AI Model Predicts Male Infertility Risk Using Blood Hormone Levels

AI model predicts male infertility risk using blood hormone levels

Toho UniversityJul 31 2024 According to a World Health Organization (WHO) study (2017), about half of all infertility is due to men. Semen analysis is considered essential for diagnosis of male infertility, but is not readily available at medical institutions other than those specializing in infertility treatment, and there is a high threshold for receiving it. In this study, a group led by Associate Professor Hideyuki Kobayashi of the Department of Urology, Toho University School of Medicine, Tokyo, Japan developed an AI model that can predict the risk of male infertility without the need for semen analysis by only measuring hormone levels in a blood test. AI creation software that requires no programming was used for the model, and the study was reported in the British scientific journal Scientific Reports. The AI prediction model was based on data from 3,662 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 the semen tests, and LH, FSH, PRL, testosterone, and E2 were measured in the hormone tests. T/E2 was also added. Total motile sperm count (semen volume X sperm concentration X 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, 6th edition (2021), a total motile sperm count of 9.408 X 106 (1.4 mL X 16 X 106/mL X 42%) was defined as the lower limit of normal, assigning a value of "0" if the total motility sperm count for an individual patient was above 9.408 X 106 and a value of "1" when it was below. The accuracy of the AI model was approximately 74%. Next, the AI model was validated using data from 2021 and 2022 for which both semen and hormone tests were available. Using the data of 188 patients in 2021, the accuracy was about 58%, while accuracy using the data for 166 patients in 2022 was about 68%. However, non-obstructive azoospermia could be predicted with a 100% accuracy rate in both 2021 and 2022. According to Associate Professor Kobayashi, "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." 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." Hideyuki Kobayashi, Associate Professor, Department of Urology, Toho University School of Medicine, Tokyo, Japan CreaTact, Inc. (Mito City, Ibaraki Prefecture, Japan; President: Iori Nakaniwa) is conducting software development and data analysis to develop a commercial original AI prediction model for the above purpose. "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," said Associate Professor Kobayashi. The study was published in Scientific Reports on 31 July, 2024. Toho University 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.org/10.1038/s41598-024-67910-0.

AI predicts male infertility risk with blood test, no semen needed

According to a World Health Organization (WHO) study (2017), about half of all infertility is due to men. Semen analysis is considered essential for diagnosis of male infertility, but is not readily available at medical institutions other than those specializing in infertility treatment, and there is a high threshold for receiving it. In a new study, a group led by Associate Professor Hideyuki Kobayashi of the Department of Urology, Toho University School of Medicine, Tokyo, Japan has developed an AI model that can predict the risk of male infertility without the need for semen analysis by only measuring hormone levels in a blood test. AI creation software that requires no programming was used for the model, and the study was reported in Scientific Reports. The AI prediction model was based on data from 3,662 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 the semen tests, and LH, FSH, PRL, testosterone, and E2 were measured in the hormone tests. T/E2 was also added. Total motile sperm count (semen volume X sperm concentration X 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, 6th edition (2021), a total motile sperm count of 9.408 X 10 (1.4 mL X 16 X 10/mL X 42%) was defined as the lower limit of normal, assigning a value of "0" if the total motility sperm count for an individual patient was above 9.408 X 10 and a value of "1" when it was below. The accuracy of the AI model was approximately 74%. Next, the AI model was validated using data from 2021 and 2022 for which both semen and hormone tests were available. Using the data of 188 patients in 2021, the accuracy was about 58%, while accuracy using the data for 166 patients in 2022 was about 68%. However, non-obstructive azoospermia could be predicted with a 100% accuracy rate in both 2021 and 2022. According to Associate Professor Kobayashi, "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. "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 conducting software development and data analysis to develop a commercial original AI prediction model for the above purpose. "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," said Associate Professor Kobayashi.

Japan: AI accurately predicts male infertility using blood test

The researchers collected information from over 3,600 men who had been tested for infertility. The infertility risk of a man can now be predicted through a basic blood test, and the credit goes to a new tool developed by researchers in Japan. This advanced method leverages artificial intelligence (AI) to simplify the process for men to find out if they may face trouble in having children. The AI system analyzes hormone levels from the blood test and can predict male infertility with about 74% accuracy. Importantly, it has demonstrated 100% accuracy in identifying non-obstructive azoospermia, a condition where no sperm is found in the semen.

