Machine Learning for Cross-Sectional Classification of Erectile Dysfunction Severity Using Phosphodiesterase Type 5A Genotype and Clinical Phenotypes
Journal of Visualized Experiments · 2026-11-10 · (237)
DOI: 10.3791/74899 ↗At a glance
Querschnittstudie in Journal of Visualized Experiments, published online on 2026-11-10. Written by Xiuzhen Liu and 2 co-authors.
Abstract (original language)
Clinical and metabolic phenotypes may be associated with current erectile dysfunction (ED) severity. This cross-sectional analysis of a prospectively recruited single-center sample examined the incremental value of genotype-informed model architectures. The clinical cohort included 577 men with ED, and paired model comparisons used 569 participants with available genotype calls. The positive outcome was a concurrent five-item International Index of Erectile Function (IIEF-5) score ≤16. Penalized logistic regression, random forest, and extreme gradient boosting (XGBoost) were compared using participant-level predicted probabilities and a common outcome definition. Area under the receiver operating characteristic curve (AUC) increased numerically by 0.036, 0.037, and 0.042, respectively; all paired bootstrap intervals for these differences included zero. Continuous net reclassification improvement was 0.120, 0.019, and 0.392. The XGBoost genotype-informed model had an AUC of 0.783 and a Brier score of 0.169. Its joint calibration intercept and slope were -3.516 and 5.905, indicating limited calibration. Decision curves coincide with the classify-all reference at low thresholds. Genotype information showed potential for concurrent severity classification, but the discrimination gains and calibration findings require cautious interpretation.
Cite
APA
Liu, X., Zhang, T., & Sun, X. (2026). Machine Learning for Cross-Sectional Classification of Erectile Dysfunction Severity Using Phosphodiesterase Type 5A Genotype and Clinical Phenotypes. Journal of Visualized Experiments. https://doi.org/10.3791/74899
Vancouver
Liu X, Zhang T, Sun X. Machine Learning for Cross-Sectional Classification of Erectile Dysfunction Severity Using Phosphodiesterase Type 5A Genotype and Clinical Phenotypes. Journal of Visualized Experiments. 2026. doi:10.3791/74899
BibTeX
@article{Liu2026,
author = {Liu, Xiuzhen and Zhang, Ting and Sun, Xiaodan},
title = {Machine Learning for Cross-Sectional Classification of Erectile Dysfunction Severity Using Phosphodiesterase Type 5A Genotype and Clinical Phenotypes},
journal = {Journal of Visualized Experiments},
year = {2026},
number = {237},
doi = {10.3791/74899}
}
EUVIMED