In a remarkable stride for AI in healthcare, a tool named Mia has successfully identified early-stage breast cancers that had slipped past human doctors.
This AI tool, tested by the NHS, analysed mammograms of over 10,000 women, successfully flagging all those with symptoms, plus an extra 11 cases that doctors had missed.
These early-stage cancers can be extremely small and challenging to spot, making Mia's achievement all the more impressive. The BBC witnessed Mia in action at NHS Grampian, where the tool detected tumours practically invisible to the human eye.
One of the 11 patients, Barbara, whose cancer was identified by Mia but overlooked by hospital radiologists, benefited from early detection. Her 6mm tumour was caught so early that she only required five days of radiotherapy. Breast cancer patients with tumours smaller than 15mm at discovery have a 90% survival rate over the next five years.
Want to learn more about AI's impact on the world in general and property in particular? Join us on our next Webinar! Click here to register
Mia's developer, Kheiron, claims that tools like Mia could reduce the waiting time for results from 14 days to just three. While all cases in the trial were reviewed by both Mia and a human, the hope is that one day, the tool could replace one of the radiologists, effectively halving the workload.
AI tools like Mia are trained on a vast amount of data, including anonymised images of symptoms from a diverse range of people. However, obtaining this data can be challenging due to patient confidentiality and privacy concerns.
Despite the promising results, Mia is not perfect. It had no access to patient history, so it flagged harmless cysts already identified in previous scans. Also, due to current health regulations, the machine learning element of the AI tool was disabled, meaning it couldn't learn on the job or evolve during its use.
While the Mia trial is an early test, it highlights the exciting potential of AI in diagnostics. As the number of cancer cases diagnosed each year increases, technological innovation will be vital to improving NHS services and reducing pressure on its staff.
Want to learn more about AI's impact on the world in general and property in particular? Join us on our next Webinar! Click here to register
Made with TRUST_AI - see the Charter: https://www.modelprop.co.uk/trust-ai
Comentarios