1
|
Huang R, Liu J, Wan TK, Siriwanna D, Woo YMP, Vodencarevic A, Wong CW, Chan KHK. Stroke mortality prediction based on ensemble learning and the combination of structured and textual data. Comput Biol Med 2023; 155:106176. [PMID: 36805232 DOI: 10.1016/j.compbiomed.2022.106176] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 09/12/2022] [Accepted: 10/01/2022] [Indexed: 11/23/2022]
Abstract
For severe cerebrovascular diseases such as stroke, the prediction of short-term mortality of patients has tremendous medical significance. In this study, we combined machine learning models Random Forest classifier (RF), Adaptive Boosting (AdaBoost), Extremely Randomised Trees (ExtraTree) classifier, XGBoost classifier, TabNet, and DistilBERT to construct a multi-level prediction model that used bioassay data and radiology text reports from haemorrhagic and ischaemic stroke patients to predict six-month mortality. The performances of the prediction models were measured using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), precision, recall, and F1-score. The prediction models were built with the use of data from 19,616 haemorrhagic stroke patients and 50,178 ischaemic stroke patients. Novel six-month mortality prediction models for these patients were developed, which enhanced the performance of the prediction models by combining laboratory test data, structured data, and textual radiology report data. The achieved performances were as follows: AUROC = 0.89, AUPRC = 0.70, precision = 0.52, recall = 0.78, and F1 score = 0.63 for haemorrhagic patients, and AUROC = 0.88, AUPRC = 0.54, precision = 0.34, recall = 0.80, and F1 score = 0.48 for ischaemic patients. Such models could be used for mortality risk assessment and early identification of high-risk stroke patients. This could contribute to more efficient utilisation of healthcare resources for stroke survivors.
Collapse
Affiliation(s)
- Ruixuan Huang
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China
| | - Jundong Liu
- Department of Biomedical Sciences, City University of Hong Kong, Hong Kong, China
| | - Tsz Kin Wan
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China
| | - Damrongrat Siriwanna
- Department of Biomedical Sciences, City University of Hong Kong, Hong Kong, China
| | | | | | - Chi Wah Wong
- Department of Applied AI and Data Science, City of Hope National Medical Center, Duarte, CA, 91010, United States
| | - Kei Hang Katie Chan
- Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China; Department of Biomedical Sciences, City University of Hong Kong, Hong Kong, China; Department of Epidemiology and Center for Global Cardiometabolic Health, School of Public Health, Department of Medicine, The Warrant Alpert School of Medicine, Brown University, Providence, RI, United States.
| |
Collapse
|
2
|
Li G, Wang S, Xiong Y, Gu H, Yang K, Yang X, Wang C, Wang C, Li Z, Zhao X. Prior statin and short-term outcomes of primary intracerebral hemorrhage: From a large-scale nationwide longitudinal registry. CNS Neurosci Ther 2022; 28:1240-1248. [PMID: 35603937 PMCID: PMC9253784 DOI: 10.1111/cns.13868] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2021] [Revised: 04/28/2022] [Accepted: 04/30/2022] [Indexed: 12/16/2022] Open
Abstract
Introduction The relationship between statins and intracerebral hemorrhage outcomes is unclear. Aim We aimed to compare the in‐hospital mortality and evacuation of intracranial hematoma rates in patients with primary intracerebral hemorrhage between prior statin users and nonusers. Results The final study population included 66,263 patients. Multivariable logistics analyses showed that prior statin use was not associated with in‐hospital mortality for primary intracerebral hemorrhage (adjusted odd ratio 0.78, 95% CI 0.61–1.01), but reduced the proportion of patients undergoing evacuation of intracranial hematoma (adjusted odd ratio 0.70, 95% CI 0.61–0.82). Propensity score matching analyses yielded similar results. Conclusion Prior statin use was not associated with in‐hospital mortality but did reduce evacuation of intracranial hematoma rates.
Collapse
Affiliation(s)
- Guangshuo Li
- Vascular Neurology, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Shang Wang
- Neurocardiology Center, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Yunyun Xiong
- Vascular Neurology, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Chinese Institute of Brain Research, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Hongqiu Gu
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Kaixuan Yang
- China National Clinical Research Center for Neurological Diseases, Beijing, China
| | - Xin Yang
- China National Clinical Research Center for Neurological Diseases, Beijing, China.,National Center for Healthcare Quality Management in Neurological Diseases, Beijing, China
| | - Chunjuan Wang
- China National Clinical Research Center for Neurological Diseases, Beijing, China.,National Center for Healthcare Quality Management in Neurological Diseases, Beijing, China
| | - Chuanying Wang
- Vascular Neurology, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China
| | - Zixiao Li
- Vascular Neurology, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,Chinese Institute of Brain Research, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China.,Beijing Key Laboratory of Translational Medicine for Cerebrovascular Disease, Beijing, China.,Center for Stroke, Beijing Institute for Brain Disorders, Beijing, China
| | - Xingquan Zhao
- Vascular Neurology, Department of Neurology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China.,China National Clinical Research Center for Neurological Diseases, Beijing, China
| |
Collapse
|