Artificial intelligence (AI) can match doctors when it comes to diagnosing patients, according to technology firm Babylon.
In a series of tests, including parts of the MRCGP exam taken by trainee GPs, the company’s AI demonstrated the ability to provide heath advice which is on-par with practising clinicians, Babylon claims.
The technology scored 80% for accuracy, while seven highly experienced primary care doctors achieved an accuracy range of 64-94%.
When assessed against conditions seen most frequently in primary care medicine, the accuracy of the AI was 98% and the experienced clinicians had an accuracy rate ranging from 52-99%.
The AI also achieved a safety score of 97%, compared with an average of 93.1% for the doctors.
Dr Ali Parsa, Babylon’s founder and CEO, highlighted the potential benefits of the technology in the developing world, where many people have no access to even the most basic healthcare services.
“Even in the richest nations, primary care is becoming increasingly unaffordable and inconvenient, often with waiting times that make it not readily accessible,” Dr Parsa added. “Babylon’s latest artificial intelligence capabilities show that it is possible for anyone, irrespective of their geography, wealth or circumstances, to have free access to health advice that is on-par with top-rated practising clinicians.”
However, the Royal College of GPs took a more cautious approach, arguing that apps and algorithms may have a role to play in supporting GPs but could never replicate their experience and expertise.
“The potential of technology to support doctors to deliver the best possible patient care is fantastic, but at the end of the day, computers are computers, and GPs are highly-trained medical professionals: the two can’t be compared and the former may support but will never replace the latter,” said Professor Martin Marshall, vice chair of the Royal College of GPs.