ABSTRACT
PURPOSE: Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa). MATERIALS AND METHODS: A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 and BCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model was evaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models. RESULTS: We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model. CONCLUSIONS: Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.
Subject(s)
Neurilemmoma/diagnosis , Pancreatic Neoplasms/diagnosis , Adult , Female , Humans , Immunohistochemistry , Magnetic Resonance Imaging , Male , Middle Aged , Neurilemmoma/pathology , Neurilemmoma/surgery , Pancreas/diagnostic imaging , Pancreas/pathology , Pancreas/surgery , Pancreatic Neoplasms/pathology , Pancreatic Neoplasms/surgery , Retrospective StudiesABSTRACT
Some physiological and ethical problems make it difficult to obtain semen samples from adolescents with varicocele (VC) and to directly evaluate their fertility. Therefore we can only rely on indirect methods to assess the influence of VC on the future fertility of the adolescent patients. Most of the VC adolescents may have normal semen parameters in the adulthood. Thus whether and when to intervene in adolescent VC remain a controversy in andrology. Physical examination is the most common method for screening adolescent VC and ultrasonography is very effective for its diagnosis and evaluation. Other important diagnostic indicators include the widely accepted testicular atrophy index, recently proposed peak retrograde venous flow, total testis volume, and scrotal temperature. Based on the latest literature, this review offers some proposals for the evaluation and intervention of adolescent VC.
Subject(s)
Infertility, Male/diagnosis , Varicocele/diagnosis , Adolescent , Humans , Male , Semen , Semen Analysis , Testis/pathologyABSTRACT
OBJECTIVE: To investigate the correlation of vasectomy with the risk of prostate cancer in Chinese men. METHODS: We systematically searched the databases CNKI, VIP, Wanfang, PubMed, Embase, and Cochrane Library for the literature relating the relationship between vasectomy and the risk of prostate cancer in Chinese males up to December 2014. According to the inclusion and exclusion criteria, two investigators independently selected the eligible publications, evaluated their quality, and extracted relevant information, followed by a meta-analysis with the software STATA 12.0. RESULTS: Nine studies were included in the analysis involving 1 202 cases of prostate cancer and 4,496 controls. Random-effect model analysis revealed no statistically significant correlation between vasectomy and the risk of prostate cancer (OR = 1.05; 95% CI 0.62-1.79), with an obvious heterogeneity (P < 0.001, I2 = 85.7%). No significant publication bias was found among the included studies (Egger, P = 0.824; Begg, P = 0.348). CONCLUSION: The results of our meta-analysis do not support the association of vasectomy with the increased risk of prostate cancer in Chinese population.