Laboratory Medicine ›› 2024, Vol. 39 ›› Issue (12): 1190-1195.DOI: 10.3969/j.issn.1673-8640.2024.12.010
Previous Articles Next Articles
SHEN Zhan1, BIAN Xiaobo2, HUANG Ying1, WANG Siyang1, SHEN Tingting1, ZHANG Xian1, SONG Yunxiao2, XIE Lianhong1(
)
Received:2024-04-30
Revised:2024-09-11
Online:2024-12-30
Published:2025-01-06
CLC Number:
SHEN Zhan, BIAN Xiaobo, HUANG Ying, WANG Siyang, SHEN Tingting, ZHANG Xian, SONG Yunxiao, XIE Lianhong. Stroke recurrence prediction model based on machine learning algorithms using routine blood test[J]. Laboratory Medicine, 2024, 39(12): 1190-1195.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.shjyyx.com/EN/10.3969/j.issn.1673-8640.2024.12.010
| 组别 | 例数 | 性别 | 年龄/岁 | 吸烟史/例 | 饮酒史/例 | 糖尿病史/例 | 高血压史/例 | WBC计数/(×1012·L-1) | RBC计数/(×1012·L-1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 男/例 | 女/例 | |||||||||||||||||||||||||
| 卒中未复发组 | 197 | 107 | 90 | 75±11 | 45 | 58 | 26 | 37 | 6.75±3.33 | 3.90±0.71 | ||||||||||||||||
| 卒中复发组 | 130 | 67 | 63 | 74±12 | 28 | 33 | 16 | 25 | 6.92±2.51 | 4.13±0.62 | ||||||||||||||||
| 统计值 | 0.242 | 0.805 | 0.077 | 0.642 | 0.055 | 0.010 | 0.503 | 3.341 | ||||||||||||||||||
| P值 | 0.622 | 0.422 | 0.782 | 0.423 | 0.814 | 0.919 | 0.597 | 0.001 | ||||||||||||||||||
| 组别 | Hb/ (g·L-1) | MCV/ fL | MCH/ Pg | MCHC/ (g·L-1) | PLT/ (×109·L-1) | LYMPH#/(×109·L-1) | MO#/(×109·L-1) | NEUT#/(×109·L-1) | ||||||||||||||||||
| 卒中未复发组 | 119.41±22.87 | 91.96±5.73 | 30.63±2.22 | 333.06±11.14 | 202.99±69.05 | 1.39±0.60 | 0.42±0.20 | 4.77±3.23 | ||||||||||||||||||
| 卒中复发组 | 125.88±17.84 | 93.22±5.88 | 30.50±2.40 | 332.53±10.91 | 212.94±64.90 | 1.52±0.54 | 0.42±0.17 | 4.77±2.52 | ||||||||||||||||||
| 统计值 | 3.005 | 2.147 | 0.563 | 0.478 | 1.449 | 2.186 | 0.488 | 0.029 | ||||||||||||||||||
| P值 | 0.003 | 0.033 | 0.574 | 0.633 | 0.149 | 0.030 | 0.626 | 0.977 | ||||||||||||||||||
| 组别 | EO#/ (×109·L-1) | BASO#/(×109·L-1) | RDW-CV/ % | PDW | MPV/ fL | PCT/ % | TC/(mmol·L-1) | TG/(mmol·L-1) | ||||||||||||||||||
| 卒中未复发组 | 0.17±0.17 | 0.02±0.01 | 13.60±2.09 | 16.09±0.38 | 9.81±1.12 | 0.20±0.06 | 4.98±1.23 | 1.72±0.47 | ||||||||||||||||||
| 卒中复发组 | 0.15±0.14 | 0.02±0.02 | 13.35±1.62 | 16.07±0.38 | 9.87±1.17 | 0.21±0.05 | 5.68±1.45 | 2.22±0.48 | ||||||||||||||||||
| 统计值 | 0.916 | 1.342 | 1.274 | 0.563 | 0.495 | 1.421 | 3.489 | 3.981 | ||||||||||||||||||
| P值 | 0.361 | 0.181 | 0.204 | 0.574 | 0.621 | 0.157 | <0.001 | <0.001 | ||||||||||||||||||
| 组别 | 例数 | 性别 | 年龄/岁 | 吸烟史/例 | 饮酒史/例 | 糖尿病史/例 | 高血压史/例 | WBC计数/(×1012·L-1) | RBC计数/(×1012·L-1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 男/例 | 女/例 | |||||||||||||||||||||||||
