通过血液学参数可以预测多细胞血病吗? 一个基于机器学习的研究.
Murat Haskul1, Emin Kaya2, Ahmet Kurtoğlu3
1Department of Medical Oncology, Inonu University, Malatya, Turkey mrthaskul@gmail.com.
Journal of clinical pathology
|July 23, 2025
概括
机器学习算法使用完整血清 (CBC) 参数准确诊断多细胞血症 (PV). 这种方法可以减少对昂贵的测试如JAK2,EPO和骨髓活检 (BMB) 的依赖.
科学领域:
- 血液学 血液学 血液学
- 计算生物学 计算生物学
- 医学诊断 医学诊断 医学诊断
背景情况:
- 多细胞血病 (PV) 诊断传统上依赖于侵入性和昂贵的测试.
- 早期和准确的PV诊断对于有效的患者管理和治疗至关重要.
- 完整血清 (CBC) 参数为诊断建模提供了一个潜在的可访问数据集.
研究的目的:
- 评估各种机器学习 (ML) 算法在诊断PV方面的有效性.
- 在先进测试之前,确定单独的CBC参数是否可以准确预测PV.
- 探索ML在简化PV的诊断途径方面的潜力.
主要方法:
- 利用了1484名患者的数据,将他们分为PV (n=82) 和非PV (n=1402) 组.
- 应用了合成少数人过量采样技术 (SMOTE) 来解决数据不平衡.
- 通过使用CBC参数 (WBC,HCT,HGB,PLT) 训练并测试了随机森林,支持向量机,极端梯度提升 (XGBoost) 和K-最近邻近算法.
主要成果:
- 该XGBoost算法实现了最高的预测性能 (AUC=0.99,准确性=0.94,F1-Score=0.94).
- 血小板计数 (PLT) 是最重要的预测因素,为模型的准确性贡献了42.4%.
- 在WBC,PLT,HGB,HCT,EPO和JAK2参数之间观察到PV和非PV组之间的显著差异 (p<0.001).
结论:
- 机器学习模型,特别是XGBoost,可以使用随时可用的CBC参数高精度地诊断PV.
- 这种基于机器学习的方法显示,有可能减少对昂贵的诊断方法 (如JAK2突变分析,EPO水平和骨髓活检) 的依赖.
- 在血液学诊断中实施ML可以导致更有效和更具成本效益的患者护理途径.
相关概念视频
Bone Marrow Sampling and Transplants
502
Bone marrow transplant is a potential cure for several diseases, including cancer and specific genetic disorders. Notably, this procedure is applicable for patients suffering from aplastic anemia, certain types of leukemia, severe combined immunodeficiency disease (SCID), Hodgkin's disease, non-Hodgkin's lymphoma, multiple myeloma, thalassemia, sickle-cell disease, and certain cancers.
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
The transplant begins with high doses of chemotherapy and radiation treatment, which aim to destroy...
502
Classification of Leukocytes
2.7K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
2.7K
Disorders of Erythrocytes
1.3K
Disorders of erythrocytes, or red blood cells (RBCs), include a range of conditions affecting their number, shape, or function.
Erythrocyte disorders can be broadly categorized into two main types: anemic and polycythemic conditions.
A low oxygen-carrying capacity of the blood due to the loss, lower production, or destruction of erythrocytes is termed anemia. Hemorrhagic anemia, for example, occurs when bleeding from an external wound or internal ulcer reduces erythrocyte counts.
On the other...
Erythrocyte disorders can be broadly categorized into two main types: anemic and polycythemic conditions.
A low oxygen-carrying capacity of the blood due to the loss, lower production, or destruction of erythrocytes is termed anemia. Hemorrhagic anemia, for example, occurs when bleeding from an external wound or internal ulcer reduces erythrocyte counts.
On the other...
1.3K


