Department of Urology, Hospital Medicine Center, Seoul National University Hospital, Seoul, South Korea.
Department of Urology, Seoul National University College of Medicine, Seoul, South Korea.
BJU Int. 2020 Dec;126(6):694-703. doi: 10.1111/bju.15122. Epub 2020 Aug 4.
To develop and validate a risk calculator for prostate cancer (PCa) and clinically significant PCa (csPCa) using explainable artificial intelligence (XAI).
We used data of 3791 patients to develop and validate the risk calculator. We initially divided the data into development and validation sets. An extreme gradient-boosting algorithm was applied to the development calculator using five-fold cross-validation with hyperparameter tuning following feature selection in the development set. The model feature importance was determined based on the Shapley value. The area under the curve (AUC) of the receiver operating characteristic curve was analysed for each validation set of the calculator.
Approximately 1216 (32.7%) and 562 (14.8%) patients were diagnosed with PCa and csPCa. The data of 2843 patients were used for development, whereas the data of 948 patients were used as a test set. We selected the variables for each PCa and csPCa risk calculation according to the least absolute shrinkage and selection operator regression. The AUC of the final PCa model was 0.869 (95% confidence interval [CI] 0.844-0.893), whereas that of the csPCa model was 0.945 (95% CI 0.927-0.963). The prostate-specific antigen (PSA) level, free PSA level, age, prostate volume (both the transitional zone and total), hypoechoic lesions on ultrasonography, and testosterone level were found to be important parameters in the PCa model. The number of previous biopsies was not associated with the risk of csPCa, but was negatively associated with the risk of PCa.
We successfully developed and validated a decision-supporting tool using XAI for calculating the probability of PCa and csPCa prior to prostate biopsy.
使用可解释人工智能（XAI）开发和验证前列腺癌（PCa）和临床显著前列腺癌（csPCa）的风险计算器。
我们使用 3791 名患者的数据来开发和验证风险计算器。我们最初将数据分为开发集和验证集。在开发集中使用特征选择和超参数调整后，使用五重交叉验证应用极端梯度提升算法到开发计算器中。基于 Shapley 值确定模型特征的重要性。分析计算器每个验证集的接收者操作特征曲线下面积（AUC）。
约 1216（32.7%）和 562（14.8%）名患者被诊断为 PCa 和 csPCa。2843 名患者的数据用于开发，948 名患者的数据用于测试集。我们根据最小绝对收缩和选择算子回归选择每个 PCa 和 csPCa 风险计算的变量。最终 PCa 模型的 AUC 为 0.869（95%置信区间[CI]0.844-0.893），csPCa 模型的 AUC 为 0.945（95% CI 0.927-0.963）。前列腺特异性抗原（PSA）水平、游离 PSA 水平、年龄、前列腺体积（移行区和总前列腺体积）、超声检查中的低回声病变和睾酮水平被发现是 PCa 模型中的重要参数。既往活检次数与 csPCa 的风险无关，但与 PCa 的风险呈负相关。
我们成功地使用 XAI 开发和验证了一种用于计算前列腺活检前 PCa 和 csPCa 概率的决策支持工具。
