According to a study by the World Health Organization (WHO), approximately half of infertility is due to men. In fact, it is estimated that, globally, one in 20 men has some type of fertility problem, with a low number of sperm in the ejaculate. However, Only one in 100 men has no sperm in his ejaculate.
The Most common problems linked to male infertility These are those that affect the functioning of the testicles. Other problems are hormonal imbalances or the obstruction or absence of some of the ducts of the male reproductive organs. Lifestyle factors, along with age, also play a role in male infertility.
Thus, Semen analysis is considered essential for the diagnosis of male infertility.but it is not readily available in medical institutions other than those specialized in infertility treatment, and there is a very high limitation to performing it. To facilitate this type of analysis, a team of scientists led by Hideyuki Kobayashi of the Department of Urology at the Toho University School of Medicine (Japan), developed an AI model that can predict the risk of male infertility. without the need for a semen analysis, measuring only the hormone levels in a blood test.
To do this, Kobayashi’s team used AI creation software that requires no programming for the model. The results have been published in Scientific Reports. AI prediction model was based on data from more than 3,500 patients and had an accuracy rate of approximately 74%In particular, it was 100% correct in predicting non-obstructive azoospermia, the most severe form of male infertility.
The current study collected clinical data from 3,662 men who underwent semen and hormone testing for male infertility between 2011 and 2020. Semen volume, sperm concentration, and sperm motility were measured in semen testing and were also measured in hormone testing. Total motile sperm count (semen volume, sperm concentration, and sperm motility rate) was calculated from the semen test results. Based on the reference values for semen testing in the WHO laboratory manual for the examination and processing of human semen, a total motile sperm count of 9.408 X 10 was defined.6 as the lower limit of normal, assigning a value of zero if an individual patient’s total motile sperm count was greater than 9.408 X 106 and a value of one when it was lower. The accuracy of the AI model was about 74%.
The AI model was then validated using data from 2021 and 2022 for which both semen and hormone tests were available. Using the data from 188 patients in 2021, the accuracy was approximately 58%, while the accuracy using the data from 166 patients in 2022 was approximately 68%. However, Non-obstructive azoospermia could be predicted with a 100% accuracy rate in both 2021 and 2022.
According to Kobayashi, “This AI prediction model is intended solely as a primary screening step prior to semen testing and while it is not a replacement for semen testing, it can easily be performed in facilities other than those specializing in infertility treatment.”
The Advantages of this system, over semen analysis, are severalThe first is that it is much faster and does not require special equipment, since the blood test and the hormones to be detected are standard. As for the patient, he or she does not receive any prior recommendations, as is the case with the semen analysis, an exam for which it is indicated to avoid ejaculating 24 to 72 hours before the test, not to consume alcohol or caffeine two to five days before the test, and other details.
“The AI prediction model used in this study was particularly accurate in predicting non-obstructive azoospermia, which is a severe form of azoospermia,” Kobayashi adds. “When the prediction model detects abnormal values, since patients may possibly have non-obstructive azoospermia, This should be a trigger for them to undergo detailed testing at a specialized clinic. in infertility and receive appropriate treatment.”
Azoospermia affects up to 10% of infertility cases and It is linked to other diseases, such as testicular cancer, cystic fibrosis or chronic kidney failure.among others. Therefore, early detection is essential.
“In the future, we hope that clinical laboratories and health control centers will use our AI prediction model to detect male infertility, thus making infertility testing more accessible by overcoming the obstacles to doing so,” Kobayashi concludes.