Construction of a machine learning model for identifying clinical high-risk carotid plaques based on radiomics_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

WANG Xiaohui ^1,2 , LÜ Xiaoshuo ^1,2 , LIU Zhan ^1,2 , ZHEN Yanan ² , LIN Fan ² , ZHENG Xia ² , LIU Xiaopeng ² , SUN Guang ² , WEN Jianyan ^1,2 , YE Zhidong ^1,2 ,  LIU Peng ^1,2

1. Peking University China-Japan Friendship School of Clinical Medicine, Beijing, 100029, P. R. China;
2. Department of Cardiovascular Surgery, China-Japan Friendship Hospital, Beijing, 100029, P. R. China;

Corresponding author：

LIU Peng, Email: liupeng5417@163.com

Keywords：

Carotid plaque; radiomics; machine learning

DOI：

10.7507/1007-4848.202302050

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To construct a radiomics model for identifying clinical high-risk carotid plaques. Methods A retrospective analysis was conducted on patients with carotid artery stenosis in China-Japan Friendship Hospital from December 2016 to June 2022. The patients were classified as a clinical high-risk carotid plaque group and a clinical low-risk carotid plaque group according to the occurrence of stroke, transient ischemic attack and other cerebrovascular clinical symptoms within six months. Six machine learning models including eXtreme Gradient Boosting, support vector machine, Gaussian Naive Bayesian, logical regression, K-nearest neighbors and artificial neural network were established. We also constructed a joint predictive model combined with logistic regression analysis of clinical risk factors. Results Finally 652 patients were collected, including 427 males and 225 females, with an average age of 68.2 years. The results showed that the prediction ability of eXtreme Gradient Boosting was the best among the six machine learning models, and the area under the curve (AUC) in validation dataset was 0.751. At the same time, the AUC of eXtreme Gradient Boosting joint prediction model established by clinical data and carotid artery imaging data validation dataset was 0.823. Conclusion Radiomics features combined with clinical feature model can effectively identify clinical high-risk carotid plaques.

Citation： WANG Xiaohui, LÜ Xiaoshuo, LIU Zhan, ZHEN Yanan, LIN Fan, ZHENG Xia, LIU Xiaopeng, SUN Guang, WEN Jianyan, YE Zhidong, LIU Peng. Construction of a machine learning model for identifying clinical high-risk carotid plaques based on radiomics. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2024, 31(1): 24-34. doi: 10.7507/1007-4848.202302050 Copy

