Efficacy of three machine learning algorithms in evaluating stability of carotid plaque in patients with cerebral infarction

ZHAN Xianfa; YU Xiaoya; WANG Hongjun; XIONG Kunlin

doi:10.7619/jcmp.20232657

Journal of Clinical Medicine in Practice > 2023 > 27(22): 6-12. > DOI: 10.7619/jcmp.20232657

ZHAN Xianfa, YU Xiaoya, WANG Hongjun, XIONG Kunlin. Efficacy of three machine learning algorithms in evaluating stability of carotid plaque in patients with cerebral infarction[J]. Journal of Clinical Medicine in Practice, 2023, 27(22): 6-12. DOI: 10.7619/jcmp.20232657

Citation:

PDF (2217 KB)

Efficacy of three machine learning algorithms in evaluating stability of carotid plaque in patients with cerebral infarction

1.
Department of Radiology, Fengdu County People's Hospital of Chongqing, Chongqing, 408200
2.
Department of Neurology, Fengdu County People's Hospital of Chongqing, Chongqing, 408200
3.
Department of Radiology, Army Specialty Medical Center, Chongqing, 400042

More Information

Received Date: August 20, 2023
Revised Date: October 12, 2023
Available Online: December 05, 2023

Graphical Abstract

Abstract

Abstract

Objective
To explore the predictive efficacy of three machine learning algorithms for carotid plaque stability in patients with cerebral infarction.
Methods
The clinical data of 500 patients with cerebral infarction were retrospectively analyzed. Univariate analysis and multivariate analysis were used to determine the predictive factors entering the model. The prediction model of carotid plaque stability in patients with cerebral infarction was constructed based on nomogram, decision tree and random forest respectively. The enrolled patients were randomly divided into training set and test set according to the ratio of 7:3. Sensitivity, specificity, accuracy, recall, accuracy and area under the curve (AUC) were used to compare the application efficiency of the model.
Results
The AUC of the nomogram model for evaluating the stability of carotid plaque in patients with cerebral infarction in the training set was 0.910(95%CI, 0.950 to 0.983), the sensitivity was 0.910, the specificity was 0.917, the accuracy was 0.886, the recall rate was 0.910, and the accuracy rate was 0.914. The AUC of the decision tree model for evaluating the stability of carotid plaque in patients with cerebral infarction in the training set was 0.932(95%CI, 0.903 to 0.961), the sensitivity was 0.903, the specificity was 0.922, the accuracy was 0.891, the recall rate was 0.903, and the accuracy rate was 0.914. The AUC of the random forest model for evaluating the stability of carotid plaque in patients with cerebral infarction in the training set was 0.984(95%CI, 0.970 to 0.998), the sensitivity was 0.972, the specificity was 0.995, the accuracy was 0.993, the recall rate was 0.972, and the accuracy was 0.986.
Conclusion
The model based on the random forest algorithm has a better prediction effect and stability in evaluating the stability of carotid plaque in patients with cerebral infarction, and its prediction efficiency is better than that of the Nomogram and decision tree.
- cerebral infarction,
- carotid plaque,
- stability,
- Nomogram,
- decision tree,
- random forest

FullText(HTML)

References (35)

