CBC Dataset

- About Dataset Safa S. Abdul-Jabbar, Alaa k. Farhan - Context This is the first Dataset for various ordinary patients in Iraq. The Dataset provides the patients’ Cell Blood Count test information that can be used to create a Hematology diagnosis/prediction system. Also, this Data was collected in 2022 from Al-Zahraa Al-Ahly Hospital. These data can be cleaned & analyzed using any programming language because it is provided in an excel file that can be accessed and manipulated easily. The user just needs to understand how rows and columns are arranged because the data was collected as images(CBC images) from the laboratories and then stored the extracted data in an excel file.  Content This Dataset contains 500 rows. For each row (patient information), there are 21 columns containing CBC test features that can be described as follows: 1. ID: Patients Identifier 2. WBC: White Blood Cell, Normal Ranges: 4.0 to 10.0, Unit: 10^9/L. 3. LYMp: Lymphocytes percentage, which is a type of white blood cell, Normal Ranges: 20.0 to 40.0, Unit: % 4. MIDp: Indicates the percentage combined value of the other types of white blood cells not classified as lymphocytes or granulocytes, Normal Ranges: 1.0 to 15.0, Unit: % 5. NEUTp: Neutrophils are a type of white blood cell (leukocytes); neutrophils percentage, Normal Ranges: 50.0 to 70.0, Unit: % 6. LYMn: Lymphocytes number are a type of white blood cell, Normal Ranges: 0.6 to 4.1, Unit: 10^9/L. 7. MIDn: Indicates the combined number of other white blood cells not classified as lymphocytes or granulocytes, Normal Ranges: 0.1 to 1.8, Unit: 10^9/L. 8. NEUTn: Neutrophils Number, Normal Ranges: 2.0 to 7.8, Unit: 10^9/L. 9. RBC: Red Blood Cell, Normal Ranges: 3.50 to 5.50, Unit: 10^12/L 10. HGB: Hemoglobin, Normal Ranges: 11.0 to 16.0, Unit: g/dL 11. HCT: Hematocrit is the proportion, by volume, of the Blood that consists of red blood cells, Normal Ranges: 36.0 to 48.0, Unit: % 12. MCV: Mean Corpuscular Volume, Normal Ranges: 80.0 to 99.0, Unit: fL 13. MCH: Mean Corpuscular Hemoglobin is the average amount of haemoglobin in the average red cell, Normal Ranges: 26.0 to 32.0, Unit: pg 14. MCHC: Mean Corpuscular Hemoglobin Concentration, Normal Ranges: 32.0 to 36.0, Unit: g/dL 15. RDWSD: Red Blood Cell Distribution Width, Normal Ranges: 37.0 to 54.0, Unit: fL 16. RDWCV: Red blood cell distribution width, Normal Ranges: 11.5 to 14.5, Unit: % 17. PLT: Platelet Count, Normal Ranges: 100 to 400, Unit: 10^9/L 18. MPV: Mean Platelet Volume, Normal Ranges: 7.4 to 10.4, Unit: fL 19. PDW: Red Cell Distribution Width, Normal Ranges: 10.0 to 17.0, Unit: % 20. PCT: The level of Procalcitonin in the Blood, Normal Ranges: 0.10 to 0.28, Unit: % 21. PLCR: Platelet Large Cell Ratio, Normal Ranges: 13.0 to 43.0, Unit: % - Acknowledgements We thank the entire Al-Zahraa Al-Ahly Hospital Hospital team, especially the hospital manager, for cooperating with us in collecting this data while maintaining patients' confidentiality.数据集说明 本数据集由Safa S. Abdul-Jabbar、Alaa K. Farhan整理发布，是伊拉克首个面向普通门诊患者的血液学数据集。 ### 数据集背景 本数据集旨在支撑血液疾病诊断/预测系统的构建，收录了患者的血常规（Cell Blood Count, CBC）检测信息。本数据集于2022年从宰赫拉阿赫利医院（Al-Zahraa Al-Ahly Hospital）采集获取，以Excel文件格式提供，支持任意编程语言完成数据清洗与分析工作，操作门槛极低。需注意，本数据集原始采集自实验室的血常规影像（CBC images），经数据提取后转换为表格形式，使用者仅需熟悉行列排布规则即可正常使用。 ### 数据集内容 本数据集共包含500条样本，每条样本对应一名患者的检测信息，共计21项血常规检测特征，具体说明如下： 1. ID：患者唯一标识符 2. 白细胞计数（WBC, White Blood Cell）：正常参考范围4.0~10.0，单位：10^9/L 3. 淋巴细胞百分比（LYMp）：淋巴细胞作为白细胞的一类，其占比参考范围为20.0%~40.0%，单位：% 4. 中间细胞百分比（MIDp）：未归类为淋巴细胞或粒细胞的其他白细胞类群的合并占比，正常参考范围1.0%~15.0%，单位：% 5. 中性粒细胞百分比（NEUTp）：中性粒细胞作为白细胞（leukocytes）的一类，其占比参考范围50.0%~70.0%，单位：% 6. 淋巴细胞绝对值（LYMn）：淋巴细胞的实际计数，正常参考范围0.6~4.1，单位：10^9/L 7. 中间细胞绝对值（MIDn）：未归类为淋巴细胞或粒细胞的其他白细胞类群的合并计数，正常参考范围0.1~1.8，单位：10^9/L 8. 中性粒细胞绝对值（NEUTn）：中性粒细胞实际计数，正常参考范围2.0~7.8，单位：10^9/L 9. 红细胞计数（RBC, Red Blood Cell）：正常参考范围3.50~5.50，单位：10^12/L 10. 血红蛋白（HGB, Hemoglobin）：正常参考范围11.0~16.0，单位：g/dL 11. 血细胞比容（HCT, Hematocrit）：血液中红细胞所占体积比例，正常参考范围36.0%~48.0%，单位：% 12. 平均红细胞体积（MCV, Mean Corpuscular Volume）：正常参考范围80.0~99.0，单位：fL 13. 平均红细胞血红蛋白量（MCH, Mean Corpuscular Hemoglobin）：单个红细胞内平均血红蛋白含量，正常参考范围26.0~32.0，单位：pg 14. 平均红细胞血红蛋白浓度（MCHC, Mean Corpuscular Hemoglobin Concentration）：正常参考范围32.0~36.0，单位：g/dL 15. 红细胞分布宽度标准差（RDWSD, Red Blood Cell Distribution Width）：正常参考范围37.0~54.0，单位：fL 16. 红细胞分布宽度变异系数（RDWCV, Red Blood Cell Distribution Width）：正常参考范围11.5%~14.5%，单位：% 17. 血小板计数（PLT, Platelet Count）：正常参考范围100~400，单位：10^9/L 18. 平均血小板体积（MPV, Mean Platelet Volume）：正常参考范围7.4~10.4，单位：fL 19. 血小板分布宽度（PDW, Red Cell Distribution Width）：正常参考范围10.0%~17.0%，单位：% 20. 降钙素原（PCT, Procalcitonin）：血液中降钙素原水平，正常参考范围0.10%~0.28%，单位：% 21. 血小板大细胞比率（PLCR, Platelet Large Cell Ratio）：正常参考范围13.0%~43.0%，单位：% ### 致谢 感谢宰赫拉阿赫利医院全体团队，尤其是医院管理层，在采集本数据集过程中给予的配合，同时严格保障了患者的隐私与保密性。