1.	Hassani S, Fisher M. Management of atherosclerotic carotid artery disease: A brief overview and update. Am J Med, 2022, 135(4): 430-434.
2.	Zhang R, Zhang Q, Ji A, et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol, 2021, 31(5): 3116-3126.
3.	Zhou T, Jia S, Wang X, et al. Diagnostic performance of MRI for detecting intraplaque hemorrhage in the carotid arteries: A meta-analysis. Eur Radiol, 2019, 29(10): 5129-5138.
4.	van Dam-Nolen DHK, van Egmond NCM, Dilba K, et al. Sex differences in plaque composition and morphology among symptomatic patients with mild-to-moderate carotid artery stenosis. Stroke, 2022, 53(2): 370-378.
5.	Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology, 2016, 278(2): 563-577.
6.	陈忠, 杨耀国. 颈动脉狭窄诊治指南. 中国血管外科杂志(电子版), 2017, 9(3): 169-175.
7.	Aboyans V, Ricco JB, Bartelink MEL, et al. 2017 ESC guidelines on the diagnosis and treatment of peripheral arterial diseases, in collaboration with the European Society for Vascular Surgery (ESVS): Document covering atherosclerotic disease of extracranial carotid and vertebral, mesenteric, renal, upper and lower extremity arteriesEndorsed by: The European Stroke Organization (ESO)The Task Force for the Diagnosis and Treatment of Peripheral Arterial Diseases of the European Society of Cardiology (ESC) and of the European Society for Vascular Surgery (ESVS). Eur Heart J, 2018, 39(9): 763-816.
8.	Schindler A, Schinner R, Altaf N, et al. Prediction of stroke risk by detection of hemorrhage in carotid plaques: Meta-analysis of individual patient data. JACC Cardiovasc Imaging, 2020, 13(2 Pt 1): 395-406.
9.	Zhao X, Li R, Hippe DS, et al. Chinese atherosclerosis risk evaluation (CARE Ⅱ) study: A novel cross-sectional, multicentre study of the prevalence of high-risk atherosclerotic carotid plaque in Chinese patients with ischaemic cerebrovascular events-design and rationale. Stroke Vasc Neurol, 2017, 2(1): 15-20.
10.	Liu J, Guo W, Zeng P, et al. Vertebral MRI-based radiomics model to differentiate multiple myeloma from metastases: Influence of features number on logistic regression model performance. Eur Radiol, 2022, 32(1): 572-581.
11.	Batista GE, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor Newsl, 2004, 6(1): 20-29.
12.	Chawla N, Bowyer K, Hall L, et al. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res (JAIR), 2002, 16: 321-357.
13.	Liu Z, Wang Y, Shen F, et al. Radiomics based on readout-segmented echo-planar imaging (RS-EPI) diffusion-weighted imaging (DWI) for prognostic risk stratification of patients with rectal cancer: A two-centre, machine learning study using the framework of predictive, preventive, and personalized medicine. EPMA J, 2022, 13(4): 633-647.
14.	Liu J, Tao W, Wang Z, et al. Radiomics-based prediction of hemorrhage expansion among patients with thrombolysis/thrombectomy related-hemorrhagic transformation using machine learning. Ther Adv Neurol Disord, 2021, 14: 17562864211060029.
15.	Fisch U, von Felten S, Wiencierz A, et al. Editor's choice—Risk of stroke before revascularisation in patients with symptomatic carotid stenosis: A pooled analysis of randomised controlled trials. Eur J Vasc Endovasc Surg, 2021, 61(6): 881-887.
16.	Cheng SF, Brown MM, Simister RJ, et al. Contemporary prevalence of carotid stenosis in patients presenting with ischaemic stroke. Br J Surg, 2019, 106(7): 872-878.
17.	Sukun A, Onal C, Tufanoğlu FH. The effect of living at high altitude on carotid intima-media thickness in the elderly: A comparative study. Acta Radiol, 2022, 63(7): 986-992.
18.	Montero D, Diaz-Cañestro C, Keiser S, et al. Arterial stiffness is strongly and negatively associated with the total volume of red blood cells. Int J Cardiol, 2016, 221: 77-80.
19.	Selwaness M, van den Bouwhuijsen Q, Mattace-Raso FU, et al. Arterial stiffness is associated with carotid intraplaque hemorrhage in the general population: The Rotterdam study. Arterioscler Thromb Vasc Biol, 2014, 34(4): 927-932.
20.	Alizargar J, Bai CH. Factors associated with carotid Intima media thickness and carotid plaque score in community-dwelling and non-diabetic individuals. BMC Cardiovasc Disord, 2018, 18(1): 21.
21.	Sjöberg S, Shi GP. Cysteine protease cathepsins in atherosclerosis and abdominal aortic aneurysm. Clin Rev Bone Miner Metab, 2011, 9(2): 138-147.
22.	Duewell P, Kono H, Rayner KJ, et al. NLRP3 inflammasomes are required for atherogenesis and activated by cholesterol crystals. Nature, 2010, 464(7293): 1357-1361.
