Predicting seminal quality with artificial intelligence methods

• 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. Artificial intelligence techniques are now an emerging methodology as decision support systems in medicine. In this paper we compare three artificial intelligence techniques, decision trees, Multilayer Perceptron and Support Vector Machines, in order to evaluate their performance in the prediction of the seminal quality from the data of the environmental factors and lifestyle. To do that we collect data by a normalized questionnaire from young healthy volunteers and then, we use the results of a semen analysis to asses the accuracy in the prediction of the three classification methods mentioned above. The results show that Multilayer Perceptron and Support Vector Machines show the highest accuracy, with prediction accuracy values of 86% for some of the seminal parameters. In contrast decision trees provide a visual and illustrative approach that can compensate the slightly lower accuracy obtained. In conclusion artificial intelligence methods are a useful tool in order to predict the seminal profile of an individual from the environmental factors and life habits. From the studied methods, Multilayer Perceptron and Support Vector Machines are the most accurate in the prediction. Therefore these tools, together with the visual help that decision trees offer, are the suggested methods to be included in the evaluation of the infertile patient. (C) 2012 Elsevier Ltd. All rights reserved.

Subject headings

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)

Keyword

Artificial neural network

Support Vector Machines

Decision trees

Diagnosis

Decision support system

Expert system

Semen quality

Male

fertility potential

Publication and Content Type

art (subject category)

ref (subject category)