共查询到20条相似文献,搜索用时 62 毫秒
1.
左束支传导阻滞(LBBB)作为临床常见的一种心律失常,是左心室收缩功能减低、患者死亡率增加的标志;利用机器学习算法对其进行辅助诊断,将对LBBB早发现、早治疗起到积极的推动作用。然而,由于目前常用的支持向量机(SVM)等传统的机器学习算法容易产生局部最优解,准确度有待提高,因此提出一种基于极限学习机(ELM)的LBBB辅助诊断算法。首先,利用小波进行心电信号预处理,包括基线漂移、肌电噪声及工频干扰的去除;接着,确定QRS波群与T波位置;然后,根据临床上LBBB患者比正常人的QRS波群持续时间延长等特点,建立融合时域、形态与能量3类特征的特征模型;最后,利用该模型提取的特征集合,提出基于ELM的LBBB辅助诊断算法。此外,在MIT_BIH数据库中的5 000份ECG数据上进行实验验证,结果表明所提出的预处理与波形提取算法能有效去除噪声并提取QRS-T特征波;在LBBB的判别上,相比SVM算法、ELM算法的训练时间缩短了88.5%;同时,在准确率、灵敏度、特异度、LBBB检出率和正常人检出率的指标上,分别提升2.4%、5.4%、1.2%、3.6%和2%。因此,基于ELM的LBBB辅助诊断算法具有明显优势。 相似文献
2.
对阿尔兹海默(AD)疾病进程的建模研究,有利于在其早期阶段--轻度认知障碍(MCI)进行更准确的诊断。不仅利用多模态影像数据,还分析模态间特征关系,用于增强与AD/MCI相关的特征表达能力。首先,基于典型相关分析融合不同模态间多个感兴趣区域并生成多模态关系特征表达;其次,基于稀疏最小二乘回归损失函数,以此获得稳定且有识别力的相关性表达特征;最后,使用交叉验证方法将随机选择的训练样本用于支持向量机分类模型,再对测试集受试者进行疾病阶段诊断。实验基于Alzheimer′s Disease Neuroimaging Initiative(ADNI)公共数据库的805位受试者,包括AD,MCI和正常受试者(NC)。此方法对于AD vs NC,MCI vs NC和p-MCI(进行性轻度认知障碍)vs s-MCI(稳定性轻度认知障碍)等3种不同类型数据,诊断结果分别为92.01%,74.83%和70.27%。与其他算法相比,分类准确率都有明显提高。表明所提出的方法能够有效应用于多模态数据对阿尔兹海默病的诊断分析研究。 相似文献
3.
<正>阿尔兹海默病(Alzheimer’s disease,AD),是一种由神经系统变性引发的进行性痴呆,老年者发病率较高,亦称老年痴呆。临床表现以记忆障碍、认知功能障碍、精神症状以及人格、行为方面的异常为主。典型的三大病理特征为:神经原纤维缠结、老年斑以及神经元的广泛缺失[1]。AD的动物模型按产生原因大致分为两大类:一是自发性动物模型,即 相似文献
4.
室性早搏是常见的心律异常疾病,给人的生命带来威胁,准确的心律异常诊断对于帮助人们预防心血管疾病起到重要的作用。以MIT-BIH心律异常数据库中的数据作为分析对象,提出一种基于极限学习机算法的诊断方法,主要包括信号预处理、特征提取和分类,实现心电信号室性早搏异常的判别。采用小波变换结合形态学算法,对信号进行预处理,去除干扰,得到纯净的心电信号。通过K-means聚类算法提取QRS波群等特征参数,根据这些参数建立正常窦性心律和室性早搏的正样本和预测样本,再结合极限学习机分类器进行样本训练匹配和分类识别。选取1 260个周期信号进行实验,结果表明,该算法能准确诊断出室性早搏异常,最终阳性平均检测率达到95%,平均灵敏度达到96%。该算法相比其他算法,在识别精度相当的情况下,可极大提高算法的实时性,具有很高的研究价值,同时在移动医疗和临床医疗方面也具有一定的实用价值。 相似文献
5.