23.	Wang N, Bai X, Jin B, et al. The association of serum cathepsin B concentration with age-related cardiovascular-renal subclinical state in a healthy Chinese population. Arch Gerontol Geriatr, 2016, 65: 146-155.
24.	Mazza A, Pessina AC, Tikhonoff V, et al. Serum creatinine and coronary mortality in the elderly with normal renal function: The CArdiovascular STudy in the ELderly (CASTEL). J Nephrol, 2005, 18(5): 606-612.
25.	Buscemi S, Corleo D, Buscemi C, et al. Influence of habitual dairy food intake on LDL cholesterol in a population-based cohort. Nutrients, 2021, 13(2): 593.
26.	Nettleton JA, Matijevic N, Follis JL, et al. Associations between dietary patterns and flow cytometry-measured biomarkers of inflammation and cellular activation in the Atherosclerosis Risk in Communities (ARIC) Carotid Artery MRI Study. Atherosclerosis, 2010, 212(1): 260-267.
27.	Massberg S, Schürzinger K, Lorenz M, et al. Platelet adhesion via glycoprotein Ⅱb integrin is critical for atheroprogression and focal cerebral ischemia: An in vivo study in mice lacking glycoprotein Ⅱb. Circulation, 2005, 112(8): 1180-1188.
28.	Monaco C, Gregan SM, Navin TJ, et al. Toll-like receptor-2 mediates inflammation and matrix degradation in human atherosclerosis. Circulation, 2009, 120(24): 2462-2469.
29.	Tischmann L, Adam TC, Mensink RP, et al. Longer-term soy nut consumption improves vascular function and cardiometabolic risk markers in older adults: Results of a randomized, controlled cross-over trial. Clin Nutr, 2022, 41(5): 1052-1058.
30.	Yaldiz M, Asil K. Evaluation of carotid intima media thickness and hematologic inflammatory markers in patients with chronic spontaneous urticaria. Postepy Dermatol Alergol, 2020, 37(2): 214-220.
31.	Ma H, Lin H, Hu Y, et al. Mean platelet volume in relation to carotid atherosclerosis in normotensive, euglycemic, and normolipidemic Chinese middle-aged and elderly adults. Angiology, 2014, 65(6): 512-518.
32.	Dai Z, Gao J, Li S, et al. Mean platelet volume as a predictor for restenosis after carotid angioplasty and stenting. Stroke, 2018, 49(4): 872-876.
33.	Haidegger M, Kneihsl M, Niederkorn K, et al. Mean platelet volume does not predict restenosis after carotid artery stenting in whites. Stroke, 2020, 51(3): 986-989.
34.	Mayer FJ, Hoke M, Schillinger M, et al. Mean platelet volume predicts outcome in patients with asymptomatic carotid artery disease. Eur J Clin Invest, 2014, 44(1): 22-28.
35.	Xu M, He XY, Huang P. The relationship between the mean platelet volume and carotid atherosclerosis and prognosis in patients with acute cerebral infarction. Biomed Res Int, 2020, 2020: 6685740.
36.	Arévalo-Lorido JC, Carretero-Gómez J, Villar-Vaca P. Mean platelet volume predicting carotid atherosclerosis in atherothrombotic ischemic stroke. Ir J Med Sci, 2012, 181(2): 179-183.
37.	Culleton S, Baradaran H, Kim SE, et al. MRI detection of carotid intraplaque hemorrhage and postintervention cognition. AJNR Am J Neuroradiol, 2022, 43(12): 1762-1769.
38.	Bos D, Arshi B, van den Bouwhuijsen QJA, et al. Atherosclerotic carotid plaque composition and incident stroke and coronary events. J Am Coll Cardiol, 2021, 77(11): 1426-1435.
39.	Chen Q, Zhang L, Liu S, et al. Radiomics in precision medicine for gastric cancer: Opportunities and challenges. Eur Radiol, 2022, 32(9): 5852-5868.
40.	Avanzo M, Stancanello J, Pirrone G, et al. Radiomics and deep learning in lung cancer. Strahlenther Onkol, 2020, 196(10): 879-887.
41.	Kozikowski M, Suarez-Ibarrola R, Osiecki R, et al. Role of radiomics in the prediction of muscle-invasive bladder cancer: A systematic review and meta-analysis. Eur Urol Focus, 2022, 8(3): 728-738.
42.	Yang J, Wu Q, Xu L, et al. Integrating tumor and nodal radiomics to predict lymph node metastasis in gastric cancer. Radiother Oncol, 2020, 150: 89-96.
43.	Naqvi TZ, Lee MS. Carotid intima-media thickness and plaque in cardiovascular risk assessment. JACC Cardiovasc Imaging, 2014, 7(10): 1025-1038.
44.	Xie W, Wu Y, Wang W, et al. A longitudinal study of carotid plaque and risk of ischemic cardiovascular disease in the Chinese population. J Am Soc Echocardiogr, 2011, 24(7): 729-737.
45.	Abeysuriya V, Wijesinha NAI, Priyadharshan PP, et al. Composite carotid intima-media thickness as a risk predictor of coronary heart disease in a selected population in Sri Lanka. PLoS One, 2022, 17(8): e0271986.

