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
NanoApps Medical is investigating the possibility that superparamagnetic nanoparticles (SPIONs) and other classes of nanoparticles (e.g., gold coated nanoshells) might have the capacity to target cancerous tumors, metastasizing cancer cells, pathogens, etc. to deactivate/eliminate [...]
If a little humanoid robot begged you to not shut it off, would you show compassion? In an experiment designed to investigate how people treat robots when they act like humans, many participants struggled [...]
Artificial intelligence and machine learning tools have the potential to analyze large datasets and extract meaningful insights to enhance patient outcomes, an ability that is proving helpful in radiology and pathology. Images obtained by [...]
Researchers at the University of East Anglia have developed a new nanoparticle-based cancer therapy to deliver a combination therapy directly to cancer cells. The new therapy, which has been demonstrated to make prostate cancer [...]
When Joe Rubinsztain started gMed, he was admittedly young—only a few years removed from medical school— and he just didn’t understand leadership that well. “I needed to be abreast of everything and understand everything [...]
Healthcare organizations are likely to see a rapidly growing market around artificial intelligence tools for medical imaging, a new report predicts. The market for artificial intelligence (AI) tools to process and analyze medical imaging [...]
Tuberculosis, a bacterial disease which predominantly affects the lungs, isn’t all that common a sight in the United States. On average, fewer than 10,000 cases are reported each year in a country with [...]
Implantation of a stent-like flow diverter can offer one option for less invasive treatment of brain aneurysms – bulges in blood vessels – but the procedure requires frequent monitoring while the vessels heal. Now, [...]