Gait analysis to quantitatively classify Ataxia and Parkinson’s disease patients: a pilot study using tree-based Machine Learning algorithms

Olfactory proteotyping: towards the enlightenment of the neurodegeneration

ABSTRACTBackground: Principal component analysis (PCA) was applied to the ground reaction force (GRF) for evaluating the deep brain stimulation of the subthalamic nucleus (DBS-STN) effects in Parkinson's disease (PD) subjects with and without medication. Methods: Ten subjects who underwent DBS-STN were evaluated under the following four conditions: without treatment (mof-sof), with stimulation (mof-son), with medication (mon-sof), and with both treatments (mon-son). A control group of 30 subjects was also evaluated. PCA was applied separately on each GRF component. Broken stick criterion selected eight principal components (PC) from vertical GRF and one from each horizontal GRF. A standard distance was calculated using these 10 PCs and the gait speed to measure how far the PD group's gait was from the normal pattern. Results: The standard distance allowed classifying normal and PD subjects in the mof-sof condition with 100% accuracy, sensitivity, and specificity. The same distance was calculated for mon-sof, mof-son, and mon-son conditions. The smallest mean standard distance was found in the mon-son condition, which was significantly different from mof-sof (Friedman test with Dunn post-hoc, p < .05). Conclusion: PCA allowed the quantitative evaluation of treatment effects, indicating that DBS-STN improves the GRF pattern in PD subjects, primarily in the medication on state.

Role of risk factors and their variable types in predicting noise-induced hearing loss using artificial intelligence algorithms.

The significance of the loss of presynaptic inhibition for step initiation in parkinsonian individuals with freezing of gait.

Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms

P03-09 - Differences in facial expression recognition between patients suffering from Parkinson's disease and healthy subjects

Malware detection engines are required a high True Positive Rate (TPR) and low False Positive rate (FPR). For example, to obtain the VB100 certification conducted by Virus Bulletin in the U.K., the detector's TPR must be 99.5% or higher, and FPR less than 0.01%. However, it is difficult for signature-based malware detection engines to detect zero-day or new variants of malware. For such malware, an approach based on machine learning is considered effective because the features of specimens are analyzed in a complex manner. Therefore, we created a malware detection model from surface analysis logs, and PE header dumps by machine learning using the FFRI Dataset 2018. Furthermore, we verified the accuracy under the constraint that the FPR is less than a certain value. As a result, we succeeded in creating a new model with high accuracy: when FPR is set to be less than 1%, TPR is 99.7%, when FPR is set to be less than 0.1%, TPR is 98.7%, and when FPR is set to be less than 0.01% and TPR is 94.5%. In addition, we revealed features with high contribution to malware detection in this model.

Studies on the variability of motor output in Parkinson's disease have found contrasting results depending on the speed-accuracy constraints of the task. The first goal of this study was to determine if Parkinson's disease subjects are more variable than control subjects. The second goal of the study was to examine the limitations on visual and motor processing that contribute to the changes in force variability in Parkinson's disease. Eight mild to moderate Parkinson's disease (age: 68-80 years) and eight matched control (age: 68-80 years) subjects maintained a constant level of force at 25% of their maximum voluntary contraction with their index finger and thumb (grip precision task) for 20 s while online visual feedback of the total force was viewed on a computer monitor. During the force task, subjects received visual feedback at varying frequencies. The sampled visual feedback levels were presented at intervals as slow as every 5 s to as fast as every 0.04 s (0.2, 0.4, 0.8, 1.6, 3.2, 6.4, 12.8, 25.6 Hz). Force variability decreased over sampled visual feedback according to hyperbolic decay functions. The minimal visual processing time for both the Parkinson's disease and control subjects was approximately 160 ms. Motor output corrections were generated in both groups at a frequency of 1 Hz over a wide range of sampled visual feedback levels. However, the amplitude of the 1-2 Hz visuo-motor corrective process was amplified in Parkinson's disease, and this related to increases in force-output variability. The findings suggest that the basal ganglia are important for adjusting the amplitude of motor output at 1-2 Hz during visuo-motor feedback control.

Neglected tropical diseases (NTDs) primarily affect the poorest populations, often living in remote, rural areas, urban slums or conflict zones. Arboviruses are a significant NTD category spread by mosquitoes. Dengue, Chikungunya, and Zika are three arboviruses that affect a large proportion of the population in Latin and South America. The clinical diagnosis of these arboviral diseases is a difficult task due to the concurrent circulation of several arboviruses which present similar symptoms, inaccurate serologic tests resulting from cross-reaction and co-infection with other arboviruses. The goal of this paper is to present evidence on the state of the art of studies investigating the automatic classification of arboviral diseases to support clinical diagnosis based on Machine Learning (ML) and Deep Learning (DL) models. We carried out a Systematic Literature Review (SLR) in which Google Scholar was searched to identify key papers on the topic. From an initial 963 records (956 from string-based search and seven from a single backward snowballing procedure), only 15 relevant papers were identified. Results show that current research is focused on the binary classification of Dengue, primarily using tree-based ML algorithms. Only one paper was identified using DL. Five papers presented solutions for multi-class problems, covering Dengue (and its variants) and Chikungunya. No papers were identified that investigated models to differentiate between Dengue, Chikungunya, and Zika. The use of an efficient clinical decision support system for arboviral diseases can improve the quality of the entire clinical process, thus increasing the accuracy of the diagnosis and the associated treatment. It should help physicians in their decision-making process and, consequently, improve the use of resources and the patient's quality of life.