由于年龄和身体条件的限制,在老年人群中跌倒是非常普遍的现象。因此,根据老年人跌倒的运动特征,远程监测他们在各个时间段的状态,以便在其摔倒或突发状况时及时采取措施显得尤为重要。针对人体运动状态进行监测,分析人体运动学特征,提出基于极限学习机的跌倒检测算法。运用三维加速度传感器采集人体的三维加速度值,建立跌倒检测特征模型。在此基础上,建立基于极限学习机的跌倒检测分类器,完成对老年人的计算机辅助跌倒检测。实验数据共540例样本,选用了不同数量的训练集和测试集,其中440例作为训练数据,其余100例为测试数据。测试结果表明,准确率为93%,敏感度为87.5%,特异性为91.7%,具有良好的分类性能。在对分类训练的运行时间方面,基于极限学习机的跌倒检测方法与传统的机器学习方法相比具有明显优势。 相似文献
6.
阿尔茨海默病是一种神经系统退行性疾病,中医称之为“痴呆”,其发病机制复杂,普遍认为主要有β-淀粉样蛋白(Aβ)过度沉积、神经炎症反应、Tau蛋白过度磷酸化等,目前临床还没有找到有效的治疗药物。黄芩的化学成分复杂,作用广泛,研究发现其主要有效成分黄酮类化合物黄芩苷、黄芩素等可改善神经退行性疾病,具有潜在的治疗阿尔兹海默病的发展前景。本文对黄芩的化学成分及治疗阿尔兹海默病的机制作一综述。 相似文献
7.
阿尔兹海默病(Alzheimer’s disease,AD)是一种老年神经系统退行性疾病。流行病学研究显示,在过去的50年里,AD的发病率增加了4倍,是目前威胁老年健康的重要疾病。对AD的影像学研究目前主要采用对图像上特征线、面积、体积测量的方法,还没有发现对AD具有特异性的影像学指标。本文尝试采用基于统计学理论的灰度共生矩阵、游程长矩阵的纹理分析方法提取AD患者MR图像上感兴趣区的纹理特征参数,通过筛选得到的参数,对AD患者和健康对照组进行分类识别,并对采用不同分类方法得到的识别结果进行比较。研究结果显示对统计学纹理特征参数使用非线性判别分析的分类方法得到的识别率最高达到90.12%。可以预见,此项研究对AD的早期诊断具有积极作用。 相似文献
8.
目的 探讨合成磁共振成像(SynMRI)联合三维动脉自旋标记成像(3D-ASL)序列在AD中双侧海马定量值的变化,研究二者联合对阿尔兹海默病(AD)早期诊断的价值。方法 收集2022年1月-6月在郑州大学第二附属医院就诊经临床诊断为AD患者24例作为阿尔兹海默病组(AD组),同时按照年龄、性别和教育程度相匹配的条件下从健康体检者中纳入26例作为本次实验的健康对照组(HC组)。所有受试者均在3.0T GE MRI扫描仪上进行MAGiC序列和3D-ASL序列扫描,选取双测海马作为感兴趣区(ROI),并分别测量其感兴趣区的T1、T2、PD及CBF值,并且所有受试者均获得简易精神状态检查(MMSE)评分。记录AD组与HC组双侧海马值,并与MMSE评分之间进行Pearson相关分析。结果 AD组患者与HC组之间双侧海马的T1值及PD值比较,差异无统计学意义(P>0.05);AD组的T2值高于HC组,而CBF值低于HC组(P<0.05);AD患者随着MMSE评分的降低,双侧海马的T1值、T2值升高、CBF值降低(P<0.05)。结论 合成MRI联合3D-ASL对AD患者双侧海马区域具有很好的定量价值,可以对AD进行早期诊断。 相似文献
9.
