Deep Machine Learning of High Dimensional Peripheral Blood Flow Cytometric Phenotyping Data for identifying Prostate Cancer and its Clinical Risk in Asymptomatic Men

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 (CD8+CD45RA-CD27-CD28- (CD8+ Effector Memory cells), CD4+CD45RA-CD27-CD28- (CD4+ Effector Memory cells), CD4+CD45RA+CD27-CD28- (CD4+ Terminally Differentiated Effector Memory Cells re-expressing CD45RA), CD3-CD19+ (B cells), CD3+CD56+CD8+CD4+ (NKT cells) 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.

本研究采用多参数全血流式细胞术，对130例前列腺特异性抗原（Prostate-Specific Antigen, PSA）水平升高的无症状男性的外周血进行免疫谱分析。其中，后续经活检证实，42例被诊断为良性前列腺疾病，88例被诊断为前列腺癌（Prostate Cancer, PCa）。本研究构建了双向长短期记忆深度神经网络（bidirectional Long Short-Term Memory Deep Neural Network, biLSTM）模型，用于检测男性体内前列腺癌的存在情况，该模型将此前已确认的表型特征与年龄相结合，这些表型特征包括：CD8+CD45RA-CD27-CD28-（CD8+效应记忆细胞）、CD4+CD45RA-CD27-CD28-（CD4+效应记忆细胞）、CD4+CD45RA+CD27-CD28-（重新表达CD45RA的CD4+终末分化效应记忆细胞）、CD3-CD19+（B细胞）、CD3+CD56+CD8+CD4+（自然杀伤T细胞，NKT cells）。该前列腺癌检出模型在未参与训练与验证的测试集上的性能表现为：准确率（Accuracy, Acc）为86.79%（±0.10），灵敏度（Sensitivity）为82.78%（±0.15），特异度（Specificity）为95.83%（±0.11），曲线下面积（Area Under Curve, AUC）为89.31%（±0.07），操作点假阳性率（Operating Point-False Positive Rate, ORP-FPR）为7.50%（±0.20），操作点真阳性率（Operating Point-True Positive Rate, ORP-TPR）为84.44%（±0.14）。第二个biLSTM风险模型将免疫表型特征与PSA相结合，用于预测前列腺癌患者是否存在高危疾病（采用D'Amico风险分级标准定义），该模型的性能表现为：准确率为94.90%（±6.29），灵敏度为92%（±21.39），特异度为96.11%（±0.00），曲线下面积为94.06%（±10.69），操作点假阳性率为3.89%（±0.00），操作点真阳性率为92%（±21.39）。联合流式细胞术与PSA检测前列腺癌时，其操作点假阳性率低于单独使用PSA检测的情况。本研究证实，基于外周血表型谱的人工智能方法，能够区分良性前列腺疾病与前列腺癌，并可预测PSA水平升高的无症状男性的临床风险。

搜集汇总

背景与挑战

背景概述

该数据集包含130名无症状但PSA水平升高的男性的外周血流式细胞术表型数据，用于通过双向LSTM深度学习模型识别前列腺癌及其临床风险。数据集提供了两个模型的性能结果：一个用于检测前列腺癌存在（测试集准确率约86.79%），另一个结合PSA预测高风险疾病（准确率约94.90%），旨在辅助前列腺疾病的诊断和风险评估。