Using a public database of 60,000 fingerprints, Guo employed an AI-based system, a deep contrastive network, to analyze prints, revealing unexpected similarities between different fingers of the same individual.

This finding suggests that the uniqueness of intra-person fingerprints, long believed in forensics, might not be absolute.

Dr. Hod Lipson, the James and Sally Scapa Professor of Innovation at Columbia, told Earth.com: “The reviewers dismissed the possibility of detecting similarities between fingerprints from the same individual.” Despite this setback, the team’s perseverance led to their findings being published in Science Advances.

Aniv Ray, a senior at Columbia Engineering, said to BBC Science Focus, “Just imagine how well this [AI] will perform once it’s trained on millions, instead of thousands of fingerprints.”

Guo revealed, “The AI was not using ‘minutiae,’ which are the branchings and endpoints in fingerprint ridges — the patterns used in traditional fingerprint comparison. Instead, it was using something else, related to the angles and curvatures of the swirls and loops in the center of the fingerprint.”

Columbia Engineering reveals that he noted, “If this information tips the balance, then I imagine that cold cases could be revived, and even that innocent people could be acquitted.”

According to Earth.com, the research team is aware of potential biases in their data and recognizes the need for further validation across diverse demographics.

BBC Science Focus reports that Lipson stated, “Many people think that AI cannot really make new discoveries — that it just regurgitates knowledge. But this research is an example of how even a fairly simple AI, given a fairly plain data set that the research community has had lying around for years, can provide insights that have eluded experts for decades.”

The probability is estimated to be less than one in 64 billion, according to research published in Springer Nature.

Factors such as umbilical cord length, position in the womb, blood pressure, nutrition, and the rate of finger growth during fetal development all contribute to their distinctiveness, as reported by BBC Science Focus.

Species like gorillas, chimpanzees, and koalas also exhibit this trait.

As Dr. Lipson points out in Columbia Engineering, “We are about to experience an explosion of AI-led scientific discovery by nonexperts, and the expert community, including academia, needs to get ready.”