Early Detection Of Parkinson's Disease Research Articles

The Correlation Between Parkinson's Disease and Rapid Eye Movement Sleep Behavior Disorder: A Systematic Review.

Parkinson’s disease (PD) is a neurodegenerative disease caused due to the destruction of dopaminergic neurons and the deposition of α-synuclein proteins, known as Lewy bodies. Generally, the diagnosis of PD is centered around motor symptoms. However, the early recognition of non-motor symptoms such as autonomic dysfunction, sleep disturbances, and cognitive and psychiatric disturbances are gaining increased attention for the early diagnosis of PD. Rapid eye movement (REM) sleep behavior disorder or REM sleep behavior disorder (RBD) is described as parasomnia, which is a condition of loss of normal muscle atonia causing the person to act out vivid dreams and it has been seen to be associated with the misprocessing of intercellular α-synuclein leading to neurodegenerative diseases such as PD. This review’s objective is to highlight the significance of RBD as a prodromal premotor marker for the early detection of PD. We used PubMed as our primary database to search for articles on May 2, 2021, and a total of 1849 articles were found in our initial search using keywords and medical subject heading (MeSH) keywords. Thereafter, we removed the duplicates, applied the inclusion/exclusion criteria, and did a quality appraisal to include 10 articles in this study. We concluded that the recognition and diagnosis of RBD are of paramount importance to detect early PD, and further longitudinal studies and clinical trials are of utmost importance to understand their correlation; also, treatment trials are needed to prevent the phenoconversion of RBD into PD.

Lipoprotein-Associated Phospholipase A2 Is a Risk Factor for Patients With Parkinson's Disease.

ObjectiveTo explore the association between lipoprotein-related phospholipase A2 (Lp-PLA2) and the risk of Parkinson’s disease (PD).MethodsA case-control study involving 58 hospitalized PD patients and 60 healthy controls was carried out. Serum Lp-PLA2 level was detected. According to the disease course and severity, PD patients were subdivided to analyze the clinical value of Lp-PLA2. Relationship between Lp-PLA2 and PD risk was analyzed by logistic regression. Diagnostic value of Lp-PLA2 in PD patients was investigated using receiver’s operator characteristic curves.ResultsLp-PLA2 level was significantly higher in the PD patients compared with the controls, and was significantly and positively correlated with the Hoehn-Yahr (H&Y) stage. The serum Lp-PLA2 level and H&Y stage of PD patients with a longer disease course were significantly higher than those with a shorter disease course. PD patients with milder conditions had significantly lower serum Lp-PLA2 levels than patients with severe conditions. Multivariable logistic regression analysis indicated higher Lp-PLA2 level was an independent risk factor of PD patients. Moreover, the area under the curve for Lp-PLA2 was 0.703, which was between those of homocysteine and serum amylase A.ConclusionTo our knowledge, this is the first study to show that increased level of Lp-PLA2 is associated with the risk of PD. Lp-PLA2 may be used for early detection of PD, and provides an effective intervention target for clinical treatment of PD.

Wavelet K-Means Clustering and Fuzzy-Based Method for Segmenting MRI Images Depicting Parkinson’s Disease

The early diagnosis of Parkinson’s disease (PD) is important to reduce deaths due to this disease. Images of patients with PD obtained through magnetic resonance imaging (MRI) show gray matter, white matter, and cerebrospinal fluids; images of these components provide physicians with important information to determine the severity of the disease. Therefore, methods for segmenting these regions in images have been employed. However, difficulties have been encountered in the segmentation of the PD MRI images owing to the unclear boundaries between the gray matter and white matter and the regions being contained in homogeneous and unclear structures. Therefore, we propose a hybrid wavelet k-means clustering (KMC) and fuzzy median filter (FMF) method. First, detailed information from the MRI images was extracted using discrete wavelet transform; these images were enhanced by increasing the pixel values. The enhanced images were then fed into the KMC model for segmentation. Finally, the segmented images were input into the FMF for removing uncertainty and noise. This method can also be used for segmenting the MRI images of other diseases such as tuberous sclerosis (TBS) and atrial fibrillation (AF). The results of a qualitative and quantitative evaluation conducted using an open-source benchmark dataset and a clinical dataset were presented. The peak signal-to-noise ratio, structural similarity, and mean-squared error were used to compare the efficiency of the proposed method with that of other segmentation methods. The results proved that the proposed method can assist in the early detection of PD, TBS, and AF from MRI.

X-Vectors: New Quantitative Biomarkers for Early Parkinson's Disease Detection From Speech.

Many articles have used voice analysis to detect Parkinson's disease (PD), but few have focused on the early stages of the disease and the gender effect. In this article, we have adapted the latest speaker recognition system, called x-vectors, in order to detect PD at an early stage using voice analysis. X-vectors are embeddings extracted from Deep Neural Networks (DNNs), which provide robust speaker representations and improve speaker recognition when large amounts of training data are used. Our goal was to assess whether, in the context of early PD detection, this technique would outperform the more standard classifier MFCC-GMM (Mel-Frequency Cepstral Coefficients—Gaussian Mixture Model) and, if so, under which conditions. We recorded 221 French speakers (recently diagnosed PD subjects and healthy controls) with a high-quality microphone and via the telephone network. Men and women were analyzed separately in order to have more precise models and to assess a possible gender effect. Several experimental and methodological aspects were tested in order to analyze their impacts on classification performance. We assessed the impact of the audio segment durations, data augmentation, type of dataset used for the neural network training, kind of speech tasks, and back-end analyses. X-vectors technique provided better classification performances than MFCC-GMM for the text-independent tasks, and seemed to be particularly suited for the early detection of PD in women (7–15% improvement). This result was observed for both recording types (high-quality microphone and telephone).