AI-modelled test for male infertility could soon be with GPs, researchers say

Initial blood test without need for for semen analysis could 'make screening more accessible' A new accessible blood test that can predict male infertility could soon be used by GPs, researchers say. Published in the journal Scientific Reports, the research looked at data from nearly 4,000 men who underwent semen and hormone testing for male infertility from 2011-2020. An AI model was developed from this that researchers said could predict male infertility risk with about 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 is 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 special laboratories. Hideyuki Kobayashi, an associate professor in the department of urology at Toho University school of medicine in Japan, who led the development of the AI model, said this method was intended only as a first screening step to identify infertility and was "not a replacement for semen testing". He added: "In the future, we hope that clinical laboratories and health check-up centres will use our AI prediction model to screen for male infertility, thereby making testing for male infertility more accessible by overcoming hurdles 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 to streamline the process of detecting male infertility. He said: "One of the first steps in diagnosing male infertility is the analysis of a sample of semen in a specialist laboratory. This will involve time off work and another appointment, sometimes at a specialist laboratory some distance away. Therefore, the idea that a first-stage diagnosis could be done from a blood sample taken by the GP does offer some advantages." He added: "The authors of this paper have done a great job in applying artificial intelligence to the problem, but their approach would have to be simplified into some kind of app that GPs could use for it to have real-world benefit. "Clearly, the male would have to provide a semen sample for analysis, eventually, but this approach, if confirmed in a larger dataset, could help streamline the process and make it a bit more user friendly."

A new model for determining risk of male infertility from serum hormone levels, without semen analysis - Scientific Reports

