Hasannejadasl Hajar, Osong Biche, Bermejo Inigo, van der Poel Henk, Vanneste Ben, van Roermund Joep, Aben Katja, Zhang Zhen, Kiemeney Lambertus, Van Oort Inge, Verwey Renee, Hochstenbach Laura, Bloemen Esther, Dekker Andre, Fijten Rianne R R
Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Reproduction, Maastricht University Medical Center, Maastricht, Netherlands.
Department of Urology, Netherlands Cancer Institute, Amsterdam, and Amsterdam University Medical Centers, Amsterdam, Netherlands.
Front Oncol. 2023 Apr 12;13:1168219. doi: 10.3389/fonc.2023.1168219. eCollection 2023.
Urinary incontinence (UI) is a common side effect of prostate cancer treatment, but in clinical practice, it is difficult to predict. Machine learning (ML) models have shown promising results in predicting outcomes, yet the lack of transparency in complex models known as "black-box" has made clinicians wary of relying on them in sensitive decisions. Therefore, finding a balance between accuracy and explainability is crucial for the implementation of ML models. The aim of this study was to employ three different ML classifiers to predict the probability of experiencing UI in men with localized prostate cancer 1-year and 2-year after treatment and compare their accuracy and explainability.
We used the ProZIB dataset from the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) which contained clinical, demographic, and PROM data of 964 patients from 65 Dutch hospitals. Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms were applied to predict (in)continence after prostate cancer treatment.
All models have been externally validated according to the TRIPOD Type 3 guidelines and their performance was assessed by accuracy, sensitivity, specificity, and AUC. While all three models demonstrated similar performance, LR showed slightly better accuracy than RF and SVM in predicting the risk of UI one year after prostate cancer treatment, achieving an accuracy of 0.75, a sensitivity of 0.82, and an AUC of 0.79. All models for the 2-year outcome performed poorly in the validation set, with an accuracy of 0.6 for LR, 0.65 for RF, and 0.54 for SVM.
The outcomes of our study demonstrate the promise of using non-black box models, such as LR, to assist clinicians in recognizing high-risk patients and making informed treatment choices. The coefficients of the LR model show the importance of each feature in predicting results, and the generated nomogram provides an accessible illustration of how each feature impacts the predicted outcome. Additionally, the model's simplicity and interpretability make it a more appropriate option in scenarios where comprehending the model's predictions is essential.
尿失禁（UI）是前列腺癌治疗的常见副作用，但在临床实践中难以预测。机器学习（ML）模型在预测结果方面显示出了有前景的结果，然而，被称为“黑箱”的复杂模型缺乏透明度，这使得临床医生在敏感决策中对依赖它们持谨慎态度。因此，在准确性和可解释性之间找到平衡对于ML模型的应用至关重要。本研究的目的是使用三种不同的ML分类器来预测局限性前列腺癌男性患者治疗后1年和2年出现UI的概率，并比较它们的准确性和可解释性。
我们使用了荷兰综合癌症组织（荷兰综合癌症中心；IKNL）的ProZIB数据集，该数据集包含来自65家荷兰医院的964名患者的临床、人口统计学和患者报告结局（PROM）数据。应用逻辑回归（LR）、随机森林（RF）和支持向量机（SVM）算法来预测前列腺癌治疗后的（尿）失禁情况。
所有模型均根据TRIPOD 3型指南进行了外部验证，并通过准确性、敏感性、特异性和曲线下面积（AUC）评估了它们的性能。虽然所有三个模型都表现出相似的性能，但在预测前列腺癌治疗后1年发生UI的风险时，LR的准确性略高于RF和SVM，准确率达到0.75，敏感性为0.82，AUC为0.79。所有预测2年结局的模型在验证集中表现不佳，LR的准确率为0.6，RF为0.65，SVM为0.54。
我们的研究结果表明，使用非黑箱模型（如LR）有助于临床医生识别高危患者并做出明智的治疗选择。LR模型的系数显示了每个特征在预测结果中的重要性，生成的列线图直观展示了每个特征如何影响预测结果。此外，该模型的简单性和可解释性使其在理解模型预测至关重要的场景中成为更合适的选择。