阿尔兹海默病(Alzheimer''s disease,AD)是一种常见的神经退行性疾病,其病理特征包括β淀粉样蛋白(β-amyloid,Aβ)沉积、神经元死亡和认知能力下降等.近年来,越来越多的研究表明,生物钟或昼夜节律紊乱与AD的发生和发展密切相关.25-40%的AD患者同时伴有不同程度的昼夜节律紊乱症状,出现夜间睡眠片段化、白天小睡增加等症状.研究结果表明,AD与节律紊乱可通过Aβ的生成和清除,神经元的损伤和死亡,tau蛋白磷酸化导致的神经纤维缠结、免疫激活导致的炎症反应以及褪黑素和 GSK-3β等共同途径来相互作用与影响.本文综述了近年来关于昼夜节律紊乱与AD双边关系的研究进展,并总结了目前针对昼夜节律紊乱与AD的治疗方法. 相似文献
10.
目的为实现运动功能障碍患者的运动意愿,基于脑-机接口(brain-computer interface,BCI)的康复训练技术是近年来的研究热点。脑-机接口的关键技术是快速准确地识别出与运动想象相关的脑电模式。针对脑电信号非平稳及个性化差异等特点,利用小波包理论和核函数极限学习机(extreme learning machine,ELM)方法,提出一种自适应的特征分类方法来提高脑电信号的分类识别率。方法由于小波包存在着频带交错的现象,所以首先利用距离准则将自适应提取的最优小波包的平均能量作为特征向量,并采用核函数ELM方法进行分类。最后利用BCI竞赛数据进行了脑电信号特征分类的仿真研究,并对不同算法的分类识别率进行仿真分析。结果自适应特征分类方法对用于实验的脑电数据的平均分类识别率达到97.6%,对比ELM、神经网络(back propagation,BP)和支持向量机(support vector machine,SVM)分类方法,核函数ELM方法在分类时间和识别精度上效果最佳。结论本文提出的脑电信号分类方法取得了较高的分类识别率,适用于脑电信号的分类应用。 相似文献
11.
现代社会中,阿尔茨海默病已经成为严重影响和限制个人日常生活甚至危及患者生命安全的一种疾病.轻度认知障碍作为阿尔茨海默病的前一个阶段,对其精确诊断有助于干预或降低患者转化为阿尔茨海默病的几率.目前,功能磁共振成像技术已经广泛应用于轻度认知障碍的检测诊断研究中.从特征提取、特征选择、数据降维和分类识别等方面,对fMRI在M... 相似文献
12.
近年来,由于帕金森病(PD)的临床复杂性与多模态磁共振(MR)图像的高维性,如何有效挖掘图像中特异性标记PD的影像生物标志物、建立高效的PD计算机辅助诊断(CAD)模型是研究中极具挑战性的问题。综述目前国内外研究进展,进一步分析MR多模态特征提取、特征选择、分类器模型等传统机器学习方法建立CAD模型的关键技术,并简要概述基于深度学习方法在早期PD分类诊断中的应用。指出基于多模态MR图像,采用机器学习或深度学习方法构建CAD模型,能够客观、准确地识别PD患者,对提高早期PD诊断的准确性具有很大价值和应用前景。今后研究应更深入挖掘多模态MR图像中的潜在标记PD的影像生物指标,开发更高阶的CAD模型,以辅助早期PD的临床智能诊断。 相似文献
13.
Upregulation of a number of chemokines, including monocyte chemotactic protein-1 (MCP-1), is associated with Alzheimer's disease (AD) pathological changes. Emerging evidence suggests that inflammatory events precede the clinical development of AD, as cytokine disregulation has been observed also in patients with mild cognitive impairment (MCI). MCP-1 levels were evaluated in serum samples from 48 subjects with MCI, 94 AD patients and 24 age-matched controls. Significantly increased MCP-1 levels were found in MCI and mild AD, but not in severe AD patients as compared with controls. mRNA levels in peripheral blood mononuclear cells (PBMC), evaluated by quantitative RT-PCR analysis, paralleled serum MCP-1 levels. Moreover, a progressive MCP-1 decrease was observed over a 1-year follow up in a subgroup of MCI subjects converted to AD. MCP-1 upregulation is likely to be a very early event in AD pathogenesis, by far preceding the clinical onset of the disease. Nevertheless, as MCP-1 is likely to play a role in several pathologies with an inflammatory component, a possible usfulness as an early AD biomarker would be possible only in combination with other molecules. 相似文献
14.
