Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study
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...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/4/1580 |
| _version_ | 1797620192398802944 |
|---|---|
| author | Kangwei Zhang Xiang Zhou Qian Xi Xinyun Wang Baoqing Yang Jinxi Meng Ming Liu Ningxin Dong Xiaofen Wu Tao Song Lai Wei Peijun Wang |
| author_facet | Kangwei Zhang Xiang Zhou Qian Xi Xinyun Wang Baoqing Yang Jinxi Meng Ming Liu Ningxin Dong Xiaofen Wu Tao Song Lai Wei Peijun Wang |
| author_sort | Kangwei Zhang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T08:37:35Z |
| format | Article |
| id | doaj.art-5213ad1db40046f4956ab535a111b6c7 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T08:37:35Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-5213ad1db40046f4956ab535a111b6c72023-11-16T21:21:39ZengMDPI AGJournal of Clinical Medicine2077-03832023-02-01124158010.3390/jcm12041580Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter StudyKangwei Zhang0Xiang Zhou1Qian Xi2Xinyun Wang3Baoqing Yang4Jinxi Meng5Ming Liu6Ningxin Dong7Xiaofen Wu8Tao Song9Lai Wei10Peijun Wang11Department of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Radiology, Shanghai East Hospital, Tongji University School of Medicine, Shanghai 200120, ChinaDepartment of Radiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200092, ChinaDepartment of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Radiology, Xinhua Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200092, ChinaDepartment of Information, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Information, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaSenseTime Research, Shanghai 200233, ChinaDepartment of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaDepartment of Radiology, Tongji Hospital, Tongji University School of Medicine, Shanghai 200065, ChinaThis 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.https://www.mdpi.com/2077-0383/12/4/1580cerebral hemorrhagesurgical proceduresprognosismachine learningradiomics |
| spellingShingle | Kangwei Zhang Xiang Zhou Qian Xi Xinyun Wang Baoqing Yang Jinxi Meng Ming Liu Ningxin Dong Xiaofen Wu Tao Song Lai Wei Peijun Wang Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study Journal of Clinical Medicine cerebral hemorrhage surgical procedures prognosis machine learning radiomics |
| title | Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study |
| title_full | Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study |
| title_fullStr | Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study |
| title_full_unstemmed | Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study |
| title_short | Outcome Prediction of Spontaneous Supratentorial Intracerebral Hemorrhage after Surgical Treatment Based on Non-Contrast Computed Tomography: A Multicenter Study |
| title_sort | outcome prediction of spontaneous supratentorial intracerebral hemorrhage after surgical treatment based on non contrast computed tomography a multicenter study |
| topic | cerebral hemorrhage surgical procedures prognosis machine learning radiomics |
| url | https://www.mdpi.com/2077-0383/12/4/1580 |
| work_keys_str_mv | AT kangweizhang outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT xiangzhou outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT qianxi outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT xinyunwang outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT baoqingyang outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT jinximeng outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT mingliu outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT ningxindong outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT xiaofenwu outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT taosong outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT laiwei outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy AT peijunwang outcomepredictionofspontaneoussupratentorialintracerebralhemorrhageaftersurgicaltreatmentbasedonnoncontrastcomputedtomographyamulticenterstudy |