1. Hassani S, Fisher M. Management of atherosclerotic carotid artery disease: A brief overview and update. Am J Med, 2022, 135(4): 430-434.
2. Zhang R, Zhang Q, Ji A, et al. Identification of high-risk carotid plaque with MRI-based radiomics and machine learning. Eur Radiol, 2021, 31(5): 3116-3126.
3. Zhou T, Jia S, Wang X, et al. Diagnostic performance of MRI for detecting intraplaque hemorrhage in the carotid arteries: A meta-analysis. Eur Radiol, 2019, 29(10): 5129-5138.
4. van Dam-Nolen DHK, van Egmond NCM, Dilba K, et al. Sex differences in plaque composition and morphology among symptomatic patients with mild-to-moderate carotid artery stenosis. Stroke, 2022, 53(2): 370-378.
5. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology, 2016, 278(2): 563-577.
6. 陈忠, 杨耀国. 颈动脉狭窄诊治指南. 中国血管外科杂志(电子版), 2017, 9(3): 169-175.
7. Aboyans V, Ricco JB, Bartelink MEL, et al. 2017 ESC guidelines on the diagnosis and treatment of peripheral arterial diseases, in collaboration with the European Society for Vascular Surgery (ESVS): Document covering atherosclerotic disease of extracranial carotid and vertebral, mesenteric, renal, upper and lower extremity arteriesEndorsed by: The European Stroke Organization (ESO)The Task Force for the Diagnosis and Treatment of Peripheral Arterial Diseases of the European Society of Cardiology (ESC) and of the European Society for Vascular Surgery (ESVS). Eur Heart J, 2018, 39(9): 763-816.
8. Schindler A, Schinner R, Altaf N, et al. Prediction of stroke risk by detection of hemorrhage in carotid plaques: Meta-analysis of individual patient data. JACC Cardiovasc Imaging, 2020, 13(2 Pt 1): 395-406.
9. Zhao X, Li R, Hippe DS, et al. Chinese atherosclerosis risk evaluation (CARE Ⅱ) study: A novel cross-sectional, multicentre study of the prevalence of high-risk atherosclerotic carotid plaque in Chinese patients with ischaemic cerebrovascular events-design and rationale. Stroke Vasc Neurol, 2017, 2(1): 15-20.
10. Liu J, Guo W, Zeng P, et al. Vertebral MRI-based radiomics model to differentiate multiple myeloma from metastases: Influence of features number on logistic regression model performance. Eur Radiol, 2022, 32(1): 572-581.
11. Batista GE, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor Newsl, 2004, 6(1): 20-29.
12. Chawla N, Bowyer K, Hall L, et al. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res (JAIR), 2002, 16: 321-357.
13. Liu Z, Wang Y, Shen F, et al. Radiomics based on readout-segmented echo-planar imaging (RS-EPI) diffusion-weighted imaging (DWI) for prognostic risk stratification of patients with rectal cancer: A two-centre, machine learning study using the framework of predictive, preventive, and personalized medicine. EPMA J, 2022, 13(4): 633-647.
14. Liu J, Tao W, Wang Z, et al. Radiomics-based prediction of hemorrhage expansion among patients with thrombolysis/thrombectomy related-hemorrhagic transformation using machine learning. Ther Adv Neurol Disord, 2021, 14: 17562864211060029.
15. Fisch U, von Felten S, Wiencierz A, et al. Editor's choice—Risk of stroke before revascularisation in patients with symptomatic carotid stenosis: A pooled analysis of randomised controlled trials. Eur J Vasc Endovasc Surg, 2021, 61(6): 881-887.
16. Cheng SF, Brown MM, Simister RJ, et al. Contemporary prevalence of carotid stenosis in patients presenting with ischaemic stroke. Br J Surg, 2019, 106(7): 872-878.
17. Sukun A, Onal C, Tufanoğlu FH. The effect of living at high altitude on carotid intima-media thickness in the elderly: A comparative study. Acta Radiol, 2022, 63(7): 986-992.
18. Montero D, Diaz-Cañestro C, Keiser S, et al. Arterial stiffness is strongly and negatively associated with the total volume of red blood cells. Int J Cardiol, 2016, 221: 77-80.
19. Selwaness M, van den Bouwhuijsen Q, Mattace-Raso FU, et al. Arterial stiffness is associated with carotid intraplaque hemorrhage in the general population: The Rotterdam study. Arterioscler Thromb Vasc Biol, 2014, 34(4): 927-932.
20. Alizargar J, Bai CH. Factors associated with carotid Intima media thickness and carotid plaque score in community-dwelling and non-diabetic individuals. BMC Cardiovasc Disord, 2018, 18(1): 21.
21. Sjöberg S, Shi GP. Cysteine protease cathepsins in atherosclerosis and abdominal aortic aneurysm. Clin Rev Bone Miner Metab, 2011, 9(2): 138-147.
22. Duewell P, Kono H, Rayner KJ, et al. NLRP3 inflammasomes are required for atherogenesis and activated by cholesterol crystals. Nature, 2010, 464(7293): 1357-1361.
