1
|
Geng Z, Yang C, Zhao Z, Yan Y, Guo T, Liu C, Wu A, Wu X, Wei L, Tian Y, Hu P, Wang K. Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage. J Transl Med 2024; 22:236. [PMID: 38439097 PMCID: PMC10910789 DOI: 10.1186/s12967-024-04896-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Accepted: 01/14/2024] [Indexed: 03/06/2024] Open
Abstract
BACKGROUND Spontaneous intracerebral hemorrhage (sICH) is associated with significant mortality and morbidity. Predicting the prognosis of patients with sICH remains an important issue, which significantly affects treatment decisions. Utilizing readily available clinical parameters to anticipate the unfavorable prognosis of sICH patients holds notable clinical significance. This study employs five machine learning algorithms to establish a practical platform for the prediction of short-term prognostic outcomes in individuals afflicted with sICH. METHODS Within the framework of this retrospective analysis, the model underwent training utilizing data gleaned from 413 cases from the training center, with subsequent validation employing data from external validation center. Comprehensive clinical information, laboratory analysis results, and imaging features pertaining to sICH patients were harnessed as training features for machine learning. We developed and validated the model efficacy using all the selected features of the patients using five models: Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), XGboost and LightGBM, respectively. The process of Recursive Feature Elimination (RFE) was executed for optimal feature screening. An internal five-fold cross-validation was employed to pinpoint the most suitable hyperparameters for the model, while an external five-fold cross-validation was implemented to discern the machine learning model demonstrating the superior average performance. Finally, the machine learning model with the best average performance is selected as our final model while using it for external validation. Evaluation of the machine learning model's performance was comprehensively conducted through the utilization of the ROC curve, accuracy, and other relevant indicators. The SHAP diagram was utilized to elucidate the variable importance within the model, culminating in the amalgamation of the above metrics to discern the most succinct features and establish a practical prognostic prediction platform. RESULTS A total of 413 patients with sICH patients were collected in the training center, of which 180 were patients with poor prognosis. A total of 74 patients with sICH were collected in the external validation center, of which 26 were patients with poor prognosis. Within the training set, the test set AUC values for SVM, LR, RF, XGBoost, and LightGBM models were recorded as 0.87, 0.896, 0.916, 0.885, and 0.912, respectively. The best average performance of the machine learning models in the training set was the RF model (average AUC: 0.906 ± 0.029, P < 0.01). The model still maintains a good performance in the external validation center, with an AUC of 0.817 (95% CI 0.705-0.928). Pertaining to feature importance for short-term prognostic attributes of sICH patients, the NIHSS score reigned supreme, succeeded by AST, Age, white blood cell, and hematoma volume, among others. In culmination, guided by the RF model's variable importance weight and the model's ROC curve insights, the NIHSS score, AST, Age, white blood cell, and hematoma volume were integrated to forge a short-term prognostic prediction platform tailored for sICH patients. CONCLUSION We constructed a prediction model based on the results of the RF model incorporating five clinically accessible predictors with reliable predictive efficacy for the short-term prognosis of sICH patients. Meanwhile, the performance of the external validation set was also more stable, which can be used for accurate prediction of short-term prognosis of sICH patients.
Collapse
Affiliation(s)
- Zhi Geng
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Chaoyi Yang
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Ziye Zhao
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Yibing Yan
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Tao Guo
- Center for Biomedical Imaging, University of Science and Technology of China, Hefei, 230026, Anhui, China
| | - Chaofan Liu
- Center for Biomedical Imaging, University of Science and Technology of China, Hefei, 230026, Anhui, China
| | - Aimei Wu
- Department of Neurology, The Second People's Hospital of Hefei, Hefei Hospital Affiliated to Anhui Medical University, Hefei, China
| | - Xingqi Wu
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Ling Wei
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
| | - Yanghua Tian
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China
- Department of Sleep Psychology, The Second Hospital of Anhui Medical University, Anhui Medical University, Hefei, China
| | - Panpan Hu
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China.
