Doctor AI

Dr. Benjamin Haibe-Kains separates fact from science fiction amid a report an AI is better at spotting breast cancer than humans. Alan explains why Star Trek Picard was awesome, and Michael explains why Avenue 5 was awesomer.

Artificial Intelligence is better for spotting breast cancer than humans are

by Shane Alexander

A new study has found AI is better at spotting breast cancer than a doctor. A super team of researchers trained an AI model on X-ray images from almost 29,000 women.

There’s this algorithm that has outperformed six radiologists in reading mammograms. It was as good as two doctors working together. And here’s the thing – the AI had only the most recent mammogram to go on. Meanwhile, the doctor had access to the patient’s health history. This could mean that AI could, rightfully so, be applied in clinical settings. This would take off the burden on healthcare systems by supporting the heavy workload.

Potential to spot breast cancer with greater accuracy

Dominic King, UK Lead at Google Health, said: “Our team is really proud of these research findings, which suggest that we are on our way to developing a tool that can help clinicians spot breast cancer with greater accuracy. Further testing, clinical validation and regulatory approvals are required before this could start making a difference for patients, but we’re committed to working with our partners towards this goal.”

The results, published in the journal Nature, say the AI reduces false positives by 5.7% in the US and 1.2% in the UK datasets. AI also reduced false negatives by 9.4% in the States and 2.7% in the United Kingdom. This means the AI spotted the cancers that humans had missed.

“This is a huge advance in the potential for early cancer detection,” said Dr. Mozziyar Etemadi, one of the study’s co-authors and a research assistant professor of anesthesiology and biomedical engineering at Northwestern University. “Breast cancer is one of the highest causes of cancer mortality in women. Finding cancer earlier means it can be smaller and easier to treat. We hope this will ultimately save a lot of lives.”

The geographical difference

There’s a difference depending on where the study took place. And it has to do with the datasets and the authors that were examining the difference how breast cancer screening work in the two countries. In the UK, the images were analyzed by two clinical experts. In the US, it’s only one clinical expert.

Breast cancer patients shouldn’t expect this anytime soon

This is undoubtedly very interesting and a small peek into what the future might hold. However, don’t expect any change yet. This is according to Dr. Alejandro Berlin, a radiation oncologist and medical director of data science, outcomes and smart cancer care at Toronto’s Princess Margaret Cancer Care Centre.

AI predicts things, he said. “A computer program can quickly and cheaply analyze a massive amount of information — more than a person can process — and “find connections and data that were invisible to the human eye.”

“Are you willing to go into the or just based on that? Or would you like your clinician to take a look at your belly and say: ‘Yes, based on my experience, I think you have appendicitis and we’re going to go through the risks of the surgery together.’”


AI company set to improve breast cancer diagnosis

Liked it? Take a second to support Shane Alexander on Patreon!
Become a patron at Patreon!

Leave a Comment