A study conducted by scientists from Weill Cornell Medicine (New York, United States) shows that an algorithm is able to know which fertilized embryos in vitro they will be more likely to cause pregnancies that end successfully. The researchers, who have published their work on the portal NPJ Digital Medicine, were based on 12,000 photographs, to which, one by one, they rated according to their appearance.
A subsequent statistical analysis established a correlation between these factors and success in fertilization. The algorithm they designed, called Stork, achieved an accuracy of 97%. For one of the authors, the Doctor Olivier Element, director of the Caryl and Israel Englander Institute for Precision Medicine at Weill Cornell Medicine, this innovation "maximizes the chances of patients having a healthy pregnancy."
Children, teachers of ‘machine learning’
A group of European colleagues, specifically from Italian and Finnish universities and hospitals, have completed another experiment that, thanks to technology, allowsdetect developmental problems in newborns. His technique consists in discovering movement patterns that could be linked to serious ailments, such as cerebral palsy. In its conclusions, disseminated through the magazine Paediatric record, highlights the role of another algorithm.
From three-dimensional video recordings and mathematical calculations, it can be ascertained whether a baby's motor maturity corresponds to her real age. The margin for further progress is as wide as the controversy that some of these solutions raise. For example, in a collaboration between Chinese and North American experts, collected by the prestigious Nature Medicine, the potential of artificial intelligence for childhood diagnoses is discussed.
Concerns like this have led Stefania Druga of the Massachusetts Institute of Technology (MIT, United States) to deepen interactions between minors and automatic devices. For this purpose he has created the platform Cognimates, so that the kids program and personalize their digital tools and even their robots. And so, almost without realizing it, they end up becoming masters of machine learning. Druga argues that, in this way, boys can make "a more informed and critical use of technology."
Like many of her classmates, she believes that artificial intelligence has a lot to learn from children. Without going any further, the psychologist Alison Gopnik Remember that the minds of the little ones can provide clues to scientists and computer scientists on how to improve machine learning techniques. "Even people of one year can be flexible and make generalizations, but the machines find that very difficult," he concludes.