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China.
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China.
- Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China.
- Anhui Provincial Institute of Translational Medicine, Anhui Medical University, Hefei, China.
| | - Kai Wang
- Department of Neurology, The First Affiliated Hospital of Anhui Medical University, Hefei, China.
- Anhui Province Key Laboratory of Cognition and Neuropsychiatric Disorders, Hefei, China.
- Collaborative Innovation Centre of Neuropsychiatric Disorder and Mental Health, Hefei, 230000, China.
- Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China.
- Anhui Provincial Institute of Translational Medicine, Anhui Medical University, Hefei, China.
| |
Collapse
|
2
|
Zhou Y, Dong W, Wang L, Ren S, Wei W, Wu G. Lower serum cystatin C level predicts poor functional outcome in patients with hypertensive intracerebral hemorrhage independent of renal function. J Clin Hypertens (Greenwich) 2022; 25:86-94. [PMID: 36545837 PMCID: PMC9832235 DOI: 10.1111/jch.14609] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Revised: 11/19/2022] [Accepted: 11/22/2022] [Indexed: 12/24/2022]
Abstract
We explored the association between the serum level of cystatin C (CysC) at admission and short-term functional outcome in patients with hypertensive intracerebral hemorrhage (HICH) without chronic kidney disease (CKD). A total of 555 patients with HICH were consecutively recruited after admission and were followed-up for 3 months after admission. The primary outcome was poor functional outcome (modified Rankin Scale [mRS] score ≥ 3). The median serum CysC level in our cohort was 1.03 mg/L (interquartile range, .89-1.20). Patients were categorized into four groups according to the serum CysC quartiles. Multivariate logistic regression analysis revealed a negative association between serum CysC and poor functional outcome at 3-month follow-up (quartile [Q]1 vs. Q4: adjusted odds ratio [OR] = .260, 95% confidence interval [CI] = .098, .691, p < .001). The negative association between serum CysC and poor functional outcome at 3 months was more pronounced in subgroups with smaller hematoma volume (≤ 30 mL), and absence of secondary intraventricular hemorrhage (IVH). Addition of serum CysC to a model containing conventional risk factors improved the model performance with net reclassification index (NRI) of .426% (p < .001) and integrated discrimination improvement (IDI) of .043% (p < .001) for poor functional outcome. Serum CysC was found to be a negative predictor of poor short-term functional outcome in HICH patients independent of renal function.
Collapse
Affiliation(s)
- Yongfang Zhou
- Second Affiliated Hospital of Soochow UniversitySuzhouChina,Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| | - Wentao Dong
- Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| | - Likun Wang
- Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| | - Siying Ren
- Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| | - Weiqing Wei
- Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| | - Guofeng Wu
- Second Affiliated Hospital of Soochow UniversitySuzhouChina,Department of EmergencyAffiliated Hospital of Guizhou Medical UniversityGuiyangChina
| |
Collapse
|
3
|
Li Z, Khan S, Liu Y, Wei R, Yong VW, Xue M. Therapeutic strategies for intracerebral hemorrhage. Front Neurol 2022; 13:1032343. [PMID: 36408517 PMCID: PMC9672341 DOI: 10.3389/fneur.2022.1032343] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Accepted: 10/17/2022] [Indexed: 09/03/2023] Open
Abstract
Stroke is the second highest cause of death globally, with an increasing incidence in developing countries. Intracerebral hemorrhage (ICH) accounts for 10-15% of all strokes. ICH is associated with poor neurological outcomes and high mortality due to the combination of primary and secondary injury. Fortunately, experimental therapies are available that may improve functional outcomes in patients with ICH. These therapies targeting secondary brain injury have attracted substantial attention in their translational potential. Here, we summarize recent advances in therapeutic strategies and directions for ICH and discuss the barriers and issues that need to be overcome to improve ICH prognosis.