References

[1]	GBD 2016 BRAIN AND OTHER CNS CANCER COLLABORATORS. Global, regional, and national burden of brain and other CNS cancer, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016[J]. Lancet Neurol, 2019, 18(4): 376-393. doi: 10.1016/S1474-4422(18)30468-X
[2]	陈青, 李合华, 赵帅, 等. 高分辨磁共振检查对颈动脉粥样硬化斑块稳定性的危险因素分析[J]. 中国实用神经疾病杂志, 2019, 22(24): 2713-2719. https://www.cnki.com.cn/Article/CJFDTOTAL-HNSJ201924007.htm
[3]	刘畅, 赵泓博, 贾宏茹, 等. 基于CT图像纹理分析结合机器学习随机森林模型对急性脑梗死的辅助诊断价值[J]. 临床放射学杂志, 2020, 39(7): 1439-1443. https://www.cnki.com.cn/Article/CJFDTOTAL-LCFS202007042.htm
[4]	LI X W, XU C Y, SHANG C M, et al. Machine learning predicts the risk of hemorrhagic transformation of acute cerebral infarction and in-hospital death[J]. Comput Methods Programs Biomed, 2023, 237: 107582. doi: 10.1016/j.cmpb.2023.107582
[5]	HEO J, YOON J G, PARK H, et al. Machine learning-based model for prediction of outcomes in acute stroke[J]. Stroke, 2019, 50: 1263-1265. doi: 10.1161/STROKEAHA.118.024293
[6]	贺佳琪, 王琳鑫, 曹阳, 等. 动脉粥样硬化斑块内出血影像学检查技术进展[J]. 心血管病学进展, 2020, 41(11): 1148-1151. https://www.cnki.com.cn/Article/CJFDTOTAL-XXGB202011010.htm
[7]	中华医学会糖尿病学分会. 中国2型糖尿病防治指南(2020年版)(上)[J]. 中国实用内科杂志, 2021, 41(8): 668-695. https://www.cnki.com.cn/Article/CJFDTOTAL-HBYX202112018.htm
[8]	中国高血压防治指南修订委员会, 高血压联盟(中国, 中华医学会心血管病学分会中国医师协会高血压专业委员会, 等. 中国高血压防治指南(2018年修订版)[J]. 中国心血管杂志, 2019, 24(1): 24-56. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGZ201904005.htm
[9]	中华医学会心血管病学分会介入心脏病学组, 中华医学会心血管病学分会动脉粥样硬化与冠心病学组, 中国医师协会心血管内科医师分会血栓防治专业委员会, 等. 稳定性冠心病诊断与治疗指南[J]. 中华心血管病杂志, 2018, 46(9): 680-694. https://www.cnki.com.cn/Article/CJFDTOTAL-XXFZ201902001.htm
[10]	张伟, 李华, 王少颖. 超声联合螺旋CT对脑梗死患者颈动脉斑块稳定性的评估价值[J]. 中国CT和MRI杂志, 2021, 19(2): 38-40, 55. https://www.cnki.com.cn/Article/CJFDTOTAL-CTMR202102013.htm
[11]	徐守权, 唐国文, 黄舞标, 等. BP神经网络、随机森林和决策树预测急性脑梗死患者静脉溶栓后发生早期神经功能恶化的效能比较[J]. 实用心脑肺血管病杂志, 2023, 31(2): 16-21. https://www.cnki.com.cn/Article/CJFDTOTAL-SYXL202302003.htm
[12]	VIRANI S S, ALONSO A, BENJAMIN E J, et al. Heart disease and stroke statistics-2020 update: a report from the American heart association[J]. Circulation, 2020, 141(9): e139-e596.
[13]	王倩, 张亮. 颈动脉粥样硬化斑块与脑梗死关系的高分辨磁共振研究[J]. 中国实用神经疾病杂志, 2017, 20(17): 85-88. https://www.cnki.com.cn/Article/CJFDTOTAL-HNSJ201717029.htm
[14]	SABA L C, ANTIGNANI P L, GUPTA A, et al. International Union of Angiology (IUA) consensus paper on imaging strategies in atherosclerotic carotid artery imaging: from basic strategies to advanced approaches[J]. Atherosclerosis, 2022, 354: 23-40.
[15]	王丹妮, 李康. 多排螺旋CT评估颈动脉斑块易损性的研究现状及进展[J]. 影像研究与医学应用, 2022, 6(9): 4-6. https://www.cnki.com.cn/Article/CJFDTOTAL-YXYY202209002.htm
[16]	鲁强, 杨瑞山, 王可. CTA对脑梗塞性颈内动脉斑块性质的评价[J]. 中国CT和MRI杂志, 2023, 21(5): 18-20. https://www.cnki.com.cn/Article/CJFDTOTAL-CTMR202305007.htm
[17]	MAURIELLO A, SANGIORGI G M, VIRMANI R, et al. A pathobiologic link between risk factors profile and morphological markers of carotid instability[J]. Atherosclerosis, 2010, 208(2): 572-580.
[18]	ZHANG S, GAO L, KANG B, et al. Radiomics assessment of carotid intraplaque hemorrhage: detecting the vulnerable patients[J]. Insights Imaging, 2022, 13(1): 200.
[19]	崔艺耀. 颈动脉粥样硬化斑块的病理学、形态学和相关细胞机制的研究[D]. 北京: 北京协和医学院, 2019.
[20]	MORI H, TORII S, KUTYNA M, et al. Coronary artery calcification and its progression: what does it really mean?[J]. JACC Cardiovasc Imaging, 2018, 11(1): 127-142.
[21]	魏梦娇, 高阳, 吴琼, 等. MRI斑块诊断软件定性评估颈动脉斑块[J]. 放射学实践, 2021, 36(12): 1493-1498. https://www.cnki.com.cn/Article/CJFDTOTAL-FSXS202112007.htm
[22]	TRELLES M, EBERHARDT K M, BUCHHOLZ M, et al. CTA for screening of complicated atherosclerotic carotid plaque—american heart association type Ⅵ lesions as defined by MRI[J]. AJNR Am J Neuroradiol, 2013, 34(12): 2331-2337.
[23]	BRUNHAM L R, RUEL I, ALJENEDIL S, et al. Canadian cardiovascular society position statement on familial hypercholesterolemia: update 2018[J]. Can J Cardiol, 2018, 34(12): 1553-1563.
[24]	XUE Q Z, MENG A G, WANG T, et al. Correlation between of small dense low-density lipoprotein cholesterol with acute cerebral infarction and carotid atherosclerotic plaque stability[J]. J Clin Lab Anal, 2019, 33(6): e22891.
[25]	GEOVANINI G, LIBBY P. Atherosclerosis and inflammation: overview and updates[J]. Clin Sci, 2018, 132(12): 1243-1252.
[26]	WU Z, LI X, WEN Q, et al. Serum LDL-C/HDL-C ratio and the risk of carotid plaques: a longitudinal study[J]. BMC Cardiovasc Disord, 2022, 22(1): 501.
[27]	BALLANTYNE C, LAUFS U, RAY K K, et al. Efficacy and safety of bempedoic acid + ezetimibe fixed-dose combination in patients at high CVD risk and with elevated LDL-C receiving maximally tolerated statin therapy[J]. Atherosclerosis, 2019, 287: e7-e8.
[28]	HU X M, LIU J L, LI W, et al. Elevated serum uric acid was associated with pre-inflammatory state and impacted the role of HDL-C on carotid atherosclerosis[J]. Nutr Metab Cardiovasc Dis, 2022, 32(7): 1661-1669.
[29]	NÙRIA A, ALICIA T, ESTHER R, et al. Correction to: type 2 diabetes-associated carotid plaque burden is increased in patients with retinopathy compared to those without retinopathy[J]. Cardiovasc Diabetol, 2018, 17(1): 49.
[30]	肖隽喆. 血糖、血浆同型半胱氨酸与颈动脉斑块稳定性的相关性分析[D], 承德: 承德医学院, 2021: 21-22.
[31]	ZHANG R Y, ZHANG Q W, JI A H, et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning[J]. Eur Radiol, 2021, 31(5): 3116-3126.
[32]	陈思玎, 俞蔚然, 黄馨莹, 等. 基于机器学习的新发急性缺血性卒中患者1年功能预后预测研究[J]. 中国卒中杂志, 2022, 17(3): 265-271. https://www.cnki.com.cn/Article/CJFDTOTAL-ZUZH202203008.htm
[33]	OBERMEYER Z, EMANUEL E J. Predicting the future-big data, machine learning, and clinical medicine[J]. N Engl J Med, 2016, 375(13): 1216-1219.
[34]	崔伟锋, 林萍, 刘萧萧, 等. 基于机器学习的原发性高血压心血管风险预后模型[J]. 中国老年学杂志, 2022, 42(15): 3625-3629. https://www.cnki.com.cn/Article/CJFDTOTAL-ZLXZ202215001.htm
[35]	LI X W, WANG Y T, XU J C. Development of a machine learning-based risk prediction model for cerebral infarction and comparison with nomogram model[J]. J Affect Disord, 2022, 314: 341-348.

