Main problem: fertility data is inadequately assessed by traditional statistical methods for a variety of reasons. First, the principal test of male fertility potential, the Semen Analysis (SA) is a composite of several dissimilar parameters, and the SA and other laboratory tests of fertility potential reflect physiological mechanisms that interact in complex ways. Second, patient data is often fragmented, obtained from multiple sources. Importantly, 2 patients are required for the final result.
Methods: Novel and powerful computational method, the neural network, was explored to analyze fertility data. An integrated series of programs was written in the C computer language to implement a back propagation algorithm. A model data analysis system was chosen, predicting the penetration of zona-free hamster ova by sperm (Sperm Penetration Assay (SPA)) and the distance travelled by the farthest swimming sperm (Penetrak Assay) from the SA, for these 2 assays are generally believed by the reproductive medical community to be independent of the SA. The classification accuracy of the neural network was compared to 2 standard statistical methods, linear discriminant function analysis (LDFA) and quadratic discriminant function analysis (QDFA).
Results: A neural network could be trained to correctly predict the Penetrak result in over 80% of assays it had not previously encountered, and another network could predict the SPA outcome in nearly 70%. The neural network was superior to LDFA and QDFA in predicting both assay outcomes (for Penetrak: LDFA = 64%, QDFA = 69%; for SPA: LDFA = 65%, QDFA = 45%).(ABSTRACT TRUNCATED AT 250 WORDS)