Reduced arm swing amplitude, symmetry, and coordination during gait have been reported in Parkinson's disease (PD), but the relationship between dopaminergic depletion and these upper limb gait changes remains unclear. We aimed to investigate the effects of dopaminergic drugs on arm swing velocity, symmetry, and coordination in PD. Forearm angular velocity was recorded in 16 PD and 17 control subjects (Controls) during free walking trials. Angular velocity amplitude of each arm, arm swing asymmetry, and maximum cross-correlation were compared between control and PD groups, and between OFF- and ON-medication states among PD subjects. Compared to Controls, PD subjects in the OFF-medication state exhibited lower angular velocity amplitude of the slower- (p = 0.0018), but not faster- (p = 0.2801) swinging arm. In addition, PD subjects demonstrated increased arm swing asymmetry (p = 0.0046) and lower maximum cross-correlation (p = 0.0026). Following dopaminergic treatment, angular velocity amplitude increased in the slower- (p = 0.0182), but not faster- (p = 0.2312) swinging arm among PD subjects. Furthermore, arm swing asymmetry decreased (p = 0.0386), whereas maximum cross-correlation showed no change (p = 0.7436). Pre-drug angular velocity amplitude of the slower-swinging arm was correlated inversely with the change in arm swing asymmetry (R = -0.73824, p = 0.0011). This study provides quantitative evidence that reduced arm swing and symmetry in PD can be modulated by dopaminergic replacement. The lack of modulations of bilateral arm coordination suggests that additional neurotransmitters may also be involved in arm swing changes in PD. Further studies are warranted to investigate the longitudinal trajectory of arm swing dynamics throughout PD progression.

Weight change in Parkinson and Alzheimer patients taking atypical antipsychotic drugs

Parkinson's disease (PD) is the second most common neurodegenerative disorder of aging. The pathological hallmark of PD is neuronal inclusions termed Lewy bodies whose main component is alpha-synuclein protein. The finding of these Lewy bodies in the intestinal enteric nerves led to the hypothesis that the intestine might be an early site of PD disease in response to an environmental toxin or pathogen. One potential mechanism for environmental toxin(s) and proinflammatory luminal products to gain access to mucosal neuronal tissue and promote oxidative stress is compromised intestinal barrier integrity. However, the role of intestinal permeability in PD has never been tested. We hypothesized that PD subjects might exhibit increased intestinal permeability to proinflammatory bacterial products in the intestine. To test our hypothesis we evaluated intestinal permeability in subjects newly diagnosed with PD and compared their values to healthy subjects. In addition, we obtained intestinal biopsies from both groups and used immunohistochemistry to assess bacterial translocation, nitrotyrosine (oxidative stress), and alpha-synuclein. We also evaluated serum markers of endotoxin exposure including LPS binding protein (LBP). Our data show that our PD subjects exhibit significantly greater intestinal permeability (gut leakiness) than controls. In addition, this intestinal hyperpermeability significantly correlated with increased intestinal mucosa staining for E. coli bacteria, nitrotyrosine, and alpha-synuclein as well as serum LBP levels in PD subjects. These data represent not only the first demonstration of abnormal intestinal permeability in PD subjects but also the first correlation of increased intestinal permeability in PD with intestinal alpha–synuclein (the hallmark of PD), as well as staining for gram negative bacteria and tissue oxidative stress. Our study may thus shed new light on PD pathogenesis as well as provide a new method for earlier diagnosis of PD and suggests potential therapeutic targets in PD subjects.Trial RegistrationClinicaltrials.govNCT01155492

Land subsidence modelling using tree-based machine learning algorithms

Interfacial tension (IFT) between surfactants and hydrocarbon is one of the important parameters in petroleum engineering to have a successful enhanced oil recovery (EOR) operation. Measuring IFT in the laboratory is time-consuming and costly. Since, the accurate estimation of IFT is of paramount significance, modeling with advanced intelligent techniques has been used as a proper alternative in recent years. In this study, the IFT values between surfactants and hydrocarbon were predicted using tree-based machine learning algorithms. Decision tree (DT), extra trees (ET), and gradient boosted regression trees (GBRT) were used to predict this parameter. For this purpose, 390 experimental data collected from previous studies were used to implement intelligent models. Temperature, normal alkane molecular weight, surfactant concentration, hydrophilic–lipophilic balance (HLB), and phase inversion temperature (PIT) were selected as inputs of models and independent variables. Also, the IFT between the surfactant solution and normal alkanes was selected as the output of the models and the dependent variable. Moreover, the implemented models were evaluated using statistical analyses and applied graphical methods. The results showed that DT, ET, and GBRT could predict the data with average absolute relative error values of 4.12%, 3.52%, and 2.71%, respectively. The R-squared of all implementation models is higher than 0.98, and for the best model, GBRT, it is 0.9939. Furthermore, sensitivity analysis using the Pearson approach was utilized to detect correlation coefficients of the input parameters. Based on this technique, the results of sensitivity analysis demonstrated that PIT, surfactant concentration, and HLB had the greatest effect on IFT, respectively. Finally, GBRT was statistically credited by the Leverage approach.

A comparative study of patient and staff safety evaluation using tree-based machine learning algorithms