Researchers at Toho University in Japan have developed an AI-based prediction model to assess the risk of male infertility without requiring semen analysis. This innovative approach has the potential to replace traditional semen testing as a standard screening method for male infertility in the future.
Image Credit: NTshutterth/Shutterstock.com
A 2017 World Health Organization (WHO) study found that around half of all infertility cases are attributed to male factors. Although semen analysis is essential for diagnosing male infertility, it is typically available only at specialized fertility clinics, making it less accessible at general medical institutions and posing a significant barrier to testing.
In response, Associate Professor Hideyuki Kobayashi and his team from the Department of Urology at Toho University School of Medicine in Tokyo, Japan, have developed an AI-based model that predicts male infertility risk using only hormone levels from a blood test, eliminating the need for semen analysis.
The study, published in the British journal Scientific Reports, utilized AI creation software that does not require programming expertise. The model, which was trained on data from 3,662 patients, achieved an overall accuracy of about 74 %, with perfect accuracy in detecting non-obstructive azoospermia, a severe form of male infertility.
The research involved collecting clinical data from 3,662 men who underwent both semen and hormone tests between 2011 and 2020. Semen tests measured volume, sperm concentration, and motility, while hormone tests assessed levels of LH, FSH, PRL, testosterone, and E2, along with T/E2 ratios. Total motile sperm count was calculated and compared against the WHO’s reference values. A total motile sperm count of 9.408 X 106 was used as the threshold, with counts below this value indicating abnormal results.
The AI model was further validated using data from 2021 and 2022. For 188 patients in 2021, the model's accuracy was around 58 %, and for 166 patients in 2022, it was approximately 68 %. Despite these variances, the model consistently achieved 100 % accuracy in predicting non-obstructive azoospermia in both years.
This AI prediction model is intended only as a primary screening step prior to semen testing, and while it is not a replacement for semen testing, it can be easily performed at facilities other than those specializing in infertility treatment.
Kobayashi, Associate Professor, Toho University
Kobayashi added, “The AI prediction model used in this study was particularly accurate in predicting non-obstructive azoospermia, which is a severe form of azoospermia. 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 specialist infertility clinic and receive appropriate treatment.”
CreaTact, Inc. (Mito City, Ibaraki Prefecture, Japan; President: Iori Nakaniwa) is working on developing a proprietary AI prediction model through advanced software development and data analysis to address this need.
Kobayashi concluded, “In the future, we hope that clinical laboratories and health checkup centers will use our AI prediction model to screen for male infertility, thereby making testing for male infertility, more accessible by overcoming hurdles to it.”
Journal Reference:
Kobayashi, H., et al. (2024) A new model for determining risk of male infertility from serum hormone levels, without semen analysis. Scientific Reports. doi:10.1038/s41598-024-67910-0