PSA-based machine learning model improves prostate cancer risk stratification in a screening population
PSA-based machine learning model improves prostate cancer risk stratification in a screening population
复制标题
DOI：
10.1007/s00345-020-03392-9
复制
发表时间：
2020-08-03
影响因子：
3.4
通讯作者：
Smith, Elliot
中科院分区：
文献类型：
--
作者：
Perera, Marlon;Mirchandani, Rohan;Smith, Elliot
背景大多数前列腺癌的诊断是通过检测血清前列腺特异性抗原（PSA）水平来实现的。尽管如此，PSA的诊断准确性仍存在局限性。考虑患者的人口统计学因素和PSA的生化指标可能会改善前列腺癌的危险分层。我们的目的是开发一个现代的，准确的和成本效益的模型，基于客观的措施，以提高前列腺癌风险分层的准确性。方法收集当地一家机构的数据，并结合前列腺、肺癌、结直肠癌和卵巢癌筛查试验（PLCO）数据库中检索的患者数据。使用4548名患者的数据集，开发了一个机器学习模型，并使用PSA、游离PSA、年龄和游离PSA与总PSA（FTR）的比值进行了训练。该模型在涉及3638名患者的数据集上进行了训练，然后在910名患者的单独数据集上进行了测试。与单独PSA（AUC 0.63）、年龄（AUC 0.52）、游离PSA（AUC 0.50）和单独FTR（AUC 0.65）相比，该模型改善了对前列腺癌（AUC 0.72）的预测。当选择操作点使得模型的灵敏度为80%时，模型的特异性为45.3%。继发于该模型的AUC获益与样本量相关，当评估队列的一个子集时，观察到AUC为0.64。结论密集神经网络模型的建立提高了前列腺癌筛查的诊断准确率。这些结果表明，当使用生化参数时，机器学习方法在前列腺癌风险分层中具有额外的效用。
Context The majority of prostate cancer diagnoses are facilitated by testing serum Prostate Specific Antigen (PSA) levels. Despite this, there are limitations to the diagnostic accuracy of PSA. Consideration of patient demographic factors and biochemical adjuncts to PSA may improve prostate cancer risk stratification. We aimed to develop a contemporary, accurate and cost-effective model based on objective measures to improve the accuracy of prostate cancer risk stratification. Methods Data were collated from a local institution and combined with patient data retrieved from the Prostate, Lung, Colorectal and Ovarian Cancer screening Trial (PLCO) database. Using a dataset of 4548 patients, a machine learning model was developed and trained using PSA, free-PSA, age and free-PSA to total PSA (FTR) ratio. Results The model was trained on a dataset involving 3638 patients and was then tested on a separate set of 910 patients. The model improved prediction for prostate cancer (AUC 0.72) compared to PSA alone (AUC 0.63), age (AUC 0.52), free-PSA (AUC 0.50) and FTR alone (AUC 0.65). When an operating point is chosen such that the sensitivity of the model is 80% the specificity of the model is 45.3%. The benefit in AUC secondary to the model was related to sample size, with AUC of 0.64 observed when a subset of the cohort was assessed. Conclusions Development of a dense neural network model improved the diagnostic accuracy in screening for prostate cancer. These results demonstrate an additional utility of machine learning methods in prostate cancer risk stratification when using biochemical parameters.