There is a belief that each fingerprint on one person's hand is completely unique, but that is now being challenged by research from Columbia University. A team at the US university trained an AI tool to examine 60,000 fingerprints to see if it could work out which ones belonged to the same individual. The researchers claim the technology could identify, with 75–90% accuracy, whether prints from different fingers came from one person. The researchers think the AI tool was analyzing the fingerprints in a different way than traditional methods, focusing on the orientation of the ridges in the center of a finger rather than the way in which the individual ridges end and fork, which is known as minutiae. "It is clear that it isn't using traditional markers that forensics have been using for decades," said Prof. Lipson. The results of the study could have the potential to impact both biometrics and forensic science.