Monday , September 26 2022

How AI Helps Transform Breast Cancer History


Every October for the past four decades, Breast Cancer Awareness Month has helped raise the visibility of the most common cancer on Earth — one that claims nearly three-quarters of a million lives each year.

Despite cases recorded as far back as ancient Egypt, breast cancer has been considered an “inconceivable” condition for thousands of years. Women were expected to suffer in silence and “respect.”

This stigma has yielded academic ignorance, as breast cancer has been disappearing as a relatively disease without research until just a few decades ago. For most of the last century, a woman suffering from breast cancer will be offered radiation and / or surgery – usually radical surgery, which has left them distorted to little avail – while treatment for another cancer is advancing.

Breast cancer mortality barely changed from the 1930s to the 1970s, until a joint effort by feminist groups and the liberation of women elevated breast cancer research and treatment to its legal position in male-dominated hospitals and research institutions. The treatment has changed in a generation.

In the 1970s a woman diagnosed with breast cancer had a 40% chance of surviving the next ten years. Today, this probability has almost doubled, thanks to new drugs, advanced survey methods and more subtle and effective surgeries.

Crucial to this change was an emphasis on early diagnosis. The earlier the breast cancer, the easier it is to treat. Artificial intelligence is playing an increasingly critical role in breast cancer detection. This year the UK National Health Service (NHS) announced research into how AI can test breast cancer. Although it is intended to increase, rather than replace, human physicians, it will help provide a shortage of radiographs – an additional 2,000 are needed to clear the NHS cluster of epidemic-induced scans.

Startups are also using AI to deal with this shortage. British Kheiron Medical Technologies plans to use AI to survey half a million women for breast cancer. The Blue Blue Book in Spain is developing a device that can detect breast cancer from urine samples. Nirmai in India is working on a low-cost tool that can help screen a large number of women in rural and semi-urban areas.

But no less essential for improving outcomes is identifying patients at high risk for recurrence. About one in ten breast cancer patients will return after their initial treatment and reduce their chances of survival.

Historically it was difficult to identify them early, but my team, who worked with Gustave Russo, a French cancer hospital, developed an AI tool that could identify 8 out of 10 high-risk patients for recurrence. AI helps patients achieve the care they need earlier, saving patients at lower risk from frequent and troublesome tests. Meanwhile, drug companies are accelerating trials of breast cancer drugs by recruiting higher-risk patients.

Patient data privacy can be an understandable barrier to rapid research. Hospitals are careful about sending data off-site, and no pharmaceutical company wants to share valuable data with competitors. But AI helps solve these problems, enabling faster, safer and cheaper development of new treatments.

Unified Learning, a new form of AI that practices data from multiple institutions without the data coming out of hospitals, is being used across Europe to give researchers access to vital but inaccessible data.

We will also use AI to deepen our understanding of why the most aggressive forms of breast cancer are resistant to certain drugs, and help us develop new and tailored drugs that differentiate between healthy cells and cancer cells better than chemotherapy.

Although the impact of AI is growing, no less important for improving outcomes is the recognition that health is a fundamentally human endeavor. No algorithm can comfort a patient in its darkest moments, and no machine can instill and evoke the resilience that every patient needs to defeat his illness.

I and any other physician know that treating disease is about understanding the patient just as much as understanding the patient. The clinician’s empathy is associated with higher patient satisfaction and lower distress, and preventing a patient from continuing during difficult treatment. Fortunately, AI technology that is increasingly helping to treat breast cancer is designed to augment and empower physicians.

Breast cancer is no longer “inconceivable” to the millions diagnosed each year. The sea of ​​pink films that herald the beginning of October mark how far we have come in our fight against one of our oldest enemies – one we are now defeating. We can never completely eradicate breast cancer. But because AI helps diagnose patients earlier and allows for rapid development of treatments, we may no longer need Breast Cancer Awareness Month in a few decades.

Source link