Share:
Share this content in WeChat
X
Clinical Article
Construction of a nomogram model for hemorrhagic transformation risk after mechanical thrombectomy in patients with acute stroke
LIU Zhen  HUANG Xiaobin  PENG Mingyang  WANG Tongxing  XIE Guanghui  REN Jun  Yin Xindao 

Cite this article as: Liu Z, Huang XB, Peng MY, et al. Construction of a nomogram model for hemorrhagic transformation risk after mechanical thrombectomy in patients with acute stroke[J]. Chin J Magn Reson Imaging, 2022, 13(4): 15-19. DOI:10.12015/issn.1674-8034.2022.04.003.


[Abstract] Objective To construct a nomogram model for hemorrhage transformation after mechanical thrombectomy in acute stroke based on multimodal MRI radiomics and clinical risk factors.Materials and Methods A total of 174 patient cases with acute ischemic stroke in Nanjing First Hospital from January 2017 to December 2020 were analyzed retrospectively. The patients were randomly divided into the training set (n=122) and test set (n=52). Then the patients were divided into hemorrhage transformation group and no hemorrhage transformation group according to the MRI images after treatment. A.K. software was used to extract diffusion weighted imaging and perfusion weighted imaging lesions features and construct radiomics tags. Multivariate Logistic regression was used to select the best predictors and construct a nomogram model. The receiver operating characteristic (ROC) curve was utilized to evaluate the predictive performance of the model.Results A total of 1584 radiomics features were extracted from each patient. After dimensionality reduction, 15 features that were highly associated with hemorrhage transformation were screened out. ROC showed that the AUC of nomograph model in the training set was 0.979 (sensitivity and specificity: 0.950, 0.989), which included radiomics labels, atrial fibrillation history, age, and NIHSS score on admission. The AUC in the test set was 0.885 (sensitivity and specificity: 0.836, 0.908). Both of them were better than models built based on pure radiomics lables (AUC=0.763) or clinical features (AUC=0.707).Conclusions Radiomics and machine learning based on multimodal MRI and clinical features are reliable to predict hemorrhage transformation after mechanical thrombectomy in acute ischemic stroke.
[Keywords] stroke;machine learning;radiomics;nomogram model;diffusion weighted imaging;perfusion weighted imaging;hemorrhage transformation

LIU Zhen1, 2   HUANG Xiaobin1   PENG Mingyang1   WANG Tongxing1   XIE Guanghui1   REN Jun1   Yin Xindao1*  

1 Department of Radiology, Nanjing First Hospital, Nanjing Medical University, Nanjing 210006, China

2 Department of CT and MRI, the Affiliated Chuzhou Hospital of Anhui Medical University (the First People's Hospital of Chuzhou), Chuzhou 239000, China

Yin XD, E-mail: y.163yy@163.com

Conflicts of interest   None.

Received  2021-12-23
Accepted  2022-03-25
DOI: 10.12015/issn.1674-8034.2022.04.003
Cite this article as: Liu Z, Huang XB, Peng MY, et al. Construction of a nomogram model for hemorrhagic transformation risk after mechanical thrombectomy in patients with acute stroke[J]. Chin J Magn Reson Imaging, 2022, 13(4): 15-19.DOI:10.12015/issn.1674-8034.2022.04.003