[1]	DONG Junqiang, XIE Fei, ZHANG Zhixiang, JIA Fang. Differential diagnosis of pancreatic cancer and pancreatitis by multi-slice spiral CT and MRI[J]. Journal of Clinical Medicine in Practice, 2023, 27(9): 8-12. DOI: 10.7619/jcmp.20230321
[2]	GUO Huafeng, WANG Xiaonan, YANG Lu. Application of multi-slice spiral CT combined with MRI in diagnosis of cerebral infarction and cerebral hemorrhage[J]. Journal of Clinical Medicine in Practice, 2020, 24(23): 8-10,14. DOI: 10.7619/jcmp.202023003
[3]	WANG Xiaonan, GUO Huafeng, YANG Lu. Analysis of multi-slice spiral CT in diagnosis of non-small cell lung cancer and small cell lung cancer[J]. Journal of Clinical Medicine in Practice, 2020, 24(23): 5-7. DOI: 10.7619/jcmp.202023002
[4]	XIAO Bin. Value of 16-slice spiral CT scanning versus transvaginal ultrasound in diagnosing female pelvic tumors[J]. Journal of Clinical Medicine in Practice, 2020, 24(20): 72-74,78. DOI: 10.7619/jcmp.202020020
[5]	ZHOU Chunshan, HUANG Yan, YAN Wenchao. Value of computed tomography scan versus magnetic resonance imaging in the diagnosis of pancreatic cystadenocarcinoma[J]. Journal of Clinical Medicine in Practice, 2020, 24(20): 47-50. DOI: 10.7619/jcmp.202020013
[6]	WU Huadong, JIAO Lidong. Value of multi-slice spiral CT and echocardiogram in evaluation of right heart function in patients with acute pulmonary embolism[J]. Journal of Clinical Medicine in Practice, 2020, 24(19): 5-8. DOI: 10.7619/jcmp.202019002
[7]	YIN Jiansong, XUE Mei, WANG Jing, LIU Caixia, WAN Yu. Diagnostic value of oxygen saturation monitoring combined with auscultation murmur detection in congenital heart disease[J]. Journal of Clinical Medicine in Practice, 2020, 24(3): 78-80. DOI: 10.7619/jcmp.202003022
[8]	LI Xiaomin, HU Xiaoyun, LIU Renfei. Value of magnetic resonance imaging versus spiral CT in the diagnosis of biliary diseases[J]. Journal of Clinical Medicine in Practice, 2019, 23(16): 33-36. DOI: 10.7619/jcmp.201916009
[9]	GUO Weijuan, YANG Liu, WU Dong, QIN Na. Application of CT perfusion original image combined with edaravone in stroke patients[J]. Journal of Clinical Medicine in Practice, 2019, 23(10): 58-60, 68. DOI: 10.7619/jcmp.201910016
[10]	WANG Chuanzhen, WANG Cuixiang, LI Qiang. Application value of multilayer spiral CT combined with MRI in the diagnosis of wrist joint injury[J]. Journal of Clinical Medicine in Practice, 2013, (15): 51-53. DOI: 10.7619/jcmp.201315018

