A new accessible blood test that can predict male infertility may soon be through GPssay researchers.
Published in the journal Scientific Reports, the research looked at data from nearly 4,000 men who underwent semen and hormone tests for male infertility from 2011-20.
From this, an AI model was developed which, according to researchers, can predict male infertility risk with approximately 74% accuracy. It works by measuring different hormone levels in a blood sample, which are associated with sperm production.
The researchers said the model could predict a severe form of infertility known as non-obstructive azoospermia – where there are no sperm in the semen – with 100% accuracy.
The team believe their AI-enhanced blood test could make screening for male infertility more accessible, as it can be used in GP surgeries without the need for specialist laboratories.
Hideyuki Kobayashi, an associate professor in the department of urology at Toho University’s school of medicine in Japan, who led the development of the AI model, said this method is only intended as a first screening step to identify infertility and is not a substitute for semen testing”.
He added: “In the future, we hope that clinical laboratories and health research centers will use our AI prediction model to screen for male infertility, thereby making male infertility testing more accessible by overcoming barriers to it.”
According to the World Health Organization, worldwide about 7% of men are affected by infertility with about half of fertility problems in a heterosexual couple coming from the man.
Allan Pacey, a professor of andrology at the University of Manchester, said the method could help streamline the process of detecting male infertility.
He said: “One of the first steps in the diagnosis of male infertility is the analysis of a sample of semen in a specialist laboratory. This will take time and involve another appointment, sometimes at a specialist laboratory some distance away. Therefore, the idea that a first-stage diagnosis can be made from a blood sample taken by the family doctor offers some advantages.
He added: “The authors of this paper have done a good job of applying artificial intelligence to the problem, but their approach will need to be simplified into the kind of application that general practitioners can use for it to have real benefit.
“Obviously, the male must ultimately provide a semen sample for analysis, but this approach, if confirmed in a larger data set, could help streamline the process and make it a bit more user-friendly.”