The perceptual processing of faces was studied using event-related potentials (ERPs) in 12 elderly patients with cognitive impairment, 15 elderly adults and 16 young adults in order to explore the sensitivity of N170/VPP to the cognitive decline associated to Alzheimer's disease. Famous and unknown faces were presented in a familiarity categorization task. Eight patients and 11 elderly adults repeated this task to obtain longitudinal data. Topographical effects were analyzed using PCA. The posterior N170 showed reduced amplitude in patients with cognitive impairment and elderly adults, compared to young adults, which could indicate perceptual impairment in configural face-encoding processing. The anterior VPP showed enhanced amplitude in patients with cognitive impairment, compared to young and elderly adults, which might relate to the prefrontal dysfunction associated to mild dementia. These preliminary findings suggest that N170/VPP could be modulated by the decline related to pathological cognitive aging. 相似文献
15.
Structural brain changes have been described in both mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, less is known about whether structural changes are detectable earlier, in the asymptomatic phase. Using voxel-based morphometry (VBM) and shape analyses of magnetic resonance imaging (MRI) data, we investigated structural brain differences between groups of healthy subjects, stratified by subsequent diagnoses of MCI or AD during a 10-year follow-up. Images taken at baseline, at least 4 years before any cognitive symptoms, showed that subjects with future cognitive impairment (preclinical AD and MCI) had reduced brain volume in medial temporal lobes, posterior cingulate/precuneus, and orbitofrontal cortex, compared with matched subjects who remained cognitively healthy for 10 years (HC). For only those subjects later diagnosed as AD, significantly greater atrophy at baseline was detected in the right medial temporal lobe, which was also confirmed by shape analysis of the right hippocampus in these subjects. Our results demonstrate that structural brain changes occur years before clinical cognitive decline in AD and are localized to regions affected by AD neuropathology. 相似文献
16.
Intelligent computer-aided diagnosis (CAD) systems can enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. CAD systems could provide physicians with a suggestion about the diagnostic of heart diseases. The objective of this paper is to review the recent published preprocessing, feature extraction and classification techniques and their state of the art of phonocardiogram (PCG) signal analysis. Published literature reviewed in this paper shows the potential of machine learning techniques as a design tool in PCG CAD systems and reveals that the CAD systems for PCG signal analysis are still an open problem. Related studies are compared to their datasets, feature extraction techniques and the classifiers they used. Current achievements and limitations in developing CAD systems for PCG signal analysis using machine learning techniques are presented and discussed. In the light of this review, a number of future research directions for PCG signal analysis are provided. 相似文献
17.
目的:考查轻度认知损害(MCI)患者的神经心理损害模式和寻找MCI和AD痴呆早期诊断的神经心理学指标。方法:以139名社区正常老人、86名符合Petersen MCI诊断标准的社区样本和35名符合DSM-ⅣAD痴呆(DAT)标准的社区和门诊患者为研究对象,用18项神经心理测验分别评估被试的内隐记忆、再认记忆、日常记忆、自由回忆、工作记忆、学习能力、推理能力、空间/计算和加工速度。结果:MCI组的神经心理测验成绩低于正常对照组、高于DAT组(P<0.001),尤其是自由回忆、工作记忆、学习能力和加工速度的组间差异更大;神经心理学指标能甄别正常与MCI或MCI与DAT,归类正确率在90.9%~93.8%之间;神经心理指标在MCI和DAT诊断中具有较高的敏感性和特异性,尤其是自由回忆、工作记忆、学习能力和加工速度,对MCI的敏感性分别为0.763、0.806、0.748和0.727,对DAT的敏感性分别为0.930、0.884、0.965和0.919,对MCI的特异性分别为0.779、0.733、0.837和0.826,对DAT的特异性分别为0.743、0.686、0.686和0.829。结论:自由回忆、工作记忆、学习能力和加工速度是MCI和AD早期可靠的神经心理学诊断指标。 相似文献
18.