Collapse
Affiliation(s)
- Zhe Li
- Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China
- Academy of Medical Science, Zhengzhou University, Zhengzhou, China
- Henan Medical Key Laboratory of Translational Cerebrovascular Diseases, Zhengzhou, China
| | - Suliman Khan
- Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China
- Academy of Medical Science, Zhengzhou University, Zhengzhou, China
- Henan Medical Key Laboratory of Translational Cerebrovascular Diseases, Zhengzhou, China
| | - Yang Liu
- Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China
- Academy of Medical Science, Zhengzhou University, Zhengzhou, China
- Henan Medical Key Laboratory of Translational Cerebrovascular Diseases, Zhengzhou, China
| | - Ruixue Wei
- Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China
- Academy of Medical Science, Zhengzhou University, Zhengzhou, China
- Henan Medical Key Laboratory of Translational Cerebrovascular Diseases, Zhengzhou, China
| | - V. Wee Yong
- Department of Clinical Neurosciences, Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
| | - Mengzhou Xue
- Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China
- Academy of Medical Science, Zhengzhou University, Zhengzhou, China
- Henan Medical Key Laboratory of Translational Cerebrovascular Diseases, Zhengzhou, China
| |
Collapse
|
4
|
Che R, Zhang M, Sun H, Ma J, Hu W, Liu X, Ji X. Long-term outcome of cerebral amyloid angiopathy-related hemorrhage. CNS Neurosci Ther 2022; 28:1829-1837. [PMID: 35975394 PMCID: PMC9532921 DOI: 10.1111/cns.13922] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2022] [Revised: 06/30/2022] [Accepted: 07/01/2022] [Indexed: 11/30/2022] Open
Abstract
Object The long‐term functional outcome of cerebral amyloid angiopathy‐related hemorrhage (CAAH) patients is unclear. We sought to assess the long‐term functional outcome of CAAH and determine the prognostic factors associated with unfavorable outcomes. Methods We enrolled consecutive CAAH patients from 2014 to 2020 in this observational study. Baseline characteristics and clinical outcomes were presented. Multivariable logistic regression analysis was performed to identify the prognostic factors associated with long‐term outcome. Results Among the 141 CAAH patients, 76 (53.9%) achieved favorable outcomes and 28 (19.9%) of them died at 1‐year follow‐up. For the longer‐term follow‐up with a median observation time of 19.0 (interquartile range, 12.0–26.5) months, 71 (50.4%) patients obtained favorable outcomes while 33 (23.4%) died. GCS on admission (OR, 0.109; 95% CI, 0.021–0.556; p = 0.008), recurrence of ICH (OR, 2923.687; 95% CI, 6.282–1360730.14; p = 0.011), WML grade 3–4 (OR, 31.007; 95% CI, 1.041–923.573; p = 0.047), severe central atrophy (OR, 4220.303; 95% CI, 9.135–1949674.84; p = 0.008) assessed by CT was identified as independent predictors for long‐term outcome. Interpretation Nearly 50% of CAAH patients achieved favorable outcomes at long‐term follow‐up. GCS, recurrence of ICH, WML grade and cerebral atrophy were identified as independent prognostic factors of long‐term outcome.
Collapse
Affiliation(s)
- Ruiwen Che
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Hypoxia Conditioning Translational Medicine, Beijing, China
| | - Mengke Zhang
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Hailiang Sun
- Department of Neurosurgery, Beijing Fengtai You'anmen Hospital, Beijing, China
| | - Jin Ma
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Wenbo Hu
- Department of Neurology, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Xin Liu
- Department of Radiology, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China
| | - Xunming Ji
- Beijing Key Laboratory of Hypoxia Conditioning Translational Medicine, Beijing, China.,Department of Neurosurgery, Xuan Wu Hospital, Capital Medical University, Beijing, China.,Beijing Institute of Brain Disorders, Beijing, China.,Capital Medical University, Beijing, China
| |
Collapse
|