Sure, artificial intelligence might end up being the downfall of humanity as we know it — that is, if Elon Musk’s fears come to fruition — but for the time being it’s actually quite useful. A new research effort by an international team of scientists reveals that machine-learning algorithms can be a powerful tool for medicine. The group, which published its work in the journal Nature, managed to create and train an AI to successfully identify different types of brain tumors with impressive accuracy.
In order to identify between different types of brain cancer, the team needed some criteria the computer could use to differentiate between them. With over 100 types of brain tumors already in the medical record, the process of identification can be tricky even for human doctors. The researchers used a DNA process called methylation as a sort of biological fingerprint and taught the AI to tell the difference between which of those fingerprints match specific cancer types.
Like all machine-learning algorithms, the AI needed a base of knowledge from which to draw comparisons. The team fed the computer the data of 2,800 cancer patients as a starting point, allowing it to identify an impress 91 different types of tumors. Then, they asked the computer to identify the type of tumor in over 1,000 known samples and found that the AI’s judgement didn’t match up with the human diagnosis in a number of cases.
As it turns out, the computer wasn’t incorrect in its identification; human doctors had misdiagnosed roughly 12 percent of the previously studied samples and the AI was correct.
Image Credit: Shutterstock
News This Week
Coronavirus tests performed in labs are the gold standard for accuracy and antigen tests are a fast and inexpensive alternative. But backers of a third type of test, developed by a Nobel Prize winner [...]
COVID-19 is a severe infectious disease that has claimed >150,000 lives and infected millions in the United States thus far, especially the elderly population. Emerging evidence has shown the virus to cause hemorrhagic and immunologic [...]
Switzerland’s Covid-19 scientific taskforce chief says hospitals across the Alpine country could be swamped with new coronavirus cases in the next two or three weeks unless the situation improves. “We estimate that the capacity limit [...]
Scientists are to increase surveillance for new coronavirus mutations amid concerns that future strains of the virus could develop at least partial resistance to antibody treatments and Covid-19 vaccines. There is no evidence that the [...]
From the moment you turn off your morning alarm, to the time you hit the pillow, your life is full of surfaces. Swiping through your phone, opening doors, putting in your PIN – there are [...]
A new report suggests that lingering “brain fog” and other neurological symptoms after COVID -19 recovery may be due to post-traumatic stress disorder (PTSD), an effect observed in past human coronavirus outbreaks such as SARS [...]
ClSARS-CoV-2, the virus that causes COVID-19, can relieve pain, according to a new study by University of Arizona Health Sciences researchers. The finding may explain why nearly half of people who get COVID-19 [...]
Contrary to president Donald Trump’s repeated declarations, the coronavirus pandemic was not — and still isn’t — totally under control. That lie is central to “Totally Under Control,” the [...]