Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study

被引:5
作者
Zhang, Kangwei [1 ]
Zhou, Xiang [1 ]
Xi, Qian [2 ]
Wang, Xinyun [3 ]
Yang, Baoqing [1 ]
Meng, Jinxi [1 ]
Liu, Ming [3 ]
Dong, Ningxin [4 ]
Wu, Xiaofen [4 ]
Song, Tao [5 ]
Wei, Lai [1 ]
Wang, Peijun [1 ]
机构
[1] Tongji Univ, Tongji Hosp, Dept Radiol, Sch Med, Shanghai 200065, Peoples R China
[2] Tongji Univ, Shanghai East Hosp, Dept Radiol, Sch Med, Shanghai 200120, Peoples R China
[3] Shanghai Jiao Tong Univ, Xinhua Hosp, Sch Med, Dept Radiol, Shanghai 200092, Peoples R China
[4] Tongji Univ, Sch Med, Tongji Hosp, Dept Informat, Shanghai 200065, Peoples R China
[5] SenseTime Res, Shanghai 200233, Peoples R China
基金
中国国家自然科学基金;
关键词
cerebral hemorrhage; surgical procedures; prognosis; machine learning; radiomics; INITIAL CONSERVATIVE TREATMENT; CEREBRAL-HEMORRHAGE; HEMATOMA GROWTH; EARLY SURGERY; SIGN; SHIFT; STICH;
D O I
10.3390/jcm12041580
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
This study aims to explore the value of a machine learning (ML) model based on radiomics features and clinical features in predicting the outcome of spontaneous supratentorial intracerebral hemorrhage (sICH) 90 days after surgery. A total of 348 patients with sICH underwent craniotomy evacuation of hematoma from three medical centers. One hundred and eight radiomics features were extracted from sICH lesions on baseline CT. Radiomics features were screened using 12 feature selection algorithms. Clinical features included age, gender, admission Glasgow Coma Scale (GCS), intraventricular hemorrhage (IVH), midline shift (MLS), and deep ICH. Nine ML models were constructed based on clinical feature, and clinical features + radiomics features, respectively. Grid search was performed on different combinations of feature selection and ML model for parameter tuning. The averaged receiver operating characteristics (ROC) area under curve (AUC) was calculated and the model with the largest AUC was selected. It was then tested using multicenter data. The combination of lasso regression feature selection and logistic regression model based on clinical features + radiomics features had the best performance (AUC: 0.87). The best model predicted an AUC of 0.85 (95%CI, 0.75-0.94) on the internal test set and 0.81 (95%CI, 0.64-0.99) and 0.83 (95%CI, 0.68-0.97) on the two external test sets, respectively. Twenty-two radiomics features were selected by lasso regression. The second-order feature gray level non-uniformity normalized was the most important radiomics feature. Age is the feature with the greatest contribution to prediction. The combination of clinical features and radiomics features using logistic regression models can improve the outcome prediction of patients with sICH 90 days after surgery.
引用
收藏
页数:16
相关论文
共 50 条
[41]   Machine learning-based prediction of symptomatic intracerebral hemorrhage after intravenous thrombolysis for stroke: a large multicenter study [J].
Wen, Rui ;
Wang, Miaoran ;
Bian, Wei ;
Zhu, Haoyue ;
Xiao, Ying ;
He, Qian ;
Wang, Yu ;
Liu, Xiaoqing ;
Shi, Yangdi ;
Hong, Zhe ;
Xu, Bing .
FRONTIERS IN NEUROLOGY, 2023, 14
[42]   The diagnostic value of a non-contrast computed tomography scan-based radiomics model for acute aortic dissection [J].
Zhou, Zewang ;
Yang, Jinquan ;
Wang, Shuntao ;
Li, Weihao ;
Xie, Lei ;
Li, Yifan ;
Zhang, Changzheng .
MEDICINE, 2021, 100 (22) :E26212
[43]   Non-contrast CT-based radiomic signature for screening thoracic aortic dissections: a multicenter study [J].
