1
|
Lin X, Lin S, Cui X, Zou D, Jiang F, Zhou J, Chen N, Zhao Z, Zhang J, Zou J. Prediction-Driven Decision Support for Patients With Mild Stroke: A Model Based on Machine Learning Algorithms. Front Neurol 2022; 12:761092. [PMID: 35002923 PMCID: PMC8733999 DOI: 10.3389/fneur.2021.761092] [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: 08/19/2021] [Accepted: 11/22/2021] [Indexed: 11/30/2022] Open
Abstract
Background and Purpose: Treatment for mild stroke remains an open question. We aim to develop a decision support tool based on machine learning (ML) algorithms, called DAMS (Disability After Mild Stroke), to identify mild stroke patients who would be at high risk of post-stroke disability (PSD) if they only received medical therapy and, more importantly, to aid neurologists in making individual clinical decisions in emergency contexts. Methods: Ischemic stroke patients were prospectively recorded in the National Advanced Stroke Center of Nanjing First Hospital (China) between July 2016 and September 2020. The exclusion criteria were patients who received thrombolytic therapy, age <18 years, lack of 3-month modified Rankin Scale (mRS), disabled before the index stroke, with an admission National Institute of Health stroke scale (NIHSS) > 5. The primary outcome was PSD, corresponding to 3-month mRS ≥ 2. We developed five ML models and assessed the area under curve (AUC) of receiver operating characteristic, calibration curve, and decision curve analysis. The optimal ML model was selected to be DAMS. In addition, SHapley Additive exPlanations (SHAP) approach was introduced to rank the feature importance. Finally, rapid-DAMS (R-DAMS) was constructed for a more urgent situation based on DAMS. Results: A total of 1,905 mild stroke patients were enrolled in this study, and patients with PSD accounted for 23.4% (447). There was no difference in AUCs between the five models (ranged from 0.691 to 0.823). Although there was similar discriminative performance between ML models, the support vector machine model exhibited higher net benefit and better calibration (Brier score, 0.159, calibration slope, 0.935, calibration intercept, 0.035). Therefore, this model was selected for DAMS. In addition, SHAP approach showed that the most crucial feature was NIHSS on admission. Finally, R-DAMS was constructed and there was similar discriminative performance between R-DAMS and DAMS, but the former performed worse on calibration. Conclusions: DAMS and R-DAMS, as prediction-driven decision support tools, were designed to aid clinical decision-making for mild stroke patients in emergency contexts. In addition, even within a narrow range of baseline scores, NIHSS on admission is the strongest feature that contributed to the prediction.
Collapse
Affiliation(s)
- Xinping Lin
- School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China.,Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Shiteng Lin
- School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China.,Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - XiaoLi Cui
- Department of Neurology, Nanjing Yuhua Hospital, Yuhua Branch of Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Daizun Zou
- School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China.,Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - FuPing Jiang
- Department of Geriatrics, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - JunShan Zhou
- Department of Neurology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - NiHong Chen
- Department of Neurology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Zhihong Zhao
- Department of Neurology, The First Affiliated Hospital (People's Hospital of Hunan Province), Hunan Normal University, Changsha, China
| | - Juan Zhang
- Department of Neurology, Nanjing Yuhua Hospital, Yuhua Branch of Nanjing First Hospital, Nanjing Medical University, Nanjing, China
| | - Jianjun Zou
- Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China.,Department of Clinical Pharmacology, Nanjing First Hospital, China Pharmaceutical University, Nanjing, China
| |
Collapse
|
2
|
Wang L, Ren C, Li Y, Gao C, Li N, Li H, Wu D, He X, Xia C, Ji X. Remote ischemic conditioning enhances oxygen supply to ischemic brain tissue in a mouse model of stroke: Role of elevated 2,3-biphosphoglycerate in erythrocytes. J Cereb Blood Flow Metab 2021; 41:1277-1290. [PMID: 32933360 PMCID: PMC8142126 DOI: 10.1177/0271678x20952264] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
Oxygen supply for ischemic brain tissue during stroke is critical to neuroprotection. Remote ischemic conditioning (RIC) treatment is effective for stroke. However, it is not known whether RIC can improve brain tissue oxygen supply. In current study, we employed a mouse model of stroke created by middle cerebral artery occlusion (MCAO) to investigate the effect of RIC on oxygen supply to the ischemic brain tissue using a hypoxyprobe system. Erythrocyte oxygen-carrying capacity and tissue oxygen exchange were assessed by measuring oxygenated hemoglobin and oxygen dissociation curve. We found that RIC significantly mitigated hypoxic signals and decreased neural cell death, thereby preserving neurological functions. The tissue oxygen exchange was markedly enhanced, along with the elevated hemoglobin P50 and right-shifted oxygen dissociation curve. Intriguingly, RIC markedly elevated 2,3-biphosphoglycerate (2,3-BPG) levels in erythrocyte, and the erythrocyte 2,3-BPG levels were highly negatively correlated with the hypoxia in the ischemic brain tissue. Further, adoptive transfusion of 2,3-BPG-rich erythrocytes prepared from RIC-treated mice significantly enhanced the oxygen supply to the ischemic tissue in MCAO mouse model. Collectively, RIC protects against ischemic stroke through improving oxygen supply to the ischemic brain tissue where the enhanced tissue oxygen delivery and exchange by RIC-induced 2,3-BPG-rich erythrocytes may play a role.
