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
Scientists from the Terasaki Institute for Biomedical Innovation (TIBI) have developed a contact lens that can capture and detect exosomes, nanometer-sized vesicles found in bodily secretions which have the potential for being diagnostic cancer [...]
Among the total number of deaths caused by different types of cancer, esophageal cancer is the sixth most significant. Several conventional treatments, such as radiotherapy, chemotherapy, and surgery have multiple side effects, including off-target [...]
Cell membrane-coated nanoparticles, applied in targeted drug delivery strategies, combine the intrinsic advantages of synthetic nanoparticles and cell membranes. Although stem cell-based delivery systems were highlighted for their targeting capability in tumor therapy, inappropriate [...]
When babies in the African countries of Guinea Bissau and Uganda were given the tuberculosis vaccine, something remarkable happened. Instead of the vaccine only protecting against the target bacteria – Myocbacterium tuberculosis – the tuberculosis vaccine offered broad protection against a [...]
Thousands of years ago, across the Eastern Mediterranean, multiple Bronze Age civilizations took a distinct turn for the worse at around the same time. The Old Kingdom of Egypt and the Akkadian Empire both collapsed, and there was [...]
IN OCTOBER 2014, virologist Edward Holmes took a tour of the Huanan Seafood Wholesale Market in Wuhan, a once relatively overlooked city of about 11 million people in the central Chinese province of Hubei. The market would [...]
Self-healable ionic sensing materials with fatigue resistance are imperative in robotics and soft electronics for extended service life. The existing artificial ionic skins with self-healing capacity were prepared by network reconfiguration, constituting low-energy amorphous [...]
As demand for solar energy rises around the world, scientists are working to improve the performance of solar devices—important if the technology is to compete with traditional fuels. But researchers face theoretical limits on [...]