In 2021, thirty-five (18.62%) of the 188 cases overall were azoospermia. There were 10 cases of OA, 24 cases of NOA, and 1 case of male MHH (hypogonadotropic hypogonadism). When validated using the AI prediction model for risk of male infertility, the result for OA was 70% correct (7 cases) while the results for NOA and MHH were 100% correct (24 cases). In 2022, fifty-three (31.93%) of the 166 cases overall were azoospermia. There were 25 cases of OA and 28 cases of NOA. When validated using the AI prediction model for the risk of male infertility, the results for OA and NOA were 72% (18 cases) and 100% (28 cases) correct, respectively. Semen analysis is important for evaluating male infertility, and often the first test ordered when a couple presents for a fertility check or when a man is interested in permanent contraception. Sperm motility, morphology, velocity, and concentration are investigated using microscopes and counting chambers by skilled embryologists. Other methods, such as CASA (computer-assisted semen analysis), which uses algorithms to automatically track spermatozoa, are also effective and are able to present qualitative information on sperm motility. However, semen analysis can only be done at a fertility clinic in most cases. In addition, many men feel uncomfortable about having semen analysis. Recently, the application of AI in medicine has been remarkable. Machine learning methods may improve prediction models. We give examples of disease prediction using AI based on serum hormone levels in the following. Although no accurate predictive models had previously been identified for hormonal prognosis in NFPA (non-functioning pituitary adenoma), Fang et al. demonstrated that machine learning models could accurately predict postoperative pituitary outcomes based on preoperative anterior pituitary hormones in NFPA. In addition, it had been reported that elevated PTH (parathyroid hormone) levels are associated with higher mortality risks, and Kato et al. found that an AI model could predict elevated PTH levels among US adults. Their results suggest that even without serum calcium, phosphatase, and vitamin D levels, the model could predict elevated PTH levels. We could make an AI model for evaluating male infertility using serum hormone levels, without conventional sperm analysis, and the Prediction One-based model had high accuracy as indicated by an AUC of 74.42%. An AI prediction model with similar accuracy was created with AutoML Tables. Prediction One and AutoML Tables are both tools for automatically generating machine learning AI models, but Prediction One is designed for companies in Japan and only supports Japanese. AutoML Tables is global and supports a wide range of industries. However, it requires a minimum of 1,000 data to create an AI model. The reason for using Prediction One and AutoML Tables is that they use different machine learning algorithms and methods, so different approaches can be tried by using them. In addition, we consider that a detailed comparison of the AI models generated by Prediction One and AutoML Tables would allow us to select the AI model with the better performance. Since we also believe that Prediction One and AutoML Tables would produce AI models with comparable accuracy, this should help ensure model reliability. The feature importance ranking of the AI models indicated that FSH had the highest importance level among all features. Its importance was significantly higher than that of "T/E2" and "LH" in the second and third positions. Because the machine learning algorithms and methods used by Prediction One and AutoML Tables are different, there will be some differences in feature values. However, the feature rankings from first to third were the same for both, suggesting that the AI models generated are highly reliable. Tradewell et al. reported a quadratic model that predicts probability of azoospermia from serum FSH levels. They concluded that being able to predict the probability of azoospermia without semen analysis would be useful to urologists when counseling patients, especially when there are logistical hurdles in obtaining a formal semen analysis or for reevaluation prior to surgical sperm extraction. However, they stated that while predicting the probability of azoospermia from serum hormones will not replace semen analysis, the role of hormonal evaluation may expand with the rise of at-home diagnosis. This is also our opinion. We would like to position our AI model as a convenient means of screening for male infertility prior to semen analysis. Thus, a limitation of this study is that the AI model created is not a substitute for semen testing. Currently, at-home diagnostics for male infertility allow men to test their semen without the bother of going to a clinic and paying a higher charge. DTC (Direct-to-consumer) home sperm kits are available from numerous companies and their use seems to be increasing at present. However, although at-home diagnostic kits for male infertility have advantages over traditional methods for semen analysis in terms of convenience and cost, they still have many limitations. First, current non-conventional sperm analysis methods are best used only for indicating whether a user should pursue further testing or not. In addition, because there is a lot of variability in semen analysis, a single parameter does not define whether an individual is fertile or infertile. Second, at-home diagnostics for male infertility are not yet a replacement for laboratory analysis. We consider our AI model for determining risk of male infertility in patients from serum hormone levels to be superior to at-home diagnostics, since serum hormone levels are less variable than semen analysis parameters. Meeker et al. characterized the relationship between serum hormone levels and semen quality among 388 infertile men. They defined abnormal semen concentration as < 20 × 10/mL and found an adjusted odds ratio of 1.0 for abnormal semen concentration in men with low serum FSH levels as compared with normal serum FSH levels and a 4.6 increased odds of semen concentration < 20 × 10/mL in men with elevated FSH levels compared to those with low FSH levels. They reported that an FSH concentration greater than 10 IU/L was predictive of a sperm concentration of less than 20 × 10/mL, with a sensitivity of 0.55 (specificity = 0.79; positive predictive value = 28%). In contrast to FSH, T/E2 and LH have not received much attention regarding feature importance. When predicting the risk of male infertility using an AI model, if it is not a case of determining the likelihood of azoospermia, it would be important to evaluate not only FSH but also other features, such as T/E2 and LH. Regarding the difference between the models in predicting the two types of azoospermia, obstructive and non-obstructive, this may be related to the feature importance of T/E2 and LH, as well as that of FSH. However, we have insufficient information at present to determine a means by which AI could distinguish oligozoospermia, asthenozoospermia, teratozoospermia, and normozoospermia from obstructive azoospermia without semen analysis. Aromatase catalyzes the conversion of testosterone to E2. Aromatase inhibitors have been offered historically to patients with a T/E2 ratio < 10 and have been shown to decrease serum E2 levels and improve semen parameters in men with a low T/E2 ratio. Therefore, it is no coincidence that T/E2 was the second largest contributor to the AI model, since T/E2 is clearly related to sperm concentration and motility. A potential limitation of this study was the collection of a single semen sample to assess semen parameters, and the collection of a single blood sample to measure serum hormone levels, from each patient. Also, the accuracy of the AI model may be compromised because it only considers hormone levels and semen analysis but does not take history into account; for example, of varicoceles. Plymate et al. examined three groups of men: normal fertile men, fertile men with a varicocele, and infertile men with a varicocele. They found that in normal men, there was a positive correlation between serum inhibition measurements and sperm concentration and testicular volume, whereas neither group of men with varicoceles exhibited these relationships. However, since we consider our AI model to be a preliminary screening tool in semen analysis, high accuracy would not be required. Also, since our AI model is intended for screening purposes, it prioritizes recall over precision, a measure of accuracy, with an emphasis on comprehensiveness. Currently, male infertility is widely considered a harbinger for a man's general health and a growing body of literature has identified male infertility as a potential biomarker for both present and future health. Salonia et al. reported that males with infertility had more medical comorbidities than fertile men. Additionally, semen quality decreases as a man's medical comorbidities increase. As a result, a man who is seeking reproductive treatment may also benefit from an evaluation of his overall health because improvements in health can also manifest as an increase in semen quality. Therefore, managing male infertility has wide health ramifications. Screening based on serum hormone levels using an AI model would not only be important for evaluating male patients for infertility but also for optimizing their future health. In conclusion, ability to predict the probability of male infertility without semen analysis would be useful to all physicians and male patients. We believe that screening for male infertility by healthcare professionals other than reproductive specialists will benefit potential male infertility patients. In future clinical application, if the AI prediction model is introduced at health check-up centers and clinical laboratory companies, for example, it will be possible to determine the risk of male infertility by only measuring serum hormone levels in adult males, without semen analysis. If abnormalities are found, individuals would be referred to an infertility facility. The model has the potential to be an unprecedented, revolutionary new tool for comprehensively identifying male infertility patients who had remained undiscovered in the past.