It’s safe to say that the technology world is excited by the potential that AI holds, especially when it comes to making advancements in a number of different fields, but what about the medical industry.

According to the latest series of tests conducted by Google AI, the technology could certainly aid in the detection and diagnosis of life threatening ailments.

More specifically Google AI was used to detect advanced (metastatic) breast cancer, with the company noting that it could do so with greater accuracy than human pathologists can.

The team behind the test was able to train its algorithm named LYmph Node Assistant or LYNA to recognise the characteristics of tumours from two specific slides.

“Last year, we described our deep learning–based approach to improve diagnostic accuracy (LYmph Node Assistant, or LYNA) to the 2016 ISBI Camelyon Challenge, which provided gigapixel-sized pathology slides of lymph nodes from breast cancer patients for researchers to develop computer algorithms to detect metastatic cancer,” explains Martin Stumpe, technical lead at Google AI.

Adding that, “furthermore, the actual benefits to pathologists using these algorithms had not been previously explored and must be assessed to determine whether or not an algorithm actually improves efficiency or diagnostic accuracy.”

In the right conditions Google AI is able to detect the difference between cancerous and non-cancerous cells in breast tissue 99 percent of the time, particularly when looking for very small metastases than the human eye may not be able to properly see.

While the results from testing does make for impressive reading, it should be noted that the team’s findings only serve as a proof of concept at this stage. Added to this is the fact that samples tested only came from two labs, and in any significant clinical trial far more samples are required in order to prove the validity of a theory or testing method.

As such, whether or not such an AI system would ever be implemented in the medical field remains to be seen, with the Google AI team well aware that such technologies need to go through an exhaustive vetting period.

“While encouraging, the bench-to-bedside journey to help doctors and patients with these types of technologies is a long one. These studies have important limitations, such as limited dataset sizes and a simulated diagnostic workflow which examined only a single lymph node slide for every patient instead of the multiple slides that are common for a complete clinical case,” concludes Stumpe.