Semen Parameters Can Be Predicted from Environmental Factors and Lifestyle Using Artificial Intelligence Methods1

Abstract

Fertility rates have dramatically decreased in the last two decades, especially in men. It has been described that environmental factors as well as life habits may affect semen quality. In this paper we use artificial intelligence techniques in order to predict semen characteristics resulting from environmental factors, life habits, and health status, with these techniques constituting a possible decision support system that can help in the study of male fertility potential. A total of 123 young, healthy volunteers provided a semen sample that was analyzed according to the World Health Organization 2010 criteria. They also were asked to complete a validated questionnaire about life habits and health status. Sperm concentration and percentage of motile sperm were related to sociodemographic data, environmental factors, health status, and life habits in order to determine the predictive accuracy of a multilayer perceptron network, a type of artificial neural network. In conclusion, we have developed an artificial neural network that can predict the results of the semen analysis based on the data collected by the questionnaire. The semen parameter that is best predicted using this methodology is the sperm concentration. Although the accuracy for motility is slightly lower than that for concentration, it is possible to predict it with a significant degree of accuracy. This methodology can be a useful tool in early diagnosis of patients with seminal disorders or in the selection of candidates to become semen donors.

Prediction of semen quality using artificial neural network

“…In the present study, we construct two artificial neural networks, one to predict the overall seminal profile, and a second for the prediction of characteristics of sperm concentration. Similar studies were conducted only by Girela et al (2013), Gil et al (2012) and Sahoo and Kumar (2014). In their study, Sahoo and Kumar (2014) created the MLP model to predict the general semen profile.…”

“…The values in the current article are 85.12%, 84.93% and 0.812, respectively (Table 9). Girela et al (2013), based on survey responses developed two MLP models to predict the motility and sperm concentration. On the basis of the factors used to evaluate the effectiveness of the test, it can be concluded that we were able to create more effective predictive models.…”

“…While artificial neural networks have been successfully used in same fertility studies (Ma et al, 2011;Vickram et al, 2016), surprisingly, their use in the preliminary diagnosis of male infertility is a lot less than we expected. Actually, only two teams of researchers have worked on this issue: Girela et al (2013) and Gil et al (2012), and Sahoo and Kumar (2014). The question we asked ourselves was whether an extensive survey, such as the one used in the studies of, both Girela et al (2013) and Gil et al (2012), (34 questions) is necessary.…”

“…Actually, only two teams of researchers have worked on this issue: Girela et al (2013) and Gil et al (2012), and Sahoo and Kumar (2014). The question we asked ourselves was whether an extensive survey, such as the one used in the studies of, both Girela et al (2013) and Gil et al (2012), (34 questions) is necessary. Thus, the aim of the present study was to construct an artificial neural network, which could be used for predicting the result of semen analysis based on the basic questionnaire data.…”

Protein profile screening: reduced expression of Sord in the mouse epididymis induced by nicotine inhibits tyrosine phosphorylation level in capacitated spermatozoa

“…Many lifestyle choices, such as tobacco smoking, have long been considered as impairments of male fertility (Girela et al 2013). Epidemiological and clinical studies have discovered significant declines in sperm density, sperm mobility, semen volume (Kü nzle et al 2003, Ramlau-Hansen et al 2007) and the percentage of normal sperm morphology in smoking populations (Trummer et al 2002, Gaur et al 2007.…”