Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{169272,
        author = {Lokesh Vazirani and Pratham Choudhary and Prathamesh Karmakar and Rahul Prasad and Dr. Ashlesha S. Nagdive},
        title = {Machine Learning Based Male Fertility Prognosis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {893-900},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169272},
        abstract = {Male factor infertility is an important and increasingly acknowledged global problem because statistics have estimated that nearly 7% of men suffer from it. It is a condition of multifactorial origin that encompasses both genetic and lifestyle determinants in male reproductive health. Conventional techniques for the diagnosis of male infertility are largely based on invasive and costly evaluation procedures, which generally include semen analysis and hormonal profiling. These are not always available, especially in rural areas that lack the specialized healthcare facilities, and are not preventive in nature. This paper introduces a machine learning-based model for the assessment of the prognosis of male fertility based on readily available health and lifestyle indicators. The integration of inputs like age, times smoked or taken alcohol, periods of inactivity, medical history, and seasonality into the model enables high prediction accuracy of a patient's fertility status while delivering interpretability through SHAP values. SHAP divides how each variable impacts individual predictions, therefore making it transparent. Finally, the model's performance on the benchmark dataset suggests that it can serve as an accessible tool for preliminary fertility assessment, enabling one to make informed lifestyle choices that may positively affect fertility. This research offers a new way forward with male fertility diagnostics in a combination of predictive accuracy with interpretability that makes a foundation for non-invasive, preventative fertility assessment tools.},
        keywords = {Male infertility, Predictive modeling, Machine learning, SHAP values, Lifestyle factors, Fertility diagnostics.},
        month = {November},
        }