Satır Atilla, Üstündağ Yasemin, Yeşil Meryem Rümeysa, Huysal Kağan
Department of Urology, University of Health Sciences, Bursa Yuksek Ihtisas Training and Research Hospital, Bursa, Turkey.
Department of Medical Biochemistry, University of Health Sciences, Bursa Yuksek Ihtisas Training and Research Hospital, Bursa, Turkey.
J Clin Lab Anal. 2025 Feb;39(3):e25143. doi: 10.1002/jcla.25143. Epub 2025 Jan 19.
In this study, we attempted to select the optimum cases for a prostate biopsy based on routine laboratory test results in addition to prostate-specific antigen (PSA) blood test using H2O automated machine learning (AutoML) software, which includes many common machine learning algorithms.
The study included 737 patients (46-88 years old). Routine laboratory measurements were used to train machine learning models using H2O AutoML. We created a model that classifies prostate biopsy results as malignant or benign. The performance of the best model was evaluated using the area under the receiver operating characteristic curve (AUC), log-loss metric, F1 score, positive predictive value (PPV), negative predictive value (NPV), sensitivity, and specificity. The model's performance was evaluated through the SHapley Additive exPlanations (SHAP) analysis feature-based interpretation method applied to comprehend the machine learning model.
The gradient boosting machine model was the most successful. The best result was obtained in the model with 11 parameters, including PSA, free PSA, free PSA to PSA, hemoglobin, neutrophils, platelets, neutrophil-to-lymphocyte ratio (NLR), glucose, platelet-to-lymphocyte ratio (PLR), lymphocytes, and age. The AUC of this model was 0.72, the specificity was 0.84, the PPV was 0.65, the NPV was 0.69, and the accuracy was 0.68.
Our results suggest that adding only routine laboratory parameters to the PSA test and developing machine learning algorithms can help reduce the number of unnecessary prostate biopsies without overlooking the diagnosis of PCa.
在本研究中，我们尝试使用包含许多常见机器学习算法的H2O自动化机器学习（AutoML）软件，除前列腺特异性抗原（PSA）血液检测外，根据常规实验室检测结果选择前列腺活检的最佳病例。
该研究纳入了737例患者（年龄46 - 88岁）。使用常规实验室测量数据通过H2O AutoML训练机器学习模型。我们创建了一个将前列腺活检结果分类为恶性或良性的模型。使用受试者操作特征曲线下面积（AUC）、对数损失度量、F1分数、阳性预测值（PPV）、阴性预测值（NPV）、敏感性和特异性来评估最佳模型的性能。通过应用SHapley加性解释（SHAP）分析基于特征的解释方法来评估模型性能，以理解机器学习模型。
梯度提升机模型最为成功。在包含PSA、游离PSA、游离PSA与PSA比值、血红蛋白、中性粒细胞、血小板、中性粒细胞与淋巴细胞比值（NLR）、葡萄糖、血小板与淋巴细胞比值（PLR）、淋巴细胞和年龄这11个参数的模型中获得了最佳结果。该模型的AUC为0.72，特异性为0.84，PPV为0.65，NPV为0.69，准确率为0.68。
我们的结果表明，在PSA检测中仅添加常规实验室参数并开发机器学习算法有助于减少不必要的前列腺活检数量，同时不会忽视前列腺癌的诊断。
