Interpretable machine learning models for predicting clinical pregnancies associated with surgical sperm retrieval from testes of different etiologies: a retrospective study.

BACKGROUND: The relationship between surgical sperm retrieval of different etiologies and clinical pregnancy is unclear. We aimed to develop a robust and interpretable machine learning (ML) model for predicting clinical pregnancy using the SHapley Additive exPlanation (SHAP) association of surgical sperm retrieval from testes of different etiologies. METHODS: A total of 345 infertile couples who underwent intracytoplasmic sperm injection (ICSI) treatment with surgical sperm retrieval due to different etiologies from February 2020 to March 2023 at the reproductive center were retrospectively analyzed. The six machine learning (ML) models were used to predict the clinical pregnancy of ICSI. After evaluating the performance characteristics of the six ML models, the Extreme Gradient Boosting model (XGBoost) was selected as the best model, and SHAP was utilized to interpret the XGBoost model for predicting clinical pregnancies and to reveal the decision-making process of the model. RESULTS: Combining the area under the receiver operating characteristic curve (AUROC), accuracy, precision, recall, F1 score, brier score, and the area under the precision-recall (P-R) curve (AP), the XGBoost model has the best performance (AUROC: 0.858, 95% confidence interval (CI): 0.778-0.936, accuracy: 79.71%, brier score: 0.151). The global summary plot of SHAP values shows that the female age is the most important feature influencing the model output. The SHAP plot showed that younger age in females, bigger testicular volume (TV), non-tobacco use, higher anti-müllerian hormone (AMH), lower follicle-stimulating hormone (FSH) in females, lower FSH in males, the temporary ejaculatory disorders (TED) group, and not the non-obstructive azoospermia (NOA) group all resulted in an increased probability of clinical pregnancy. CONCLUSIONS: The XGBoost model predicts clinical pregnancies associated with testicular sperm retrieval of different etiologies with high accuracy, reliability, and robustness. It can provide clinical counseling decisions for patients with surgical sperm retrieval of various etiologies.

A Phase 1/2 Multicenter Randomized Trial of Local Ablation plus Toripalimab versus Toripalimab Alone for Previously Treated Unresectable Hepatocellular Carcinoma.

PURPOSE: To assess the safety and efficacy of local ablation plus PD-1 inhibitor toripalimab in previously treated unresectable hepatocellular carcinoma (HCC). PATIENTS AND METHODS: In the multicenter, two-stage, and randomized phase 1/2 trial, patients were randomly assigned to receive toripalimab alone (240 mg, every 3 weeks), subtotal local ablation followed by toripalimab starting on post-ablation day 3 (Schedule D3), or on post-ablation day 14 (Schedule D14). The first endpoint of stage 1 was to determine which combination schedule could continue and progression-free survival (PFS) as the primary endpoint for stage 1/2. RESULTS: A total of 146 patients were recruited. During stage 1, Schedule D3 achieved numerically higher objective response rate (ORR) than Schedule D14 for non-ablation lesions (37.5% vs. 31.3%), and was chosen for stage 2 evaluation. For the entire cohort of both stages, patients with Schedule D3 had a significantly higher ORR than with toripalimab alone (33.8% vs. 16.9%; P = 0.027). Moreover, patients with Schedule D3 had improved median PFS (7.1 vs. 3.8 months; P < 0.001) and median overall survival (18.4 vs. 13.2 months; P = 0.005), as compared with toripalimab alone. In addition, six (9%) patients with toripalimab, eight (12%) with Schedule D3, and 4 (25%) with Schedule D14 developed grade 3 or 4 adverse events, and one patient (2%) with Schedule D3 manifested grade 5 treatment-related pneumonitis. CONCLUSIONS: In patients with previously treated unresectable HCC, subtotal ablation plus toripalimab improved the clinical efficacy as compared with toripalimab alone, with an acceptable safety profile.

[Impacts of different procedures of testicular sperm retrieval on testicular function and antisperm antibodies in azoospermia patients].

OBJECTIVE: To investigate the influence of different procedures of testicular sperm retrieval on the levels of serum inhibin B (INHB), antisperm antibodies (AsAb), follicle-stimulating hormone (FSH), and testosterone (T) in patients with azoospermia. METHODS: We randomly assigned 210 azoospermia patients to receive testicular sperm extraction (TESE, n = 50), testicular sperm aspiration (TESA, n = 56), testicular fine needle aspiration (TEFNA, n = 64), or microscopic TESE (micro-TESE, n = 40). We measured the levels of serum INHB, FSH, and T and the positive rate of AsAb before and at 1 and 3 months after surgery. RESULTS: Compared with the baseline, the levels of serum FSH at 1 and 3 months after surgery showed no statistically significant differences in the TESE (ï¼»8.51 ± 4.34ï¼½ vs ï¼»8.76 ± 3.07ï¼½ and ï¼»7.24 ± 3.32ï¼½ IU/L, P >0.05), TESA (ï¼»7.70 ± 2.72ï¼½ vs ï¼»7.90 ± 4.57ï¼½ and ï¼»8.04 ± 3.65ï¼½ IU/L, P >0.05), TEFNA (ï¼»6.04 ± 3.17ï¼½ vs ï¼»6.08 ± 2.70ï¼½ and ï¼»6.10 ± 3.32ï¼½ IU/L, P >0.05), or micro-TESE group (ï¼»6.59 ± 2.74ï¼½ vs ï¼»6.89 ± 1.78ï¼½ and ï¼»6.75 ± 2.57ï¼½ IU/L, P >0.05); the positive rate of AsAb (IgM) was significantly increased at 1 month in the TESE (0.00 vs 14.00%, P <0.05) and micro-TESE groups (2.50% vs 15.00%, P <0.05), while the serum T level markedly decreased in the two groups (ï¼»16.52 ± 6.25ï¼½ vs ï¼»9.25 ± 5.76ï¼½ nmol/L and ï¼»14.16 ± 5.45ï¼½ vs ï¼»8.23 ± 4.12ï¼½ nmol/L, P <0.05); the levels of serum INHB were remarkably reduced at 1 and 3 months in the TESE (ï¼»70.56 ± 23.17ï¼½ vs ï¼»42.63 ± 15.34ï¼½ and ï¼»44.05 ± 18.47ï¼½ pg/ml, P <0.05), TESA (ï¼»68.71 ± 14.74ï¼½ vs ï¼»40.55 ± 20.51ï¼½ and ï¼»42.11 ± 19.34ï¼½ pg/ml, P <0.05), TEFNA (ï¼»76.81 ± 27.04ï¼½ vs ï¼»46.31 ± 19.28ï¼½ and ï¼»48.32 ± 20.54ï¼½ pg/ml, P <0.05), and micro-TESE groups (ï¼»74.74 ± 28.35ï¼½ vs ï¼»45.27 ± 18.83ï¼½ and ï¼»47.64 ± 28.34ï¼½ pg/ml, P <0.05), but with no statistically significant differences among the four groups (P >0.05). CONCLUSIONS: Different procedures of testicular sperm retrieval have different impacts on the testicular function and AsAb in patients with azoospermia.