| 卒中未复发组 | 197 | 107 | 90 | 75±11 | 45 | 58 | 26 | 37 | 6.75±3.33 | 3.90±0.71 | ||||||||||||||||
| 卒中复发组 | 130 | 67 | 63 | 74±12 | 28 | 33 | 16 | 25 | 6.92±2.51 | 4.13±0.62 | ||||||||||||||||
| 统计值 | 0.242 | 0.805 | 0.077 | 0.642 | 0.055 | 0.010 | 0.503 | 3.341 | ||||||||||||||||||
| P值 | 0.622 | 0.422 | 0.782 | 0.423 | 0.814 | 0.919 | 0.597 | 0.001 | ||||||||||||||||||
| 组别 | Hb/ (g·L-1) | MCV/ fL | MCH/ Pg | MCHC/ (g·L-1) | PLT/ (×109·L-1) | LYMPH#/(×109·L-1) | MO#/(×109·L-1) | NEUT#/(×109·L-1) | ||||||||||||||||||
| 卒中未复发组 | 119.41±22.87 | 91.96±5.73 | 30.63±2.22 | 333.06±11.14 | 202.99±69.05 | 1.39±0.60 | 0.42±0.20 | 4.77±3.23 | ||||||||||||||||||
| 卒中复发组 | 125.88±17.84 | 93.22±5.88 | 30.50±2.40 | 332.53±10.91 | 212.94±64.90 | 1.52±0.54 | 0.42±0.17 | 4.77±2.52 | ||||||||||||||||||
| 统计值 | 3.005 | 2.147 | 0.563 | 0.478 | 1.449 | 2.186 | 0.488 | 0.029 | ||||||||||||||||||
| P值 | 0.003 | 0.033 | 0.574 | 0.633 | 0.149 | 0.030 | 0.626 | 0.977 | ||||||||||||||||||
| 组别 | EO#/ (×109·L-1) | BASO#/(×109·L-1) | RDW-CV/ % | PDW | MPV/ fL | PCT/ % | TC/(mmol·L-1) | TG/(mmol·L-1) | ||||||||||||||||||
| 卒中未复发组 | 0.17±0.17 | 0.02±0.01 | 13.60±2.09 | 16.09±0.38 | 9.81±1.12 | 0.20±0.06 | 4.98±1.23 | 1.72±0.47 | ||||||||||||||||||
| 卒中复发组 | 0.15±0.14 | 0.02±0.02 | 13.35±1.62 | 16.07±0.38 | 9.87±1.17 | 0.21±0.05 | 5.68±1.45 | 2.22±0.48 | ||||||||||||||||||
| 统计值 | 0.916 | 1.342 | 1.274 | 0.563 | 0.495 | 1.421 | 3.489 | 3.981 | ||||||||||||||||||
| P值 | 0.361 | 0.181 | 0.204 | 0.574 | 0.621 | 0.157 | <0.001 | <0.001 | ||||||||||||||||||
| 组别 | 例数 | 性别 | 年龄/岁 | 吸烟史/例 | 饮酒史/例 | 糖尿病史/例 | 高血压史/例 | WBC计数/(×1012·L-1) | RBC计数/(×1012·L-1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 男/例 | 女/例 | |||||||||||||||||||||||||
| 卒中未复发组 | 56 | 29 | 27 | 75±13 | 15 | 20 | 17 | 22 | 6.88±3.48 | 3.97±0.69 | ||||||||||||||||
| 卒中复发组 | 54 | 28 | 26 | 75±12 | 12 | 21 | 13 | 23 | 6.60±2.65 | 4.24±0.53 | ||||||||||||||||
| 统计值 | 0.000 | 0.177 | 0.309 | 0.119 | 0.547 | 1.086 | 0.444 | 2.068 | ||||||||||||||||||
| P值 | 0.994 | 0.86 | 0.578 | 0.731 | 0.459 | 0.297 | 0.658 | 0.041 | ||||||||||||||||||
| 组别 | Hb/ (g·L-1) | MCV/ fL | MCH/ Pg | MCHC/ (g·L-1) | PLT/ (×109·L-1) | LYMPH#/(×109·L-1) | MO#/(×109·L-1) | NEUT#/(×109·L-1) | ||||||||||||||||||
| 卒中未复发组 | 120.49±20.22 | 91.82±6.28 | 30.46±2.20 | 331.87±11.35 | 187.51±61.69 | 1.35±0.58 | 0.41±0.21 | 4.87±3.40 | ||||||||||||||||||
| 卒中复发组 | 129.02±18.09 | 94.99±4.20 | 30.83±2.34 | 334.76±10.70 | 204.45±52.41 | 1.50±0.53 | 0.43±0.17 | 4.47±2.68 | ||||||||||||||||||
