-volume blood samples.

Potential jurors favor use of AI in precision medicine

Potential jurors favor use of AI in precision medicine

Physicians who follow AI advice may be considered less liable for medical malpractice than is commonly thought, according to a new study of potential jury candidates in the U.S.

AIs detect diabetic eye disease inconsistently

AIs detect diabetic eye disease inconsistently

Although some artificial intelligence software tested reasonably well, only one met the performance of human screeners.

Self-learning algorithms analyze imaging data

Self-learning algorithms analyze imaging data

Artificial neural networks open up new possibilities in interpreting the time-consuming imaging ´data.

Popular articles