23. Wang N, Bai X, Jin B, et al. The association of serum cathepsin B concentration with age-related cardiovascular-renal subclinical state in a healthy Chinese population. Arch Gerontol Geriatr, 2016, 65: 146-155.
24. Mazza A, Pessina AC, Tikhonoff V, et al. Serum creatinine and coronary mortality in the elderly with normal renal function: The CArdiovascular STudy in the ELderly (CASTEL). J Nephrol, 2005, 18(5): 606-612.
25. Buscemi S, Corleo D, Buscemi C, et al. Influence of habitual dairy food intake on LDL cholesterol in a population-based cohort. Nutrients, 2021, 13(2): 593.
26. Nettleton JA, Matijevic N, Follis JL, et al. Associations between dietary patterns and flow cytometry-measured biomarkers of inflammation and cellular activation in the Atherosclerosis Risk in Communities (ARIC) Carotid Artery MRI Study. Atherosclerosis, 2010, 212(1): 260-267.
27. Massberg S, Schürzinger K, Lorenz M, et al. Platelet adhesion via glycoprotein Ⅱb integrin is critical for atheroprogression and focal cerebral ischemia: An in vivo study in mice lacking glycoprotein Ⅱb. Circulation, 2005, 112(8): 1180-1188.
28. Monaco C, Gregan SM, Navin TJ, et al. Toll-like receptor-2 mediates inflammation and matrix degradation in human atherosclerosis. Circulation, 2009, 120(24): 2462-2469.
29. Tischmann L, Adam TC, Mensink RP, et al. Longer-term soy nut consumption improves vascular function and cardiometabolic risk markers in older adults: Results of a randomized, controlled cross-over trial. Clin Nutr, 2022, 41(5): 1052-1058.
30. Yaldiz M, Asil K. Evaluation of carotid intima media thickness and hematologic inflammatory markers in patients with chronic spontaneous urticaria. Postepy Dermatol Alergol, 2020, 37(2): 214-220.
31. Ma H, Lin H, Hu Y, et al. Mean platelet volume in relation to carotid atherosclerosis in normotensive, euglycemic, and normolipidemic Chinese middle-aged and elderly adults. Angiology, 2014, 65(6): 512-518.
32. Dai Z, Gao J, Li S, et al. Mean platelet volume as a predictor for restenosis after carotid angioplasty and stenting. Stroke, 2018, 49(4): 872-876.
33. Haidegger M, Kneihsl M, Niederkorn K, et al. Mean platelet volume does not predict restenosis after carotid artery stenting in whites. Stroke, 2020, 51(3): 986-989.
34. Mayer FJ, Hoke M, Schillinger M, et al. Mean platelet volume predicts outcome in patients with asymptomatic carotid artery disease. Eur J Clin Invest, 2014, 44(1): 22-28.
35. Xu M, He XY, Huang P. The relationship between the mean platelet volume and carotid atherosclerosis and prognosis in patients with acute cerebral infarction. Biomed Res Int, 2020, 2020: 6685740.
36. Arévalo-Lorido JC, Carretero-Gómez J, Villar-Vaca P. Mean platelet volume predicting carotid atherosclerosis in atherothrombotic ischemic stroke. Ir J Med Sci, 2012, 181(2): 179-183.
37. Culleton S, Baradaran H, Kim SE, et al. MRI detection of carotid intraplaque hemorrhage and postintervention cognition. AJNR Am J Neuroradiol, 2022, 43(12): 1762-1769.
38. Bos D, Arshi B, van den Bouwhuijsen QJA, et al. Atherosclerotic carotid plaque composition and incident stroke and coronary events. J Am Coll Cardiol, 2021, 77(11): 1426-1435.
39. Chen Q, Zhang L, Liu S, et al. Radiomics in precision medicine for gastric cancer: Opportunities and challenges. Eur Radiol, 2022, 32(9): 5852-5868.
40. Avanzo M, Stancanello J, Pirrone G, et al. Radiomics and deep learning in lung cancer. Strahlenther Onkol, 2020, 196(10): 879-887.
41. Kozikowski M, Suarez-Ibarrola R, Osiecki R, et al. Role of radiomics in the prediction of muscle-invasive bladder cancer: A systematic review and meta-analysis. Eur Urol Focus, 2022, 8(3): 728-738.
42. Yang J, Wu Q, Xu L, et al. Integrating tumor and nodal radiomics to predict lymph node metastasis in gastric cancer. Radiother Oncol, 2020, 150: 89-96.
43. Naqvi TZ, Lee MS. Carotid intima-media thickness and plaque in cardiovascular risk assessment. JACC Cardiovasc Imaging, 2014, 7(10): 1025-1038.
44. Xie W, Wu Y, Wang W, et al. A longitudinal study of carotid plaque and risk of ischemic cardiovascular disease in the Chinese population. J Am Soc Echocardiogr, 2011, 24(7): 729-737.
45. Abeysuriya V, Wijesinha NAI, Priyadharshan PP, et al. Composite carotid intima-media thickness as a risk predictor of coronary heart disease in a selected population in Sri Lanka. PLoS One, 2022, 17(8): e0271986.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Construction of a machine learning model for identifying clinical high-risk carotid plaques based on radiomics

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content