| 统计值 | 2.447 | 2.199 | 0.801 | 1.272 | 1.429 | 1.785 | 0.527 | 0.624 | ||||||||||||||||||
| P值 | 0.016 | 0.030 | 0.425 | 0.206 | 0.156 | 0.077 | 0.599 | 0.534 | ||||||||||||||||||
| 组别 | EO#/ (×109·L-1) | BASO#/(×109·L-1) | RDW-CV/ % | PDW | MPV/ fL | PCT/ % | TC/(mmol·L-1) | TG/(mmol·L-1) | ||||||||||||||||||
| 卒中未复发组 | 0.24±0.07 | 0.02±0.01 | 13.51±1.41 | 16.18±0.41 | 9.99±1.05 | 0.18±0.05 | 4.81±1.18 | 1.66±0.42 | ||||||||||||||||||
| 卒中复发组 | 0.22±0.08 | 0.02±0.01 | 13.31±0.91 | 16.08±0.36 | 9.85±1.07 | 0.20±0.05 | 5.56±1.37 | 2.35±0.60 | ||||||||||||||||||
| 统计值 | 0.663 | 1.236 | 0.792 | 1.189 | 0.653 | 1.510 | 4.782 | 3.901 | ||||||||||||||||||
| P值 | 0.509 | 0.219 | 0.430 | 0.237 | 0.515 | 0.134 | <0.001 | <0.001 | ||||||||||||||||||
| 组别 | 例数 | 性别 | 年龄/岁 | 吸烟史/例 | 饮酒史/例 | 糖尿病史/例 | 高血压史/例 | WBC计数/(×1012·L-1) | RBC计数/(×1012·L-1) | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 男/例 | 女/例 | |||||||||||||||||||||||||
| 卒中未复发组 | 56 | 29 | 27 | 75±13 | 15 | 20 | 17 | 22 | 6.88±3.48 | 3.97±0.69 | ||||||||||||||||
| 卒中复发组 | 54 | 28 | 26 | 75±12 | 12 | 21 | 13 | 23 | 6.60±2.65 | 4.24±0.53 | ||||||||||||||||
| 统计值 | 0.000 | 0.177 | 0.309 | 0.119 | 0.547 | 1.086 | 0.444 | 2.068 | ||||||||||||||||||
| P值 | 0.994 | 0.86 | 0.578 | 0.731 | 0.459 | 0.297 | 0.658 | 0.041 | ||||||||||||||||||
| 组别 | Hb/ (g·L-1) | MCV/ fL | MCH/ Pg | MCHC/ (g·L-1) | PLT/ (×109·L-1) | LYMPH#/(×109·L-1) | MO#/(×109·L-1) | NEUT#/(×109·L-1) | ||||||||||||||||||
| 卒中未复发组 | 120.49±20.22 | 91.82±6.28 | 30.46±2.20 | 331.87±11.35 | 187.51±61.69 | 1.35±0.58 | 0.41±0.21 | 4.87±3.40 | ||||||||||||||||||
| 卒中复发组 | 129.02±18.09 | 94.99±4.20 | 30.83±2.34 | 334.76±10.70 | 204.45±52.41 | 1.50±0.53 | 0.43±0.17 | 4.47±2.68 | ||||||||||||||||||
| 统计值 | 2.447 | 2.199 | 0.801 | 1.272 | 1.429 | 1.785 | 0.527 | 0.624 | ||||||||||||||||||
| P值 | 0.016 | 0.030 | 0.425 | 0.206 | 0.156 | 0.077 | 0.599 | 0.534 | ||||||||||||||||||
| 组别 | EO#/ (×109·L-1) | BASO#/(×109·L-1) | RDW-CV/ % | PDW | MPV/ fL | PCT/ % | TC/(mmol·L-1) | TG/(mmol·L-1) | ||||||||||||||||||
| 卒中未复发组 | 0.24±0.07 | 0.02±0.01 | 13.51±1.41 | 16.18±0.41 | 9.99±1.05 | 0.18±0.05 | 4.81±1.18 | 1.66±0.42 | ||||||||||||||||||
| 卒中复发组 | 0.22±0.08 | 0.02±0.01 | 13.31±0.91 | 16.08±0.36 | 9.85±1.07 | 0.20±0.05 | 5.56±1.37 | 2.35±0.60 | ||||||||||||||||||
| 统计值 | 0.663 | 1.236 | 0.792 | 1.189 | 0.653 | 1.510 | 4.782 | 3.901 | ||||||||||||||||||
| P值 | 0.509 | 0.219 | 0.430 | 0.237 | 0.515 | 0.134 | <0.001 | <0.001 | ||||||||||||||||||
