The extraction of neuroimaging features of migraine patients and the design of identification models are of great significance for the auxiliary diagnosis of related diseases. Compared with the commonly used image features, this study directly uses time-series signals to characterize the functional state of the brain in migraine patients and healthy controls, which can effectively utilize the temporal information and reduce the computational effort of classification model training. Firstly, Group Independent Component Analysis and Dictionary Learning were used to segment different brain areas for small-sample groups and then the regional average time-series signals were extracted. Next, the extracted time series were divided equally into multiple subseries to expand the model input sample. Finally, the time series were modeled using a bi-directional long-short term memory network to learn the pre-and-post temporal information within each time series to characterize the periodic brain state changes to improve the diagnostic accuracy of migraine. The results showed that the classification accuracy of migraine patients and healthy controls was 96.94%, the area under the curve was 0.98, and the computation time was relatively shorter. The experiments indicate that the method in this paper has strong applicability, and the combination of time-series feature extraction and bi-directional long-short term memory network model can be better used for the classification and diagnosis of migraine. This work provides a new idea for the lightweight diagnostic model based on small-sample neuroimaging data, and contributes to the exploration of the neural discrimination mechanism of related diseases.
【摘要】 目的 探讨3分法画钟测验（clock drawing test，CDT）对阿尔茨海默病患者（Alzheimer disease，AD）与血管性痴呆患者（vascular dementia，VD）的鉴别作用。 方法 收集四川大学华西医院神经内科门诊及住院部2009年9月-2010年6月就诊的认知功能障碍患者150例，进行病史采集及神经心理测试量表，筛选出AD患者57例及VD患者43例，共计纳入100例。在两者间进行CDT，分析两者间CDT有无差别、CDT与中文版简易智能量表（Chinese version of the mini-mental state examination，MMSE）及临床痴呆评定量表（clinical dementia rating scale，CDR）的相关性。 结果 AD患者及VD患者间CDT差异无统计学意义（Pgt;0.05）；CDT与MMSE及CDR有相关性，Spearman相关系数分别为0.573和-0.542（Plt;0.001）。 结论 3分法画钟测验无法准确区分AD和VD，但对粗略判断AD及VD程度可能有一定效果。【Abstract】 Objective To investigate the differential function of the three-point scoring system for the clock drawing test (CDT) between Alzheimer’s disease (AD) and vascular dementia (VD). Methods We analyzed the clinical data of 150 patients with cognitive impairment treated in the neurology and inpatient departments of our hospital from September 2009 to July 2010. Medical history of the subjects were collected. Through the assessment by neurological and psychological rating scale, we picked out 57 patients with AD and 43 with VD and tested them with CDT. The difference of CDT results between the two groups, and the correlation of CDT with Chinese version of the mini-mental state examination (MMSE) and clinical dementia rating scale (CDR) were analyzed. Results There was no statistical difference of CDT results between AD and VD patients (Pgt;0.005). CDT had a correlations with MMSE and CDR, the Spearman correlation coefficient being 0.573 and -0.542 respectively (Plt;0.001). Conclusion The three-point scoring system for the clock drawing test cannot differentiate exactly between Alzheimer Disease and Vascular Dementia, but it can make a gross judgment of the degree of AD and VD.
ObjectiveTo systematically review the efficacy of immunoglobulin for treatment of clinical diagnosed viral encephalitis in China.MethodsCNKI, VIP, WanFang Data, PubMed, ScienceDirect, The Cochrane Library and EMbase databases were electronically searched to collect randomized controlled trials (RCTs) of immunoglobulin for treatment of clinical diagnosed viral encephalitis in China from inception to January 2021. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Meta-analysis was then performed by using RevMan 5.4 software.ResultsA total of 57 RCTs involving 4 431 patients were included. The results of meta-analysis showed that in both children and adults of clinically diagnosed viral encephalitis, the combination of immunoglobulin could reduce the mean recovery time of fever, unconsciousness, convulsion, emesis, average hospitalization time, and non-effective rate. Moreover, there was no difference in the incidence of adverse effects between the two groups.ConclusionsCurrent evidence shows that immunoglobulin is superior to conventional therapies both in adults and children patients of clinically diagnosed viral encephalitis. Due to the limited quality and quantity of the included studies, more high-quality studies are needed to verify the above conclusions.
ObjectivesTo assess the efficacy and safety of corticosteroid and antiviral agents for idiopathic facial nerve paralysis (IFNP) by network meta-analysis.MethodsPubMed, EMbase, The Cochrane Library, CBM, CNKI, WangFang Data and VIP databases were electronically searched to collect randomized controlled trials (RCTs) of corticosteroid and antiviral agents for IFNP from inception to January 31th, 2018. Two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. The meta-analysis was performed by R 3.3.3 and Stata 13.0 software.ResultsA total of 16 RCTs involving 3 061 patients were included. The results of network meta-analysis showed that: for the facial function recovery rates, corticosteroid plus antiviral agents was superior to placebo and antiviral agents alone at 3-month follow-up. Corticosteroid plus antiviral agents was superior to placebo, antiviral agents or corticosteroid alone at 6-month follow-up (if the satisfactory recovery was defined as a House-Brackmann grade class Ⅱ or below). When the follow-up exceeded 6 months, corticosteroid alone was superior to placebo and antiviral agents alone, corticosteroid plus antiviral agents was superior to placebo and antiviral agents alone. All of the differences above were statistically significant. For the sequelae, corticosteroid plus antiviral agents and corticosteroid alone were superior to placebo and antiviral agents alone. Corticosteroid plus antiviral agents was superior to corticosteroid alone. The differences were statistically significant. For the adverse events, there were no significant differences between any other pairwise comparisons of these different interventions.ConclusionConsidering the efficacy and safety, patients with IFNP treated corticosteroid plus antiviral agents are more likely to have a better recovery of facial function and less likely to develop sequelae, followed by corticosteroid alone. More high-quality, large scaled and multicenter RCTs are required to verify the conclusions above, and focus on the treatment of children and patients with severe facial paralysis.