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
Researchers from Duke University are developing a flu shot with the new technology that was used for two coronavirus vaccines. Both the Pfizer-BioNTech and the Moderna shots use part of the virus's genetic code [...]
Researchers from the University of Liverpool have shown the potential of repurposing an existing and cheap drug into a long-acting injectable therapy that could be used to treat Covid-19. In a paper published in the journal Nanoscale, [...]
Researchers have developed a new superbug-destroying coating that could be used on wound dressings and implants to prevent and treat potentially deadly bacterial and fungal infections. The material is one of the thinnest antimicrobial [...]
The U.S. is recommending a "pause" in administration of the single-dose Johnson & Johnson COVID-19 vaccine to investigate reports of potentially dangerous blood clots. In a joint statement Tuesday, the Centers for Disease Control [...]
The South African coronavirus variant is better at "breaking through" the defences of the Pfizer/BioNTech vaccine than other forms of the virus, Israeli experts said Sunday. However, one of the authors told AFP that [...]
EPFL scientists have developed AI-powered nanosensors that let researchers track various kinds of biological molecules without disturbing them. The tiny world of biomolecules is rich in fascinating interactions between a plethora of different agents [...]
A team of researchers from the Institute for Infectious Diseases (IFIK) at the University of Bern and the Federal Institute of Virology and Immunology (IVI) have assessed virus growth and activation of the cellular [...]
Researchers at Brown University have succeeded in creating the first wireless, implantable, rechargeable, long-term brain-computer interface. The wireless BCIs have been implanted in pigs and monkeys for over 13 months without issue, and human [...]