[1]
Zhou M, Wang H, Zeng X, et al. Mortality, morbidity, and risk factors in China and its provinces, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017[J]. Lancet, 2019, 394(10204): 1145-1158. DOI: 10.1016/S0140-6736(19)30427-1.
[2]
Rajsic S, Gothe H, Borba HH, et al. Economic burden of stroke: a systematic review on post-stroke care[J]. Eur J Health Econ, 2019, 20(1): 107-134. DOI: 10.1007/s10198-018-0984-0.
[3]
Ge WQ, Chen J, Pan H, et al. Analysis of Risk Factors Increased Hemorrhagic Transformation after Acute Ischemic Stroke[J]. J Stroke Cerebrovasc Dis, 2018, 27(12): 3587-3590. DOI: 10.1016/j.jstrokecerebrovasdis.2018.08.028.
[4]
Wu Y, Chen H, Liu X, et al. A new nomogram for individualized prediction of the probability of hemorrhagic transformation after intravenous thrombolysis for ischemic stroke patients[J]. BMC Neurol, 2020, 20(1): 426. DOI: 10.1186/s12883-020-02002-w.
[5]
Cai QK, Lin RT, Lin HS, et al. Role of 5 risk scales in predicting symptomatic intracerebral hemorrhage and poor outcome in AIS patients after intravenous thrombolytic therapy[J]. Chin J Geriatr Heart Brain Vessel Dis, 2017, 19(9): 906-909. DOI: 10.3969/j.issn.1009-0126.2017.09.003.
[6]
Oppenheim C, Samson Y, Dormont D, et al. DWI prediction of symptomatic hemorrhagic transformation in acute MCA infarct[J]. J Neuroradiol, 2002, 29(1): 6-13. DOI: 10.1109/CBMS.2001.941748.
[7]
Deo RC. Machine Learning in Medicine[J]. Circulation. 2015, 132(20): 1920-1930. DOI: 10.1161/CIRCULATIONAHA.115.001593.
[8]
Sirsat MS, Fermé E, Câmara J. Machine Learning for Brain Stroke: A Review[J]. J Stroke Cerebrovasc Dis, 2020, 29(10): 105162. DOI: 10.1016/j.jstrokecerebrovasdis.2020.105162.
[9]
Heo J, Yoon JG, Park H, et al. Machine Learning-Based Model for Prediction of Outcomes in Acute Stroke[J]. Stroke, 2019, 50(5): 1263-1265. DOI: 10.1161/STROKEAHA.118.024293.
[10]
Kumar V, Gu Y, Basu S, et al. Radiomics: the process and the challenges[J]. Magn Reson Imaging, 2012, 30(9): 1234-1248. DOI: 10.1016/j.mri.2012.06.010.
[11]
Li Q, Ye ZX. Radiomics: the process and applications in tumor research[J]. Zhonghua Zhong Liu Za Zhi, 2018, 40(11): 801-804. Chinese Journal of Oncology, DOI: 10.3760/cma.j.issn.0253-3766.2018.11.001.
[12]
Kamal H, Lopez V, Sheth SA. Machine Learning in Acute Ischemic Stroke Neuroimaging[J]. Front Neurol, 2018, 9: 945. DOI: 10.3389/fneur.2018.00945.
[13]
Xie K, Sun HF, Lin T, et al. Research progresses in feature extraction of radiomics[J]. Chin J Med Imaging Technol, 2017, 33(12): 1792-1796. DOI: 10.13929/j.1003-3289.201707022.
[14]
Suh CH, Jung SC, Cho SJ, et al. MRI for prediction of hemorrhagic transformation in acute ischemic stroke: a systematic review and meta-analysis[J]. Acta Radiol, 2020, 61(7): 964-972. DOI: 10.1177/0284185119887593.
[15]
Cai J, Zhou Y, Zhao Y, et al. Comparison of various reconstructions derived from dual-energy CT immediately after endovascular treatment of acute ischemic stroke in predicting hemorrhage[J]. Eur Radiol, 2021, 31(7): 4419-4427. DOI: 10.1007/s00330-020-07574-2.
[16]
Lovelock C, Anslow P, Molyneux A, et al. Substantial observer variability in the differentiation between primary intracerebral hemorrhage and hemorrhagic transformation of infarction on CT brain imaging[J]. Stroke, 2009, 40(12): 3763. DOI: 10.1161/STROKEAHA.109.553933.
[17]
Langel C, Surlan K. Infarct-core CT perfusion parameters in predicting post-thrombolysis hemorrhagic transformation of acute ischemic stroke[J]. Radiology and Oncology, 2019, 53(1): 25-30. DOI: 10.2478/raon-2018-0048.
[18]
Sun FT, Zhang HN, Yu L, et al. Value of CT perfusion in predicting hemorrhagic transformation in acute ischemic cerebral infarction patients after thrombolysis. Chin J Geriatr Heart Brain Vessel Dis, 2021, 23(1): 4. DOI: 10.3969/j.issn.1009-0126.2021.01.016.
[19]
Souza LC, Payabvash S, Wang Y, et al. Admission CT perfusion is an independent predictor of hemorrhagic transformation in acute stroke with similar accuracy to DWI[J]. Cerebrovasc Dis, 2012, 33(1): 8-15. DOI: 10.1159/000331914.
[20]
Yu Y, Guo D, Lou M, et al. Prediction of Hemorrhagic Transformation Severity in Acute Stroke From Source Perfusion MRI[J]. IEEE Trans Biomed Eng, 2018, 65(9): 2058-2065. DOI: 10.1109/TBME.2017.2783241.
[21]
Agarwal S, Scher E, Lord A, et al. Redefined Measure of Early Neurological Improvement Shows Treatment Benefit of Alteplase Over Placebo[J]. Stroke, 2020, 51(4): 1226-1230. DOI: 10.1161/STROKEAHA.119.027476.
[22]
Wen L, Zhang S, Wan K, et al. Risk factors of haemorrhagic transformation for acute ischaemic stroke in Chinese patients receiving intravenous thrombolysis: A meta-analysis[J]. Medicine (Baltimore), 2020, 99(7): e18995. DOI: 10.1097/MD.0000000000018995.
[23]
Rose DZ, Meriwether JN, Fradley MG, et al. Protocol for AREST: Apixaban for Early Prevention of Recurrent Embolic Stroke and Hemorrhagic Transformation-A Randomized Controlled Trial of Early Anticoagulation After Acute Ischemic Stroke in Atrial Fibrillation[J]. Front Neurol, 2019, 10: 975. DOI: 10.3389/fneur.2019.00975.

PREV Preliminary study of diffusion tensor imaging and 18F-AV1451 PET tau protein brain imaging in the diagnosis and differential diagnosis of MCI
NEXT The diagnostic value of 18F-FDG PET/MR for cerebral tumefactive demyelinating lesions
  



Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn