Department of Computer Science, Loughborough University, Loughborough, United Kingdom.
John van Geest Cancer Research Centre, School of Science and Technology, Nottingham Trent University, Nottingham, United Kingdom.
Front Immunol. 2021 Dec 16;12:786828. doi: 10.3389/fimmu.2021.786828. eCollection 2021.
Detecting the presence of prostate cancer (PCa) and distinguishing low- or intermediate-risk disease from high-risk disease early, and without the need for potentially unnecessary invasive biopsies remains a significant clinical challenge. The aim of this study is to determine whether the T and B cell phenotypic features which we have previously identified as being able to distinguish between benign prostate disease and PCa in asymptomatic men having Prostate-Specific Antigen (PSA) levels < 20 ng/ml can also be used to detect the presence and clinical risk of PCa in a larger cohort of patients whose PSA levels ranged between 3 and 2617 ng/ml. The peripheral blood of 130 asymptomatic men having elevated Prostate-Specific Antigen (PSA) levels was immune profiled using multiparametric whole blood flow cytometry. Of these men, 42 were subsequently diagnosed as having benign prostate disease and 88 as having PCa on biopsy-based evidence. We built a bidirectional Long Short-Term Memory Deep Neural Network (biLSTM) model for detecting the presence of PCa in men which combined the previously-identified phenotypic features (CD8CD45RACD27CD28 (), CD4CD45RACD27CD28 (), CD4CD45RACD27CD28 (), CD3CD19 (), CD3CD56CD8CD4 () with Age. The performance of the PCa presence 'detection' model was: Acc: 86.79 ( ± 0.10), Sensitivity: 82.78% (± 0.15); Specificity: 95.83% (± 0.11) on the test set (test set that was not used during training and validation); AUC: 89.31% (± 0.07), ORP-FPR: 7.50% (± 0.20), ORP-TPR: 84.44% (± 0.14). A second biLSTM 'risk' model combined the immunophenotypic features with PSA to predict whether a patient with PCa has high-risk disease (defined by the D'Amico Risk Classification) achieved the following: Acc: 94.90% (± 6.29), Sensitivity: 92% (± 21.39); Specificity: 96.11 (± 0.00); AUC: 94.06% (± 10.69), ORP-FPR: 3.89% (± 0.00), ORP-TPR: 92% (± 21.39). The ORP-FPR for predicting the presence of PCa when combining FC+PSA was lower than that of PSA alone. This study demonstrates that AI approaches based on peripheral blood phenotyping profiles can distinguish between benign prostate disease and PCa and predict clinical risk in asymptomatic men having elevated PSA levels.
检测前列腺癌（PCa）的存在，并在早期区分低风险或中风险疾病与高风险疾病，同时避免潜在的不必要的侵入性活检，这仍然是一个重大的临床挑战。本研究旨在确定我们之前已经确定的能够区分无症状男性良性前列腺疾病和前列腺特异性抗原（PSA）水平<20ng/ml 的 PCa 的 T 和 B 细胞表型特征是否也可用于检测更大队列中 PSA 水平在 3 至 2617ng/ml 之间的 PCa 的存在和临床风险。使用多参数全血流式细胞术对 130 名 PSA 水平升高的无症状男性的外周血进行免疫分析。其中 42 人随后被诊断为良性前列腺疾病，88 人被诊断为基于活检的 PCa。我们构建了一个双向长短期记忆深度神经网络（biLSTM）模型，用于检测男性 PCa 的存在，该模型结合了先前确定的表型特征（CD8CD45RACD27CD28（）、CD4CD45RACD27CD28（）、CD4CD45RACD27CD28（）、CD3CD19（）、CD3CD56CD8CD4（）与年龄。PCa 存在“检测”模型的性能为：Acc：86.79（±0.10），敏感性：82.78%（±0.15）；特异性：95.83%（±0.11）在测试集（未用于训练和验证的测试集）上；AUC：89.31%（±0.07），ORP-FPR：7.50%（±0.20），ORP-TPR：84.44%（±0.14）。第二个 biLSTM“风险”模型将免疫表型特征与 PSA 相结合，以预测患有 PCa 的患者是否患有高危疾病（由 D'Amico 风险分类定义），达到以下标准：Acc：94.90%（±6.29），敏感性：92%（±21.39）；特异性：96.11（±0.00）；AUC：94.06%（±10.69），ORP-FPR：3.89%（±0.00），ORP-TPR：92%（±21.39）。当结合 FC+PSA 预测 PCa 的存在时，ORP-FPR 低于 PSA 单独预测时的 ORP-FPR。本研究表明，基于外周血表型谱的人工智能方法可以区分良性前列腺疾病和 PCa，并预测 PSA 水平升高的无症状男性的临床风险。
