Identifying risk factors for vasculogenic etiology in patients with erectile dysfunction based on clinical features and machine learning - Takeaways - MDSpire

Identifying risk factors for vasculogenic etiology in patients with erectile dysfunction based on clinical features and machine learning

  • By

  • Jian Wang

  • Yancheng Wu

  • Xiaoyan Zhang

  • Yang Lu

  • Zhenrong Piao

  • Wei Zhao

  • Maosen Zhang

  • May 21, 2026

  • 0 min

Share

  • 1

    The study identified seven key risk factors for vasculogenic erectile dysfunction, including age, hypertension, smoking, diabetes, and hormonal levels.

  • 2

    Machine learning models, particularly random forest, were utilized to analyze clinical data, achieving moderate discriminative ability with an AUC of 0.682.

  • 3

    Anxiety, as measured by the Hamilton Anxiety Scale, emerged as a significant non-traditional risk factor for vasculogenic erectile dysfunction.

  • 4

    The study emphasizes the need for further research to validate findings and optimize machine learning models for clinical decision-making.

  • 5

    Routine clinical indicators can help identify high-risk populations for vasculogenic erectile dysfunction, facilitating early recognition and intervention.

Original Source(s)

Identifying risk factors for vasculogenic etiology in patients with erectile dysfunction based on clinical features and machine learning

  • by Jian Wang, Yancheng Wu, Xiaoyan Zhang, Yang Lu, Zhenrong Piao, Wei Zhao, Maosen Zhang

  • May 21, 2026

Related Content

Clinical parameters-based machine learning models for predicting intraoperative hemodynamic instability in hypertensive pheochromocytomas and paragangliomas patients

Blood pressure can be seriously elevated during botulinum toxin A detrusor injection

Inverse Relationship Between Serum Small Dense LDL Cholesterol Levels and Kidney Stone Incidence: Findings from Two Distinct Cross-Sectional Studies