Sun Dehua, Chen Wei, He Jun, He Yongjian, Jiang Haoqin, Jiang Hong, Liu Dandan, Li Lu, Liu Min, Mao Zhigang, Qu Chenxue, Qu Linlin, Sun Ziyong, Wang Jianbiao, Wu Wenjing, Wang Xuefeng, Xu Wei, Xing Ying, Zhang Chi, Zhang Jingxian, Zheng Lei, Zhang Shihong, Ye Bo, Guan Ming
Department of Clinical Laboratory, Nanfang Hospital, Guangzhou, 516006, China.
Department of Clinical Laboratory, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710061, China.
BMC Med Inform Decis Mak. 2025 Feb 11;25(1):72. doi: 10.1186/s12911-025-02892-1.
Screening of malignant hematological diseases is of great importance for their diagnosis and subsequent treatment. This study constructed an optimal screening model for malignant hematological diseases based on routine blood cell parameters.
The venous blood samples of 1751 patients collected from 10 tertiary hospitals in China were divided into a training set (1223 cases) and a validation set (528 cases). In addition to the clinical diagnostic information of the samples in the training set, 26 blood cell parameters including morphological parameters were selected using manual screening and filtering to construct eight machine learning models. These models were used to identify hematological malignancies among the validation set.
Comparison of the discrimination, calibration and clinical detection performance of the eight machine learning models revealed that the artificial neural network (ANN) model performed the optimal in identifying malignant haematological diseases in the validation set (528 cases), with an area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity of 0.906, 0.857, 0.832 and 0.884, respectively.
The ANN model constructed can be used for screening of malignant hematological diseases, especially in primary hospitals that lack comprehensive diagnosis, and this ANN model will help patients to get diagnosis and treatment of malignant hematological diseases as early as possible.
恶性血液病的筛查对其诊断及后续治疗至关重要。本研究基于常规血细胞参数构建了恶性血液病的最佳筛查模型。
收集来自中国10家三级医院的1751例患者的静脉血样本，分为训练集（1223例）和验证集（528例）。除了训练集中样本的临床诊断信息外，通过人工筛选和过滤选择包括形态学参数在内的26项血细胞参数，构建8种机器学习模型。这些模型用于在验证集中识别血液系统恶性肿瘤。
对8种机器学习模型的区分度、校准度和临床检测性能进行比较，结果显示人工神经网络（ANN）模型在验证集（528例）中识别恶性血液病的表现最佳，其受试者工作特征曲线（AUC）下面积、准确率、灵敏度和特异度分别为0.906、0.857、0.832和0.884。
构建的ANN模型可用于恶性血液病的筛查，尤其是在缺乏综合诊断能力的基层医院，该ANN模型将有助于患者尽早获得恶性血液病的诊断和治疗。