| 算法 | AUC | 敏感性/% | 特异性/% | 阳性预测值 | 阴性预测值 | 准确性/% | F1值 |
|---|---|---|---|---|---|---|---|
| XGboost算法 | 0.88 | 83.25 | 92.44 | 0.84 | 0.89 | 87.41 | 0.78 |
| RF算法 | 0.76 | 43.44 | 89.38 | 0.72 | 0.72 | 72.08 | 0.53 |
| Adaboost算法 | 0.68 | 49.08 | 79.01 | 0.57 | 0.72 | 67.19 | 0.53 |
| KNN算法 | 0.60 | 35.16 | 78.36 | 0.49 | 0.66 | 63.29 | 0.40 |
| LR算法 | 0.67 | 35.27 | 88.21 | 0.68 | 0.69 | 68.11 | 0.45 |
| 算法 | AUC | 敏感性/% | 特异性/% | 阳性预测值 | 阴性预测值 | 准确性/% | F1值 |
|---|---|---|---|---|---|---|---|
| XGboost算法 | 0.88 | 83.25 | 92.44 | 0.84 | 0.89 | 87.41 | 0.78 |
| RF算法 | 0.76 | 43.44 | 89.38 | 0.72 | 0.72 | 72.08 | 0.53 |
| Adaboost算法 | 0.68 | 49.08 | 79.01 | 0.57 | 0.72 | 67.19 | 0.53 |
| KNN算法 | 0.60 | 35.16 | 78.36 | 0.49 | 0.66 | 63.29 | 0.40 |
| LR算法 | 0.67 | 35.27 | 88.21 | 0.68 | 0.69 | 68.11 | 0.45 |
| [1] | GBD 2019 Stroke Collaborators. Global,regional,and national burden of stroke and its risk factors,1990-2019:a systematic analysis for the Global Burden of Disease Study 2019[J]. Lancet Neurol,2021, 20(10):795-820. |
| [2] | DONKOR E S. Stroke in the 21st century:a snapshot of the burden,epidemiology,and quality of life[J]. Stroke Res Treat, 2018,2018:3238165. |
| [3] | DING Q, LIU S, YAO Y, et al. Global,regional,and national burden of ischemic stroke,1990-2019[J]. Neurology, 2022, 98(3):e279-e290. |
| [4] | VODENCAREVIC A, WEINGÄRTNER M, CARO J J, et al. Prediction of recurrent ischemic stroke using registry data and machine learning methods:the erlangen stroke registry[J]. Stroke, 2022, 53(7):2299-2306. |
| [5] | SUMI S, ORIGASA H, HOUKIN K, et al. A modified Essen stroke risk score for predicting recurrent cardiovascular events:development and validation[J]. Int J Stroke, 2013, 8(4):251-257. |
| [6] | DIENER H C, RINGLEB P A, SAVI P. Clopidogrel for the secondary prevention of stroke[J]. Expert Opin Pharmacother, 2005, 6(5):755-764. |
| [7] | FENG G H, LI H P, LI Q L, et al. Red blood cell distribution width and ischaemic stroke[J]. Stroke Vasc Neurol, 2017, 2(3):172-175. |
| [8] | LAPPEGÅRD J, ELLINGSEN T S, SKJELBAKKEN T, et al. Red cell distribution width is associated with future risk of incident stroke[J]. Thromb Haemost, 2016, 115(1):126-134. |
| [9] | 刘淑静, 常欣魁, 陈柯霖, 等. 载脂蛋白E基因多态性与脑梗患者年龄和血脂的相关性研究[J]. 标记免疫分析与临床, 2018, 25(11):1595-1598. |
| [10] | BUSHNELL C, KERNAN W N, SHARRIEF A Z, et al. 2024 guideline for the primary prevention of stroke:a guideline from the American Heart Association/American Stroke Association[J]. Stroke, 2024, 55(12):e344-e424. |