Collapse
Affiliation(s)
- Lin Wang
- Department of Hematology, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Changhong Ren
- Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Municipal Geriatric Medical Research Center, Beijing, China
| | - Yang Li
- Department of Hematology, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Chen Gao
- Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Ning Li
- Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Haiyan Li
- Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Di Wu
- Deparment of Neurology, China-America Institute of Neuroscience, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Xiaoduo He
- Deparment of Neurology, China-America Institute of Neuroscience, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Changqing Xia
- Department of Hematology, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Xunming Ji
- Beijing Key Laboratory of Hypoxia Translational Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China.,Beijing Municipal Geriatric Medical Research Center, Beijing, China.,Deparment of Neurology, China-America Institute of Neuroscience, Xuanwu Hospital, Capital Medical University, Beijing, China.,Center of Stroke, Beijing Institute for Brain Disorder, Beijing, China
| |
Collapse
|
3
|
Han Y, Li G, Tang Y, Zhang B, Zhan Y, Zhang C, Zuo L, Wu W. Effect of rt-PA intravenous thrombolysis on the prognosis of patients with minor ischemic stroke. Neurol Res 2021; 43:653-658. [PMID: 33847231 DOI: 10.1080/01616412.2021.1908672] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
Abstract
AIMS The evidence of rt-PA intravenous thrombolysis in patients with minor ischemic stroke (MIS) is still controversial. This study aims to investigate the effect of rt-PA intravenous thrombolysis on the prognosis of patients with MIS. METHODS We continuously enrolled and analyzed patients with MIS admitted into our hospital within 24 h after symptom onset between January 2016 and December 2018, including 96 patients received intravenous thrombolysis within 4.5 h after symptom onset and 84 patients not received intravenous thrombolysis. A favorable long-term outcome was a 90-day mRS score of 0-1. Good short-term outcome was a 7-day NIHSS score of 0 or less than NIHSS onset. RESULTS There were no statistical differences between two groups of patients' age, gender, history of hypertension, coronary heart disease, atrial fibrillation, smoking, drinking, and baseline NIHSS score. Patients with history of stroke (22.62% vs. 10.42%, p < 0.05) and diabetes (46.43% vs. 22.92%, p = 0.01) were higher in group of non-thrombolysis. The difference of NIHSS score after 7 days was statistically different between the two groups (p < 0.05), while there was no significant difference in 90-day mRS score. Logistic regression analysis indicated that the prognosis of patients was correlated with neutrophil ratio and CRP at admission. CONCLUSION Patients with MIS received intravenous thrombolysis may be associated with earlier neurological improvement, but might has no significant effect on long-term prognosis. The level of neutrophil ratio and CRP at admission are risk factors determining the prognosis, which requires further research.
