Machine learning models for Parkinson’s disease detection and stage classification based on spatial-temporal gait parameters

BackgroundParkinson’s disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.Research questionThis article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.MethodsGait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.ResultsIn the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.SignificanceThe results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.     

The use of 3D surface fitting for robust polyp detection and classification in CT colonography

In this paper we describe the development of a computationally efficient computer-aided detection (CAD) algorithm based on the evaluation of the surface morphology that is employed for the detection of colonic polyps in computed tomography (CT) colonography. Initial polyp candidate voxels were detected using the surface normal intersection values. These candidate voxels were clustered using the normal direction, convexity test, region growing and Gaussian distribution. The local colonic surface was classified as polyp or fold using a feature normalized nearest neighborhood classifier. The main merit of this paper is the methodology applied to select the robust features derived from the colon surface that have a high discriminative power for polyp/fold classification. The devised polyp detection scheme entails a low computational overhead (typically takes 2.20 min per dataset) and shows 100% sensitivity for phantom polyps greater than 5 mm. It also shows 100% sensitivity for real polyps larger than 10 mm and 91.67% sensitivity for polyps between 5 to 10 mm with an average of 4.5 false positives per dataset. The experimental data indicates that the proposed CAD polyp detection scheme outperforms other techniques that identify the polyps using features that sample the colon surface curvature especially when applied to low-dose datasets.     

致癌物分子结构识别中的一种特征提取方法

本文论述基于拓扑参数的致癌物分子结构识别中的一种特征参数－－特征片段的提取方法；对一组活性已知的分子训练集，将其分子结构用ＫＬＮ编码法进行编码并输入计算机，在三个约束条件下用深度第一法对各分子进行结构分解，生成片段文件，并汇总成片段总库，然后用统计检验和聚类分析提取和优化特征片段，从而为识别模型提供合理有效的特征参数。     

An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks

In this paper, an intelligent system is presented for interpretation of the Doppler signals of the heart valve diseases based on the pattern recognition. This paper especially deals with combination of the feature extraction and classification from measured Doppler signal waveforms at the heart valve using the Doppler Ultrasound. Because of this, a wavelet packet neural network model developed by us is used. The model consists of two layers: wavelet and multi-layer perceptron. The wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of wavelet packet decomposition and wavelet packet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the developed system has been evaluated in 215 samples. The test results showed that this system was effective in detecting Doppler heart sounds. The correct classification rate was about 94% for abnormal and normal subjects.     

Synaptogenesis and myelinogenesis in dissociated cerebral cells from rat embryo on polylysine coated surfaces

Summary The appearance of myelinated axons and establishment of synaptic contacts in dissociated cells from rat embryo cerebral hemispheres grown on polylysine precoated surfaces were studied by light and electron microscopy. Typical myelin lamellae ensheathing axons were observed as early as the eighth day. Immature synaptic profiles exhibiting slight membrane thickening and few synaptic vesicles were observed after seven days. At 3 weeks, mature synapses containing many synaptic vesicles and the typical irregular membrane thickening could be seen. It is suggested that the presence of polylysine may provide a support which enhances the attachment and subsequent establishment of contacts between neuronal and glial cells, resulting in the early onset of myelin formation.     

基于自适应小波神经网络的心电图检测法

自适应小波神经网络检测法就是利用小波函数取代通常神经网络中隐层的作用函数来实现的，通过网络的学习自适应地调整尺度参数和时移因子，提高了特征提取能力，因此，该网络可提高心电信号的检测率和可靠性。     

基于经验模式分解的心电特征提取算法

本研究应用基于经验模式分解的心电特征提取方法,利用第一本征模函数(intrinsic mode function,IMF)分量对QRS波进行定位,并通过减少分解层数、筛选次数、处理区域等策略实现了快速算法。利用MIT-BIT心律失常数据库的数据进行算法测试,取得较高的检测率,检测速度也有明显提高。实验结果表明,经验模式分解算法在QRS波定位中具有相当的优越性,临床应用中取得了良好的检测效果。     

心电信号预处理与心电信号分析

本文介绍了在一种便携式心电监护仪器中是如何对心电数据进行预处理和智能分析的．为了适应便携式仪器的特征，我们在心电信号预处理中采用了FFT滤波和滑动平均滤波的方法去除各种干扰并使图像得以平滑，同时采用了差分阈值法提取特征点，考虑到监护仪器的实用性，在心电信号分析阶段，我们采用了分析特征间期异常情况的方法来替代对病症的智能诊断功能。     

引入关联维的表面肌电信号的特征提取

考虑到表面肌电信号的非平稳特性,本研究在传统特征提取的基础上,又引入了非线性动力学中的关联维,通过小波系数的标准差和关联维重新构造特征向量,将其送入自组织映射网络对拇指弯曲、食指弯曲和无名指弯曲三种手势动作进行分类识别。结果表明:引入关联维的特征提取方法其识别正确率明显优于传统的小波变换的方法。可见,关联维作为一种新的特征参数,为肌电信号的特征提取提供了新的思路。     

Inflammation markers in nasal lavage, and nasal symptoms in relation to relocation to a newly painted building: a longitudinal study

Introduction: There is a need to evaluate possible health effects of ventilation improvements and emissions from new buildings, in longitudinal studies. New methods to study biological effects on the eyes and upper airways are now available. Material and methods: A longitudinal study was performed on 83 trained social workers in two offices in Uppsala, Sweden. The exposed group (n= 57) moved to a newly redecorated building nearby. Low emitting building material had been used, including a new type of solvent-free water-based paint. The control group (n= 26) worked in the same office during the study period (November 1995 to February 1996). Hygiene management was carried out in both offices, at the beginning and the end of the investigation. Tear film stability (BUT) was measured. Nasal patency was measured by acoustic rhinometry, and eosinophilic cationic protein (ECP), myeloperoxidase (MPO), lysozyme and albumin were analyzed in nasal lavage fluid (NAL). Results: The relocation resulted in an increase in the personal outdoor airflow rate from 11 to 22 l/s. Indoor concentrations of terpenes were higher in the new building, and powdering of the new linoleum floor was observed. Measurements showed low levels of volatile organic compounds (VOC), formaldehyde, carbon dioxide (CO₂), nitrogen dioxide, respirable dust, and microorganisms in the air of all buildings. The move resulted in an increased nasal patency and an increase of ECP and lysozyme in NAL, after adjusting for changes in the control group. No changes were observed for nasal or ocular symptoms. A seasonal effect, with a decrease of ECP, was observed in the control group. Conclusion: A well-ventilated office building can be redecorated without any major ocular or nasal effects, or measurable increase of indoor air pollution if low-emitting building materials are selected. In agreement with previous evidence, the improved ventilation flow may explain the increase of nasal patency. The increase of ECP and lysozyme in NAL suggested an inflammatory effect in the new building. Since this building had increased ventilation flow, increased concentrations of terpenes, and powdering from the polish on the new linoleum floor, identification of causative agents was difficult. The hygiene measures did not give any evidence that emissions from the new type of solvent-free water-based paints or building dampness were responsible for the observed nasal effects. Considering the higher emissions of VOC reported from older types of water-based latex paints and solvent-based wall paints, the new type of solvent-free water-based paint seems to be a good choice from the hygiene point of view. Received: 21 December 1998 / Accepted: 20 June 1999