| [11] | PERERA K S, DE SA BOASQUEVISQUE D, RAO-MELACINI P, et al. Evaluating rates of recurrent ischemic stroke among young adults with embolic stroke of undetermined source:the young ESUS longitudinal cohort study[J]. JAMA Neurol, 2022, 79(5):450-458. |
| [12] |
王双, 陈思, 付阳, 等. 机器学习在血细胞分析中智能筛查原始细胞的应用[J]. 检验医学, 2019, 34(12):1118-1123.
DOI |
| [13] | 贾音, 孙婷婷, 刘海东, 等. 常规检验大数据在胃癌早期诊断中的应用[J]. 中华检验医学杂志, 2021, 44(3):197-203. |
| [14] | 郭杰, 刘海东, 韦琴, 等. 基于检验大数据的结直肠癌风险预测模型建立与验证[J]. 中华检验医学杂志, 2021, 44(10):914-920. |
| [15] | HE M, WANG H, TANG Y, et al. Red blood cell distribution width in different time-points of peripheral thrombolysis period in acute ischemic stroke is associated with prognosis[J]. Aging(Albany NY), 2022, 14(14):5749-5767. |
| [16] | SHEN Z, HUANG Y, ZHOU Y, et al. Association between red blood cell distribution width and ischemic stroke recurrence in patients with acute ischemic stroke:a 10-years retrospective cohort analysis[J]. Aging(Albany NY), 2023, 15(8):3052-3063. |
| [17] | JIA Y P, WANG J M, LYU J Q, et al. Triglyceride-rich lipoproteins cholesterol,10-years atherosclerotic cardiovascular disease risk,and risk of myocardial infarction and ischemic stroke[J]. J Lipid Res, 2024, 65(11):100653. |
| [18] | 彭蘡, 黄婷, 徐燕. 载脂蛋白E、三酰甘油、LDL-C及联合检测在早期动脉粥样硬化性脑梗死患者中的应用价值[J]. 医学信息, 2023, 36(20):99-102. |
| [1] | JIN Weifeng, LI Dan, WANG Mengxia, PAN Nuoxuan, ZHANG Hong, LIN Ping. A risk prediction model for depressive disorders in children based on serum amino acids and cytokines [J]. Laboratory Medicine, 2025, 40(7): 666-672. |
| [2] | GUAN Chao, HUANG Ying, SONG Yunxiao, ZHOU Ying. Application of a machine learning model based on routine inflammatory markers to distinguish the severity of community-acquired pneumonia [J]. Laboratory Medicine, 2025, 40(7): 680-686. |
| [3] | WANG Xumei, XU Dongqing, GAO Limei, ZHANG Lihua, JIANG Wenli, WANG Weiwei, MA Juan, SHEN Lisong. Construction of a machine learning-based model for predicting the risk of neuroblastoma bone metastasis [J]. Laboratory Medicine, 2025, 40(6): 534-539. |
| [4] | DAI Jingwen, YANG Shuo, WANG Chong, SUN Lin, GU Meixiu, XIAN Jingrong, PAN Baishen, WANG Beili, ZHANG Chunyan, GUO Wei. Role of preoperative mean corpuscular hemoglobin concentration for predicting postoperative recurrence in intrahepatic cholangiocarcinoma patients [J]. Laboratory Medicine, 2025, 40(4): 344-349. |
| [5] | LING Xiaoting, PAN Liqiu, HUANG Yunhua, WEI Yuanyuan, DENG Xiaohui, YE Lihua, LIN Faquan, HUANG Yifang. Establishment of machine learning discriminatory formulas for thalassemia and iron deficiency anemia based on red blood cell morphology and parameters [J]. Laboratory Medicine, 2025, 40(4): 365-371. |
