Development and validation of a machine learning model for sperm DNA fragmentation rate in infertile men: a multicenter retrospective study

1

A machine learning model was developed to predict sperm DNA fragmentation index (DFI) in infertile men using clinical and semen parameters.
2

The Random Forest model demonstrated the highest predictive performance with an AUC of 0.979 in the development cohort and 0.945 in external validation.
3

Core factors influencing DFI included sperm motility, concentration, viability, lifestyle habits, and stress levels, which were used to create an online prediction platform.
4

The model showed notable miscalibration in external validation, indicating systematic overestimation of risk and necessitating further validation before clinical use.
5

This study highlights the importance of integrating machine learning in assessing sperm quality, addressing limitations of traditional sperm analysis methods.

1