Title: SEMEN PARAMETERS CAN BE PREDICTED FROM ENVIRONMENTAL FACTORS AND LIFESTYLE USING ARTIFICIAL INTELLIGENCE METHODS Short Title: Predicting Semen Quality with Neural Networks

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 from environmental factors, life habits and health status, as a possible Decision Support System that can help in the study of the male fertility potential. One hundred twenty three young healthy volunteers provide a semen sample that was analyzed according to the World Health Organization 2010 criteria. They also were asked to fulfill a validated questionnaire about life habits and health status. Sperm concentration and percentage of motile sperm were related to socio-demographic data, environmental factors, health status, and life habits, 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 of motility is slightly lower than concentration, it is possible to predict it with a significant accuracy. This methodology can be a useful tool in order to early diagnosis of patients with seminal disorders or in the selection of candidates to become semen donors. Summary sentence: Artificial Neural Networks predicts, with high classification accuracy, seminal parameters of young and healthy volunteers using the health status, lifestyle and exposure to environmental factors as inputs variables.