A multimodal machine learning model for predicting reproductive outcomes in the rare congenital hypogonadotropic hypogonadism after treatment.
5 affiliations
- 1Department of Diagnostic Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China.
- 2Department of Endocrinology and Metabolism, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China.
- 3Department of Diagnostic Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China. [email protected].
- 4Department of Endocrinology and Metabolism, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China. [email protected].
- 5Department of Diagnostic Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, 510515, China. [email protected].
Abstract
Objective
Testicular volume serves as a crucial indicator for evaluating therapeutic outcomes in patients with congenital hypogonadotropic hypogonadism (CHH), which is a rare disease. We aim to develop a multimodal machine learning model that integrates clinical data, testicular ultrasonography, and pituitary magnetic resonance imaging (MRI) radiomic features to predict whether testicular volume exceeds 4 mL following treatment in CHH patients.Methods
This study retrospectively included 66 male patients with CHH from 2015 to 2024, with a follow-up period of 12 to 36 months. All patients received gonadotropin or GnRH pulse pump therapy. The patients' visit information was systematically collected, and the peak testicular volume during follow-up was used as the outcome. Multiple machine learning prediction models were constructed using clinical information, initial-visit testicular ultrasound images, and pituitary MRI images, and were evaluated using ten-fold cross-validation. Model performance was compared using the Delong test. Model interpretability was analyzed using SHapley Additive exPlanations (SHAP).Results
A total of 28 patients achieved a testicular volume greater than 4 mL after treatment, indicating favorable reproductive outcomes. The multimodal model that integrated all information demonstrated the highest predictive performance, with an area under the receiver operating characteristic curve (AUC) of 0.932 (95% CI: 0.891-0.997), outperforming the clinical model (AUC = 0.863, 95% CI: 0.747-1.000). The best AUCs for models based solely on ultrasound and MRI radiomic features were 0.798 (95% CI: 0.697-1.000) and 0.680 (95% CI: 0.526-0.868), respectively. The combined imaging model (ultrasound + MRI) yielded an AUC of 0.759 (95% CI: 0.510-0.969). Among the top 10 SHAP-ranked features in the multimodal model, two originated from ultrasound, one from MRI, and seven from clinical variables.Conclusion
The multimodal model, which integrated clinical factors with radiomic features from both ultrasound and magnetic resonance imaging, demonstrated favorable performance in predicting reproductive outcomes in patients with CHH after treatment.
Related
- Recurring and isolated intronic FGFR1 variants as an underdiagnosed cause of congenital hypogonadotropic hypogonadism
- Previously Unrecognized Congenital Hypogonadotropic Hypogonadism in an 89-Year-Old Man: A Case Report.
- Primary Amenorrhea Revealing Adamantinomatous Craniopharyngioma Associated With Central Hypogonadotropic Hypogonadism in an Adolescent Girl: A Case Report
- Restoration of spermatogenesis in a male with prolactinoma-induced hypogonadotropic hypogonadism using follitropin delta and recombinant choriogonadotropin alfa: a case report
- Multimodal imaging features of pelvic ectopic liver combined with type I congenital extrahepatic portosystemic shunt (Abernethy malformation) in a child: a case report
BibTeX
@article{li2026multimodal,
title = {{A multimodal machine learning model for predicting reproductive outcomes in the rare congenital hypogonadotropic hypogonadism after treatment.}},
author = {Xiaomeng Li and Chuyin Ruan and Zebin Wu and Sina Wang and Tianli Liang and Derun Pan and Ying Cao and Weiguo Chen},
journal = {BMC medical imaging},
year = {2026},
month = aug,
doi = {10.1186/s12880-026-02634-3},
url = {https://europepmc.org/article/MED/42963540},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - A multimodal machine learning model for predicting reproductive outcomes in the rare congenital hypogonadotropic hypogonadism after treatment.
AU - Xiaomeng Li
AU - Chuyin Ruan
AU - Zebin Wu
AU - Sina Wang
AU - Tianli Liang
AU - Derun Pan
AU - Ying Cao
AU - Weiguo Chen
PY - 2026
DA - 2026/08/04
JO - BMC medical imaging
DO - 10.1186/s12880-026-02634-3
UR - https://europepmc.org/article/MED/42963540
AB - Objective Testicular volume serves as a crucial indicator for evaluating therapeutic outcomes in patients with congenital hypogonadotropic hypogonadism (CHH), which is a rare disease. We aim to develop a multimodal machine learning model that integrates clinical data, testicular ultrasonography, and pituitary magnetic resonance imaging (MRI) radiomic features to predict whether testicular volume exceeds 4 mL following treatment in CHH patients.Methods This study retrospectively included 66 male patients with CHH from 2015 to 2024, with a follow-up period of 12 to 36 months. All patients received gonadotropin or GnRH pulse pump therapy. The patients' visit information was systematically collected, and the peak testicular volume during follow-up was used as the outcome. Multiple machine learning prediction models were constructed using clinical information, initial-visit testicular ultrasound images, and pituitary MRI images, and were evaluated using ten-fold cross-validation. Model performance was compared using the Delong test. Model interpretability was analyzed using SHapley Additive exPlanations (SHAP).Results A total of 28 patients achieved a testicular volume greater than 4 mL after treatment, indicating favorable reproductive outcomes. The multimodal model that integrated all information demonstrated the highest predictive performance, with an area under the receiver operating characteristic curve (AUC) of 0.932 (95% CI: 0.891-0.997), outperforming the clinical model (AUC = 0.863, 95% CI: 0.747-1.000). The best AUCs for models based solely on ultrasound and MRI radiomic features were 0.798 (95% CI: 0.697-1.000) and 0.680 (95% CI: 0.526-0.868), respectively. The combined imaging model (ultrasound + MRI) yielded an AUC of 0.759 (95% CI: 0.510-0.969). Among the top 10 SHAP-ranked features in the multimodal model, two originated from ultrasound, one from MRI, and seven from clinical variables.Conclusion The multimodal model, which integrated clinical factors with radiomic features from both ultrasound and magnetic resonance imaging, demonstrated favorable performance in predicting reproductive outcomes in patients with CHH after treatment.
SN - 1471-2342
ER -