早老素蛋白(presenilin.PS)的基因多态性与阿尔茨海默病(Alzheimer's disease,AD)发病关系密切。P5是具有多个跨膜区的膜蛋白,在神经细胞中表达最广泛,主要定位在内质网(endoplasmic reticulum,ER)。PS与Notch蛋白、sel-12及δ-catenin蛋白都有相关性,因此可能在一定程度上参与lin-12/Nocth、Wingless/Wnt信号传导途径。另外,P5可使Aβ42分泌增多,PS-2使神经细胞对凋亡刺激物敏感性增强,同此在AD的发生中起到重要作用。 相似文献
19.
Accumulating evidence suggests that a disruption of zinc (Zn) homeostasis may play a role in the pathogenesis of Alzheimer's disease. Although several Zn transporter proteins responsible for the regulation of Zn balance are present in the brain, there has been little study of these proteins in Alzheimer's disease. To determine if alterations of Zn transporter proteins exist, levels of Zn transporter-4, which functions to remove Zn from the cytoplasm to endosomal/lysosomal compartments, and Zn transporter-6, which allocates cytoplasmic Zn to the trans-Golgi network, were measured in the hippocampus/parahippocampal gyrus, superior and middle temporal gyrus, and cerebellum of subjects with mild cognitive impairment, early Alzheimer's disease, late stage Alzheimer's disease, and age-matched controls using Western blot analysis and protein specific antibodies. Our results show that Zn transporter-4 and Zn transporter-6 are significantly (P<0.05) increased in hippocampus/parahippocampal gyrus of early Alzheimer's disease and Alzheimer's disease subjects. Zn transporter-6 is also increased (P<0.1) in the superior and middle temporal gyrus of Alzheimer's disease brain. 相似文献
20.
Study ObjectivesSleep abnormalities emerge early in dementia and may accelerate cognitive decline. Their accurate characterization may facilitate earlier clinical identification of dementia and allow for assessment of sleep intervention efficacy. This scoping review determines how sleep is currently measured and reported in Mild Cognitive Impairment (MCI) and early dementia, as a basis for future core outcome alignment. MethodsThis review follows the PRISMA Guidelines for Scoping Reviews. CINAHL, Embase, Medline, Psychinfo, and British Nursing Index databases were searched from inception—March 12, 2021. Included studies had participants diagnosed with MCI and early dementia and reported on sleep as a key objective/ outcome measure. ResultsNineteen thousand five hundred and ninety-six titles were returned following duplicate removal with 188 studies [ N] included in final analysis. Sleep data was reported on 17 139 unique, diagnostically diverse participants ( n). “Unspecified MCI” was the most common diagnosis amongst patients with MCI ( n = 5003, 60.6%). Despite technological advances, sleep was measured most commonly by validated questionnaires ( n = 12 586, N = 131). Fewer participants underwent polysomnography (PSG) ( n = 3492, N = 88) and actigraphy ( n = 3359, N = 38) with little adoption of non-PSG electroencephalograms (EEG) ( n = 74, N = 3). Sleep outcome parameters were reported heterogeneously. 62/165 (37.6%) were described only once in the literature (33/60 (60%) in interventional studies). There was underrepresentation of circadian ( n = 725, N = 25) and micro-architectural ( n = 360, N = 12) sleep parameters. ConclusionsAlongside under-researched areas, there is a need for more detailed diagnostic characterization. Due to outcome heterogeneity, we advocate for international consensus on core sleep outcome parameters to support causal inference and comparison of therapeutic sleep interventions. 相似文献
|