A machine learning approach using semen parameters and sperm mitochondrial DNA copy number to predict couples’ fecundity
Sperm mtDNAcn is associated with multiple conventional and detailed semen parameters. Moreover, a composite machine learning ElNet-SQI that included mtDNAcn and several semen parameters had the highest predictive ability of pregnancy. These results indicate that sperm mtDNAcn can serve as a biomarker of overall sperm fitness and likelihood of reproductive success.
Authors
- Brian W. Whitcomb (ORCID: https://orcid.org/0000-0002-8646-5823)
- J. Richard Pilsner (ORCID: https://orcid.org/0000-0002-4541-6267)
- Karolina Nowak (ORCID: https://orcid.org/0000-0002-9971-0023)
- Savni Sawant (ORCID: https://orcid.org/0009-0000-9157-5771)
- Amanda L. Paskavitz
- Allyson J Rosati
- Ricardo Pimenta Bertolla (ORCID: https://orcid.org/0000-0001-6892-9244)
- Ted Westling
Institutions
- Amherst College (US)
- Wayne State University (US)
- University of Massachusetts Amherst (US)
Publication Details
- Journal
- F&S Reports
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1016/j.xfre.2025.05.002
- Primary Topic
- Forensic and Genetic Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00