A novel method for screening malignant hematological diseases by constructing an optimal machine learning model based on blood cell parameters

作者：Dehua Sun, Wei Chen, Jun He, HE Yong-jian, Haoqin Jiang, Hong Jiang, Dandan Liu, Lu Li, Min Liu, Zhigang Mao, Chenxue Qu, Linlin Qu, Ziyong Sun, Jianbiao Wang, Wenjing Wu, Xuefeng Wang, Wei Xu, Ying Xing, Chi Zhang, Jingxian Zhang, Lei Zheng, Shihong Zhang, Bo Ye, Ming Guan · 发表于：BMC Medical Informatics and Decision Making · 年份：2025 · DOI：10.1186/s12911-025-02892-1 · 被引用次数：8 · 研究领域：Digital Imaging for Blood Diseases、AI in cancer detection、Clinical Laboratory Practices and Quality Control

BACKGROUND: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.