| [6] | ZHEN Di, JIA Bin, MENG Xianyi. Roles of serum sPD-1 and sTWEAK levels in patients with ulcerative colitis in disease monitoring and prognosis assessment [J]. Laboratory Medicine, 2025, 40(12): 1171-1176. |
| [7] | ZHAO Yilin, XU Yan, YIN Hui. Roles of serum miR-145-5p,miR-200C-3p and miR-1290 in prognosis assessment of patients with papillary thyroid carcinoma [J]. Laboratory Medicine, 2025, 40(12): 1177-1182. |
| [8] | CHANG Nan, WEI Yali, LU Qifeng, LI Tian, HOU Tingting, LI Yuan, ZHU Mengyu, SHEN Yajuan. A machine learning early warning model for acute promyelocytic leukemia based on blood cell analyzer parameters [J]. Laboratory Medicine, 2025, 40(12): 1190-1196. |
| [9] | CHEN Kun, XU Guowei, WANG Qiuli. Expression changes of plasma lncRNA PINK1-AS and miR-532-5p in patients with ischemic stroke and their effects on sleep quality and cognitive function [J]. Laboratory Medicine, 2025, 40(12): 1203-1208. |
| [10] | SHEN Zhiying, CHEN Ming, DONG Yueying. Correlation between serum Hcy,S100B levels and cerebral metabolite indicators and cognitive impairment in elderly AIS patients [J]. Laboratory Medicine, 2025, 40(11): 1097-1101. |
| [11] | LI Mingchao, SHEN Tong, ZHOU Binghe, DOU Xin, HU Liang, CHANG Dong, ZHANG Ze. Evaluation of prognosis prediction effects in acute ischemic stroke patients based on machine learning algorithms [J]. Laboratory Medicine, 2025, 40(10): 1004-1009. |
| [12] | KANG Yi, ZHANG Qiaoling, SHI Yanfang, WANG Yujia, CHEN Xiaodan, PENG Youqun. Roles of serum miR-181b and miR-144 expressions in early neurological deterioration in patients with acute ischemic stroke [J]. Laboratory Medicine, 2025, 40(1): 73-78. |
| [13] | LIU Yi, SU Xiaoming, WANG Yuanyuan, JU Tao. Roles of serum L-Arg and IL-4 levels in predicting recurrent ischemic stroke in patients with symptomatic carotid artery stenosis [J]. Laboratory Medicine, 2024, 39(7): 634-639. |
| [14] | HUANG Ying, ZHOU Ying, SONG Yunxiao, MAO Junjie, GUAN Chao, ZHAO Jinyan, NI Peiqing. Pulmonary tuberculosis diagnosis model for blood routine test based on machine learning algorithms [J]. Laboratory Medicine, 2024, 39(7): 668-672. |
| [15] | DING Jing, ZHANG Chunling, WANG Xiaorui, LI Huidan, WANG Hongling, LIU Weiling, LIN Lihui, LI Li. Laboratory diagnosis and prognostic factor analysis of core binding factor-related acute myeloid leukemia [J]. Laboratory Medicine, 2024, 39(7): 673-681. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||