Guo, Yifan ;
Chen, Xiaojun ;
Lin, Xianda ;
Chen, Litian ;
Shu, Jiner ;
Pang, Peipei ;
Cheng, Jianmin ;
Xu, Maosheng ;
Sun, Zhichao .
EUROPEAN RADIOLOGY, 2021, 31 (09) :7067-7076
[44]   Non-contrast CT-based radiomic signature for screening thoracic aortic dissections: a multicenter study [J].
Yifan Guo ;
Xiaojun Chen ;
Xianda Lin ;
Litian Chen ;
Jiner Shu ;
Peipei Pang ;
Jianmin Cheng ;
Maosheng Xu ;
Zhichao Sun .
European Radiology, 2021, 31 :7067-7076
[45]   Prediction of functional outcome in supratentorial intracerebral hemorrhage patients treated with stereotactic computed tomographic-guided aspiration and recombinant tissue plasminogen activator (rt-PA) [J].
Dang, Lan H. ;
Thach, Khanh N. ;
Nguyen, Yen T. ;
Nguyen, Tuyen V. ;
Dinh, Ha H. ;
Nguyen, Loan T. ;
Nguyen, Cuc T. .
INTERDISCIPLINARY NEUROSURGERY-ADVANCED TECHNIQUES AND CASE MANAGEMENT, 2024, 37
[46]   Predicting functional outcomes of patients with spontaneous intracerebral hemorrhage based on explainable machine learning models: a multicenter retrospective study [J].
Pan, Bin ;
Li, Fengda ;
Liu, Chuanghong ;
Li, Zeyi ;
Sun, Chengfa ;
Xia, Kaijian ;
Xu, Hong ;
Kong, Gang ;
Gu, Longyuan ;
Cheng, Kaiyuan .
FRONTIERS IN NEUROLOGY, 2025, 15
[47]   Development of a non-contrast CT-based radiomics nomogram for early prediction of delayed cerebral ischemia in aneurysmal subarachnoid hemorrhage [J].
Lingxu Chen ;
Xiaochen Wang ;
Sihui Wang ;
Xuening Zhao ;
Ying Yan ;
Mengyuan Yuan ;
Shengjun Sun .
BMC Medical Imaging, 25 (1)
[48]   Associated Factors of Long-Term Functional Outcome and Recovery Pattern After Intracerebral Hemorrhage: A Prospective Population-Based Study in Ulaanbaatar, Mongolia [J].
Sakamoto, Yuki ;
Bosookhuu, Oyungerel ;
Ouyang, Menglu ;
Banzrai, Chimeglkham ;
Dambasuren, Bolormaa ;
Wang, Xia ;
Turbat, Sarantsetseg ;
Myadagsuren, Mandakhnar ;
Boldbayar, Punsaldulam ;
Baatar, Khandsuren ;
Erdenedalai, Tuguldur ;
Munkhtur, Uuriintuya ;
Yadamsuren, Erdenechimeg ;
Chen, Xiaoying ;
Anderson, Craig S. .
STROKE, 2025, 56 (02) :437-446
[49]   Left ventricular area on non-contrast cardiac computed tomography as a predictor of incident heart failure The Multi-Ethnic Study of Atherosclerosis [J].
Bittencourt, Marcio Sommer ;
Blankstein, Ron ;
Mao, Songshou ;
Rivera, Juan J. ;
Bertoni, Alain G. ;
Shaw, Leslee J. ;
Blumenthal, Roger S. ;
Budoff, Matthew J. ;
Nasir, Khurram .
JOURNAL OF CARDIOVASCULAR COMPUTED TOMOGRAPHY, 2016, 10 (06) :500-506
[50]   Prediction of recurrence after surgery in colorectal cancer patients using radiomics from diagnostic contrast-enhanced computed tomography: a two-center study [J].
Badic, Bogdan ;
Da-Ano, Ronrick ;
Poirot, Karine ;
Jaouen, Vincent ;
Magnin, Benoit ;
Gagniere, Johan ;
Pezet, Denis ;
Hatt, Mathieu ;
Visvikis, Dimitris .
EUROPEAN RADIOLOGY, 2022, 32 (01) :405-414