Identification of factors associated with failure to meet nocturnal penile tumescence and rigidity criteria based on RigiScan monitoring and machine learning algorithms: a cross-sectional study
5 affiliations
- 1Department of Andrology, Yangzhou Hospital of Traditional Chinese Medicine
- 2Department of General Surgery, Affiliated Hospital of Nanjing University of Chinese Medicine/Jiangsu Province Hospital of Chinese Medicine
- 3Department of Respiratory Medicine, Sichuan First Hospital of Traditional Chinese Medicine
- 4Department of Andrology, Affiliated Hospital of Nanjing University of Chinese Medicine/Jiangsu Province Hospital of Chinese Medicine
- 5School of Medicine, Nanjing University of Chinese Medicine
Abstract
Background: Using RigiScan nocturnal penile tumescence and rigidity (NPTR) monitoring as reference, we applied machine learning to identify routine clinical indicators associated with failure to meet NPTR criteria (no effective nocturnal erection).
Methods: A total of 519 patients with erectile dysfunction completed two consecutive nights of RigiScan monitoring and were divided into effective and no-effective nocturnal erection groups. Data were split 7:3 into training (n = 364) and internal validation (n = 155) sets. Feature selection (univariate logistic regression, Boruta, LASSO) was performed exclusively in the training set. Five models (LR, RF, SVM, LightGBM, XGBoost) were constructed. The classification threshold was determined in the training set and fixed in the validation set. Performance was assessed using AUC with bootstrap 95% CIs, Brier score, calibration slope and intercept, sensitivity, specificity, PPV, and NPV. Nested cross-validation (5 × 3) was performed. SHAP interpreted the best model.
Results: The effective group comprised 389 patients and the no-effective group 130. Six variables were selected: HbA1c, GLU, Smoke, Hypertension, Age, and BMI. In the validation set, LR achieved the highest AUC (0.779, 95% CI 0.692–0.861), followed by LGBM (0.718), XGB (0.700), RF (0.699), and SVC (0.646). DeLong’s test showed LR significantly outperformed RF (p = 0.028) and SVC (p = 0.009), but not LGBM or XGB. In nested cross-validation, LR also had a higher mean AUC than RF (0.726 ± 0.052 vs 0.666 ± 0.034). LR showed the lowest Brier score (0.151) and calibration slope closest to 1 (1.258). SHAP identified BMI, GLU, and Age as the top three contributors.
Conclusions: Conventional metabolic indicators achieved only moderate discrimination. BMI, GLU, and HbA1c were consistently associated with failure to meet NPTR criteria. LR was the most robust model but cannot replace RigiScan monitoring. These findings should be interpreted as associations, not causal relationships.
Related
- Real-World Marijuana Use Is Associated With Altered Nocturnal Cardiac Autonomic Function, Reduced Sleep Quality, and Declining Consumption During Wearable Monitoring
- Monitoring nocturnal movement and sleep in Parkinson’s disease: a systematic review of movement sensors
- Construction and validation of an identification model for frailty in maintenance hemodialysis patients using multiple machine learning algorithms: a cross-sectional study of retrospectively collected data
- Preserved cardiac vagal tone is associated with nocturnal glycaemic stability
- Nocturnal sleep duration, clinical activity score, and thyroid functional remission after radioactive iodine therapy in Graves’ disease with thyroid-associated ophthalmopathy
BibTeX
@article{wang2026identification,
title = {{Identification of factors associated with failure to meet nocturnal penile tumescence and rigidity criteria based on RigiScan monitoring and machine learning algorithms: a cross-sectional study}},
author = {Jian Wang and Yang Shan and Silun Li and Zihao Sun and Zhenrong Piao and Xiaoyan Zhang and Maosen Zhang},
journal = {Frontiers in Endocrinology},
year = {2026},
month = oct,
doi = {10.3389/fendo.2026.1926525},
url = {https://www.frontiersin.org/articles/10.3389/fendo.2026.1926525/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Identification of factors associated with failure to meet nocturnal penile tumescence and rigidity criteria based on RigiScan monitoring and machine learning algorithms: a cross-sectional study
AU - Jian Wang
AU - Yang Shan
AU - Silun Li
AU - Zihao Sun
AU - Zhenrong Piao
AU - Xiaoyan Zhang
AU - Maosen Zhang
PY - 2026
DA - 2026/10/27
JO - Frontiers in Endocrinology
DO - 10.3389/fendo.2026.1926525
UR - https://www.frontiersin.org/articles/10.3389/fendo.2026.1926525/full
AB - Background: Using RigiScan nocturnal penile tumescence and rigidity (NPTR) monitoring as reference, we applied machine learning to identify routine clinical indicators associated with failure to meet NPTR criteria (no effective nocturnal erection). Methods: A total of 519 patients with erectile dysfunction completed two consecutive nights of RigiScan monitoring and were divided into effective and no-effective nocturnal erection groups. Data were split 7:3 into training (n = 364) and internal validation (n = 155) sets. Feature selection (univariate logistic regression, Boruta, LASSO) was performed exclusively in the training set. Five models (LR, RF, SVM, LightGBM, XGBoost) were constructed. The classification threshold was determined in the training set and fixed in the validation set. Performance was assessed using AUC with bootstrap 95% CIs, Brier score, calibration slope and intercept, sensitivity, specificity, PPV, and NPV. Nested cross-validation (5 × 3) was performed. SHAP interpreted the best model. Results: The effective group comprised 389 patients and the no-effective group 130. Six variables were selected: HbA1c, GLU, Smoke, Hypertension, Age, and BMI. In the validation set, LR achieved the highest AUC (0.779, 95% CI 0.692–0.861), followed by LGBM (0.718), XGB (0.700), RF (0.699), and SVC (0.646). DeLong’s test showed LR significantly outperformed RF (p = 0.028) and SVC (p = 0.009), but not LGBM or XGB. In nested cross-validation, LR also had a higher mean AUC than RF (0.726 ± 0.052 vs 0.666 ± 0.034). LR showed the lowest Brier score (0.151) and calibration slope closest to 1 (1.258). SHAP identified BMI, GLU, and Age as the top three contributors. Conclusions: Conventional metabolic indicators achieved only moderate discrimination. BMI, GLU, and HbA1c were consistently associated with failure to meet NPTR criteria. LR was the most robust model but cannot replace RigiScan monitoring. These findings should be interpreted as associations, not causal relationships.
SN - 1664-2392
ER -