Nearest Centroid achieves 94.2% accuracy predicting male fertility from semen parameters

A study investigates using machine learning to classify male fertility status based on sperm concentration, motility, and morphology using the VISEM dataset of 85 participants.

• The Nearest Centroid classifier achieved an accuracy of 94.2%, outperforming Support Vector Machines and Quadratic Discriminant Analysis among over 40 tested algorithms.
• Model robustness was validated using 5-fold cross-validation and multiclass ROC-AUC analysis.
• The dataset classifies samples into Fertile, Sub-Fertile, and Infertile categories according to World Health Organization criteria.

The findings suggest that machine learning models can provide fast, accurate, and objective assessments of semen quality to support clinical decision-making in andrology.