基于人体血液学检测的机器学习辅助泌尿系肿瘤筛查

Assisted Screening of Urological Carcinoma by Deep Learning Based on Human Hematological Examination

目的探索应用人工智能机器学习算法单纯基于肝、肾功等血液学检查来辅助筛查泌尿系统肿瘤。方法分别利用支持向量机和神经网络算法对3136例正常人员和泌尿系统恶性肿瘤患者肝肾功数据进行分析,找到肝肾功数据与泌尿系统恶性肿瘤的相关性。结果对于泌尿系统恶性肿瘤通过5次交叉验证的最优平均分类准确率达到了92.05%,支持向量机与神经网络算法结果基本一致。结论机器学习算法可以单纯通过肝、肾功等血液学检测分类正常人和泌尿系统恶性肿瘤患者,表明该方法有望成为一种泌尿系统肿瘤辅助筛查手段。

Objective To explore a new assist method in the diagnosis of urological carcinoma based on routine hematological examination by deep learning. Method The support vector machine （ SVM）and artificial neural network（ ANN）were applied to distinguish the urological carcinoma by analyzing the data of routine hemato logical examination from 3163 patients including normal persons and urological carcinoma cases. Results The average accuracy rate of deep learning method through 5 cross validation was 92. 05% for urological urological carcinoma cases. The accuracy was no significant differences between SVM and ANN. Conclusions There is probability to classify normal and urological carcinoma patients by using deep learning method on the routine hematological examination.