Cited By

Cited by

Periodical cited type(7)

1.	苏燕，徐九云，雷海露，刘晓蓓. 老年危重症患者发生再喂养综合征的危险因素回归方程的构建及干预措施分析. 实用临床医药杂志. 2024(01): 123-128 . 本站查看
2.	谢婷，侯超，周旭辉，郭育君，练宇泽，曾亚琦. 经皮穴位电刺激在酒精依赖患者中的应用效果. 实用临床医药杂志. 2024(02): 38-42 . 本站查看
3.	孙桂敏. 脑卒中伴吞咽障碍患者营养管理现况及研究进展. 医药前沿. 2024(24): 17-21 .
4.	王锦程，刘闯，周相宇，周素芳. 周素芳运用参苓白术散治疗酒精性肝病经验. 中医药通报. 2023(01): 12-14+67 .
5.	张兰，沈晓芳，金瑾，徐吉，张静. 无基础代谢性疾病急性缺血性卒中患者短期营养不良预测模型构建与验证. 中国卒中杂志. 2023(04): 428-433 .
6.	付志鹏，郑盛，杨涓. 肝硬化患者营养评价方法研究进展. 国际医药卫生导报. 2023(23): 3341-3344 .
7.	姚绍敏，王学义，余艳堂，雍恩华，宋志领. 早期营养支持对酒依赖患者临床结局的影响. 神经疾病与精神卫生. 2021(08): 557-561 .

Other cited types(0)

Get Citation

PDF

XML

Article views (165) PDF downloads (15) Cited by(7)

Turn off MathJax

Article Contents

Abstract

References

Efficacy of three machine learning algorithms in evaluating stability of carotid plaque in patients with cerebral infarction