Objective To evaluate the predictive effect of three machine learning methods, namely support vector machine (SVM), K-nearest neighbor (KNN) and decision tree, on the daily number of new patients with ischemic stroke in Chengdu. Methods The numbers of daily new ischemic stroke patients from January 1st, 2019 to March 28th, 2021 were extracted from the Third People’s Hospital of Chengdu. The weather and meteorological data and air quality data of Chengdu came from China Weather Network in the same period. Correlation analyses, multinominal logistic regression, and principal component analysis were used to explore the influencing factors for the level of daily number of new ischemic stroke patients in this hospital. Then, using R 4.1.2 software, the data were randomly divided in a ratio of 7∶3 (70% into train set and 30% into validation set), and were respectively used to train and certify the three machine learning methods, SVM, KNN and decision tree, and logistic regression model was used as the benchmark model. F1 score, the area under the receiver operating characteristic curve (AUC) and accuracy of each model were calculated. The data dividing, training and validation were repeated for three times, and the average F1 scores, AUCs and accuracies of the three times were used to compare the prediction effects of the four models. Results According to the accuracies from high to low, the prediction effects of the four models were ranked as SVM (88.9%), logistic regression model (87.5%), decision tree (85.9%), and KNN (85.1%); according to the F1 scores, the models were ranked as SVM (66.9%), KNN (62.7%), decision tree (59.1%), and logistic regression model (57.7%); according to the AUCs, the order from high to low was SVM (88.5%), logistic regression model (87.7%), KNN (84.7%), and decision tree (71.5%). Conclusion The prediction result of SVM is better than the traditional logistic regression model and the other two machine learning models.
This paper describes a simulation of microwave brain imaging for the detection of hemorrhagic stroke. Firstly, in the research process, the formula of DebyeⅡwas used to study tissues of brain and blood clot so that microwave frequency band was confirmed for imaging. Then a model with electromagnetic characteristics of brain was built on this basis. In addition, an ultra-wideband (UWB) Vivaldi antenna is designed to use for transmitting and receiving microwave signals of widths 1.7 GHz to 4 GHz. Microwave signals were transmitted and received when the antenna revolved around the brain model. Symmetric position de-noising method was used to eliminate the strong background noise signals, and finally confocal imaging method was applied to get brain imaging. Blood clot was distinguished clearly from result of imaging and position error was less than 1 cm.
Cryptogenic stroke (CS) accounts for 25% of ischemic stroke. The etiology of undetermined stroke is unclear leading to untargeted secondary prevention, high recurrence rate, so the clinical burden of cryptogenic stroke is substantial. Cardiac magnetic resonance (CMR) imaging can identify more occult cardiac embolism that cannot be identified by standard cardiac assessment based on its excellent spatial resolution and contrast, three-dimensional imaging capacity and ability to depict soft tissues, to accelerate the initiation of optimal secondary prevention and improve the prognosis of patients. This review summarizes the application of CMR in the field of CS in recent years. Based on the latest evidence of diagnosis and management strategies, this paper proposes a cardiac diagnostic examination plan for CS patients, thereby improving the secondary prevention strategy of CS patients and improving their quality of life.
ObjectiveTo review the recent research progress of different types of stem cells in the treatment of ischemic stroke.MethodsBy searching the PubMed database, a systematic review had been carried out for the results of applying different types of stem cells in the treatment of ischemic stroke between 2000 and 2020.ResultsStem cells can be transplanted via intracranial, intravascular, cerebrospinal fluid, and intranasal route in the treatment of ischemic stroke. Paracrine and cell replacement are the two major mechanisms of the therapy. The researches have mainly focused on utilization of neural stem cells, embryonic stem cells, and mesenchymal stem cells. Each has its own advantages and disadvantages in terms of capability of migration, survival rate, and safety. Certain stem cell therapies have completed phase one clinical trial.ConclusionStem cells transplantation is feasible and has a great potential for the treatment of ischemic stroke, albeit that certain obstacles, including the selection of stem cells, transplantation strategy, migration ability, survival rate, still wait to be solved.
Objective To explore the impact of early blood pressure reduction on the prognosis of acute ischemic stroke. Methods We searched PubMed, Embase, Cochrane Library, Wanfang, China National Knowledge Infrastructure, and Chongqing VIP, with the search period from databases establishment to December 31, 2024. Randomized controlled studies on early blood pressure reduction within 7 days after the onset of acute ischemic stroke were included, and meta-analysis was conducted using RevMan 5.4 software. Results Finally, 15 randomized controlled studies were included. The meta-analysis results showed that there was no statistically significant difference in the primary outcome (90 days disability or death) and the secondary outcomes (90 days all-cause death) between the early blood pressure reduction group and the control group (P>0.05). Compared with the control group, the early blood pressure reduction group had a higher National Institute of Health Stroke Scale score at 2 weeks [standardized mean difference=0.25, 95% confidence interval (0.07, 0.44), P=0.008]. Conclusion Early blood pressure reduction cannot reduce the risk of 90 days disability or death and 90 days all-cause death in patients with acute ischemic stroke, and may be detrimental to 2 weeks neurological function recovery.
