Purpose

Robust prediction of progression on active surveillance (AS) for prostate cancer can allow for risk-adapted protocols. To date, models predicting progression on AS have invariably used traditional statistical approaches. We sought to evaluate whether a machine learning (ML) approach could improve prediction of progression on AS.

Patients and Methods

We performed a retrospective cohort study of patients diagnosed with very-low or low-risk prostate cancer between 1997 and 2016 and managed with AS at our institution. In the training set, we trained a traditional logistic regression (T-LR) classifier, and alternate ML classifiers (support vector machine, random forest, a fully connected artificial neural network, and ML-LR) to predict grade-progression. We evaluated model performance in the test set. The primary performance metric was the F1 score.

Results

Our cohort included 790 patients. With a median follow-up of 6.29 years, 234 developed grade-progression. In descending order, the F1 scores were: support vector machine 0.586 (95% CI 0.579 – 0.591), ML-LR 0.522 (95% CI 0.513 – 0.526), artificial neural network 0.392 (95% CI 0.379 – 0.396), random forest 0.376 (95% CI 0.364 – 0.380), and T-LR 0.182 (95% CI 0.151 – 0.185). All alternate ML models had a significantly higher F1 score than the T-LR model (all p <0.001).

Conclusion

In our study, ML methods significantly outperformed T-LR in predicting progression on AS for prostate cancer. While our specific models require further validation, we anticipate that a ML approach will help produce robust prediction models that will facilitate individualized risk-stratification in prostate cancer AS.

中文翻译：

---

一种预测前列腺癌主动监测进展的机器学习方法

目的

对前列腺癌主动监测 (AS) 进展的稳健预测可以允许风险适应方案。迄今为止，预测 AS 进展的模型总是使用传统的统计方法。我们试图评估机器学习 (ML) 方法是否可以改善 AS 进展的预测。

患者和方法

我们对 1997 年至 2016 年间诊断为极低或低风险前列腺癌并在我们机构接受 AS 治疗的患者进行了一项回顾性队列研究。在训练集中，我们训练了传统逻辑回归 (T-LR) 分类器和替代 ML 分类器（支持向量机、随机森林、完全连接的人工神经网络和 ML-LR）来预测成绩进展。我们评估了测试集中的模型性能。主要性能指标是 F1 分数。

结果

我们的队列包括 790 名患者。中位随访时间为 6.29 年，234 人出现了等级进展。按降序排列，F1 分数为：支持向量机 0.586（95% CI 0.579 – 0.591），ML-LR 0.522（95% CI 0.513 – 0.526），人工神经网络 0.392（95% CI 0.379 – 0.396），随机森林0.376（95% CI 0.364 – 0.380）和 T-LR 0.182（95% CI 0.151 – 0.185）。所有替代 ML 模型的 F1 分数都明显高于 T-LR 模型（所有p <0.001）。

结论

在我们的研究中，ML 方法在预测前列腺癌 AS 进展方面明显优于 T-LR。虽然我们的特定模型需要进一步验证，但我们预计 ML 方法将有助于生成稳健的预测模型，从而促进前列腺癌 AS 的个体化风险分层。