Collapse
Affiliation(s)
- Yingying Han
- Department of Neurology, East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Gang Li
- Department of Neurology, East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Yueyu Tang
- Department of Neurology, East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Bei Zhang
- Department of Neurology, East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Yiqiang Zhan
- Department of Neurology, Yang-Si Hospital, Shanghai, China
| | - Chunfang Zhang
- Department of Shanghai Pudong Medical Emergency Center, Shanghai, China
| | - Lian Zuo
- Department of Neurology, East Hospital, Tongji University School of Medicine, Shanghai, China
| | - Wei Wu
- Department of Neurology, Qi-Lu Hospital of Shandong University and Brain Science Research Institute, Shandong University, Shandong, China
| |
Collapse
|
4
|
Tsivgoulis G, Kargiotis O, De Marchis G, Kohrmann M, Sandset EC, Karapanayiotides T, de Sousa DA, Sarraj A, Safouris A, Psychogios K, Vadikolias K, Leys D, Schellinger PD, Alexandrov AV. Off-label use of intravenous thrombolysis for acute ischemic stroke: a critical appraisal of randomized and real-world evidence. Ther Adv Neurol Disord 2021; 14:1756286421997368. [PMID: 33737956 PMCID: PMC7934037 DOI: 10.1177/1756286421997368] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2021] [Accepted: 01/25/2021] [Indexed: 12/12/2022] Open
Abstract
Intravenous thrombolysis (IVT) represents the only systemic reperfusion therapy able to reverse neurological deficit in patients with acute ischemic stroke (AIS). Despite its effectiveness in patients with or without large vessel occlusion, it can be offered only to a minority of them, because of the short therapeutic window and additional contraindications derived from stringent but arbitrary inclusion and exclusion criteria used in landmark randomized controlled clinical trials. Many absolute or relative contraindications lead to disparities between the official drug label and guidelines or expert recommendations. Based on recent advances in neuroimaging and evidence from cohort studies, off-label use of IVT is increasingly incorporated into the daily practice of many stroke centers. They relate to extension of therapeutic time windows, and expansion of indications in co-existing conditions originally listed in exclusion criteria, such as use of alternative thrombolytic agents, pre-treatment with antiplatelets, anticoagulants or low molecular weight heparins. In this narrative review, we summarize recent randomized and real-world data on the safety and efficacy of off-label use of IVT for AIS. We also make some practical recommendations to stroke physicians regarding the off-label use of thrombolytic agents in complex and uncommon presentations of AIS or other conditions mimicking acute cerebral ischemia. Finally, we provide guidance on the risks and benefits of IVT in numerous AIS subgroups, where equipoise exists and guidelines and treatment practices vary.
Collapse
Affiliation(s)
- Georgios Tsivgoulis
- Second Department of Neurology, National & Kapodistrian University of Athens, School of Medicine, Iras 39, Gerakas Attikis, Athens 15344, Greece
- Department of Neurology, The University of Tennessee Health Science Center, Memphis, TN, USA
| | | | - Gianmarco De Marchis
- Neurology and Stroke Center, Department of Clinical Research, University Hospital of Basel, University of Basel, Basel, Switzerland
| | - Martin Kohrmann
- Department of Neurology, Universitätsklinikum Essen, Essen, Germany
| | | | - Theodore Karapanayiotides
- Department of Neurology, School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece
| | - Diana Aguiar de Sousa
- Department of Neurosciences (Neurology), Hospital de Santa Maria, University of Lisbon, Lisbon, Portugal
| | - Amrou Sarraj
- Department of Neurology, The University of Texas at Houston, Houston, TX, USA
| | - Apostolos Safouris
- Second Department of Neurology, National & Kapodistiran University of Athens, School of Medicine, “Attikon” University Hospital, Athens, Greece
- Stroke Unit, Metropolitan Hospital, Piraeus, Greece
| | | | - Konstantinos Vadikolias
- Department of Neurology, University Hospital of Alexandroupolis, Democritus University of Thrace, School of Medicine, Alexandroupolis, Greece
| | - Didier Leys
- Department of Neurology (Stroke Unit), Lille Neuroscience and Cognition, Degenerative and Vascular Cognitive Disorders, University of Lille, INSERM (U-1172), Lille, France
| | - Peter D. Schellinger
- Department of Neurology, Johannes Wesling Medical Center Minden, UK RUB Minden, Germany
| | - Andrei V. Alexandrov
- Department of Neurology, The University of Tennessee Health Science Center, Memphis, TN, USA
| |
Collapse
|
5
|
|