To evaluate the effectiveness and safety of anticoagulants in ischaemic stroke primary or secondary prevention and treatment, we searched The Cochrane Library and MEDLINE to find high quality evidence and summarized the available evidence. The results showed that routine immediate anticoagulant therapy in patients with acute ischaemic stroke should not be recommended because it increased the risk of hemorrhage with ineffective reduction to the risk of death or disability. For the high risk group with cardiogenic embolism, anticoagulant therapy could safely and effectively reduce the incidence of stroke or other vascular events. However, for non-cardiogenic embolism group, anticoagulant therapy was hard to balance the benefits and harms.
Homocysteine is an intermediate product of methionine and cysteine metabolism, and plays a key role in methylation. Epilepsy is one of the common diseases of the nervous system, long-term repeated seizures will not only cause damage to the brain tissue, but also cause cognitive impairment. At present, the clinical treatment for epilepsy is still mainly to control symptoms, the fundamental etiology of epilepsy still needs to be improved, to explore the etiology of seizures, fundamentally control seizures, is still our long-term struggle direction. High homocysteine is associated with many diseases. Epidemiological studies have shown that the serum homocysteine level of 10% ~ 40% of epilepsy patients is higher than that of the normal population. By exploring the relationship between serum Hcy and epilepsy,We expect to provide help for the diagnosis and treatment of clinical epilepsy.
ObjectiveTo systematically review the effectiveness and safety of Wuling capsule for patients with depression after stroke.
MethodsThe randomized controlled trials (RCTs) about Wuling capsule for treating the patients with post-stroke depression was searched in PubMed, The Cochrane Library (Issue 4, 2013), EMbase, CBM, CNKI, WanFang Data and VIP from the dates of their establishment to November 2013. Literature screening according to the inclusion and exclusion criteria, data extraction and methodological quality assessment of the included studies were completed by two reviewers independently. Meta-analysis was conducted using RevMan 5.2 software.
ResultsA total of eighteen RCTs involving 1 683 patients were finally enrolled. The results of meta-analysis indicated that:a) the Wuling capsule group was more effective in decreasing depression scores than the control group at 4, 8, 12 weeks (4 weeks:SMD=-0.87, 95%CI-1.25 to-0.5, P < 0.000 1; 8 weeks:SMD=-1.22, 95%CI-1.86 to-0.59, P=0.000 2; 12 weeks:SMD=-0.62, 95%CI-1.09 to-0.15, P=0.01). b) The effectiveness rate (92.7%) of the Wuling capsule group was significantly higher than that of the control group (77.2%) at the end of follow-up, with a significant difference (RR=1.20, 95%CI 1.14 to 1.27, P < 0.000 01). c) The two groups were alike in the incidence of palpitation.
ConclusionCurrent evidence suggests that, Wuling capsule improves the symptoms of stroke-stroke depression with less adverse reaction. However, due to the limited quantity and quality of the included studies, more multicenter high quality RCTs with large sample size are needed to verify the above conclusion.
Objective To investigate the relationship between Oxfordshire community stroke project (OCSP) classification and MRI classification in acute cerebral infarction. Methods A total of 282 patients with acute cerebral infarction were retrospectively evaluated with OCSP classification and imaging characteristics. Results According to OCSP classification, of all 282 patients with acute cerebral infarction, 32 (11.3%) experienced total anterior circulation infarction (TACI), 86 (30.5%) partial anterior circulation infarction (PACI), 111 (39.4%) lacunar infarction (LACI), and 53 (18.8%) posterior circulation infarction (POCI). The consistency was found in 201 cases (71.3%) between the OCSP classification and imaging classification, with the accuracy of 77% (27/35) for TACI, 79% (42/53) for PACI, 69% (95/137) for LACI and 65% (37/57) for POCI. Conclusion OCSP classification can predict the location and size of cerebral infarction with a high accuracy, and is well consistent with the MRI findings.
Objective To systematically review the relationship between helicobacter pyloric (HP) infection and ischemia stroke. Methods We searched MEDLINE, BIOSIS, VIP, and China Full Text Journal databases to identify the studies that studied the relationship between HP infection and ischemia stroke. All the studies were strictly screened according to the inclusion criteria, and meta-analyses were performed for the included studies using RevMan 4.2 software.Results Eleven case-control studies involving 1 530 patients with ischemia stroke and 1 451 health controls were included. The results of meta-analyses showed that there was a significant difference in the infection ratio of HP between the patients with ischemia stroke and health controls (OR=1.77, 95%CI 1.38 to 2.28, Plt;0.0001), but this difference was not been found after adjusting some related risk factors (1.22, 95%CI 0.93 to 1.59, P=0.15). The results of subgroup meta-analyses showed these differences were only found in the LAA (large-artery atherosclerosis) subgroup (OR=3.65, 95%CI 2.58 to 5.17) and the SAA (small-artery atherosclerosis) subgroup (OR=1.74, 95%CI 1.30 to 2.34), but was not found in the CE (cardiogenic cerebral embolism) subgroup (OR=1.08, 95%CI 0.58 to 2.02). Conclusion HP infection is associated with ischemia stroke, but the relationships between HP infection and the subtypes of ischemia stroke are different. The association between HP and LAA is ber than that between HP and the other subtypes. More evidence is needed to prove whether Helicobacter pyloric infection is an independent risk factor of ischemia stroke.