Classification of Parkinson's disease based on multi-modal features and stacking ensemble learning

BackgroundEarly diagnosis of Parkinson’s disease (PD) enables timely treatment of patients and helps control the course of the disease. An efficient and reliable approach is therefore needed to develop for improving the clinical ability to diagnose this disease. New MethodWe proposed a two-layer stacking ensemble learning framework with fusing multi-modal features in this study, for accurately identifying early PD with healthy control (HC). To begin with, we investigated relative importance of multi-modal neuroimaging (T1 weighted image (T1WI), diffusion tensor imaging (DTI)) and early clinical assessment to classify PD and HC. Next, a two-layer stacking ensemble framework was proposed: at the first layer, we evaluated advantages of these four base classifiers: support vector machine (SVM), random forests (RF), K-nearest neighbor (KNN) and artificial neural network (ANN); at the second layer, a logistic regression (LR) classifier was applied to classify PD. The performance of the proposed model was evaluated by comparing with traditional ensemble models. ResultsThe proposed method performed an accuracy of 96.88 %, a precision of 100 %, a recall of 95 % and a F1 score of 97.44 % respectively for identifying PD and HC. Comparison with Existing MethodThe classification results showed that the proposed model achieved a superior performance in comparison with traditional ensemble models. ConclusionThe stacking ensemble model with efficiently and effectively integrate multiple base classifiers performed higher accuracy than each single traditional model. The method developed in this study provided a novel strategy to enhance the accuracy of diagnosis and early detection of PD.

How specific are non-motor symptoms in the prodrome of Parkinson's disease compared to other movement disorders?

The clinical diagnosis of Parkinson's disease (PD) based on motor signs is often preceded by several non-motor symptoms that can indicate early prodromal neurodegenerative processes. Such prodromal symptoms can aid the early detection of PD, but their specificity for prodromal PD in comparison to prodromes of other movement disorders is still largely unclear. We here aim to give a first insight into the published evidence of prodromal non-motor symptoms in PD, dementia with Lewy bodies (DLB), multiple system atrophy (MSA), Huntington's disease (HD), progressive supranuclear palsy (PSP) and spinocerebellar ataxia (SCA). REM-sleep behavior disorder (RBD) and autonomic dysfunction have been observed in the prodromes of PD, MSA, DLB and SCA. Depression and cognitive decline have been reported for prodromal PD, DLB, HD, SCA, and PSP. Olfactory loss has only been described in prodromal PD/DLB. However, estimating the specificity of prodromal non-motor symptoms in PD is so far complicated by scarce prospective evidence and study limitations. Information on marker specificity is a prerequisite for an accurate early (differential) diagnosis of prodromal diseases, as well as specific recruitment for targeted neuroprotective interventions. We here would like to raise awareness of these issues and encourage further prospective research of prodromal non-motor symptoms in neurodegenerative movement disorders and other diseases.

Medical follow up assessments of iPrognosis application users for early Parkinson's disease detection

Medical follow up assessments of iPrognosis application users for early Parkinson's disease detection

Early diagnosis of Parkinson’s disease using EEG, machine learning and partial directed coherence

Parkinson’s disease (PD) is a neurodegenerative disease, which has an upward progression. In advanced stages, motor symptoms cause functional impairment to patients due to the degeneration of the substantia nigra. In early stages of PD, there is a sensory impairment, and patients report visual processing dysfunction. There is still no cure for PD, and early diagnosis is essential to slow disease progression. Given the good anatomical representation and organization of the visual system in the cerebral cortex, in this study, we propose a biomarker of PD using EEG signals, photic stimulation, partial directed coherence (PDC) to perform feature extraction, and machine learning (ML) techniques. Our goal is to classify participants into three distinct groups: PD patients who are medicated; patients with PD and drug deprivation; and healthy subjects. We were able to achieve outstanding results, above 99% of accuracy and kappa statistic up to 0.98 using random forests and feature selection techniques. Comparison with existing methods: Our approach was evaluated using several ML methods. As features, we initially used the electrodes, without explicitly extracting feature vectors over signal samples. The good results we obtained by using random forests made possible clinical applications for the early detection of PD and, consequently, better prognosis and patient’s quality of life.

Machine Learning Algorithm for Gait Analysis and Classification on Early Detection of Parkinson

Gait analysis using kinetic data such as pressure distribution underneath the foot has been a topic of interest for assessing falls in elderly and certain pathology such as Parkinson's disease. The disease which affects the central nervous system cannot be ultimately diagnosed by a test. In this letter, we describe a detection algorithm able to classify subjects into Parkinson or normal subjects based on load distribution during gait. This will allow those with the disease to benefit from early detection and thus early treatment. We perform spatial and time signal analyses over vertical ground reaction forces to categorize gaits as balanced or unbalanced, where unbalanced gaits correspond to subjects with Parkinson's disease and balanced gaits could be relevant to both normal and diseased subjects. Then simple features like correlation are used to further differentiate between balanced-normal subjects and balanced-diseased subjects. A 95% overall classification accuracy has been achieved using a linear decision boundary. This letter can be employed to form the basis of designing a portable device for early Parkinson's disease detection on a real-time basis. Moreover, it can be used for evaluation purposes of a rehabilitation program.

Fuzzy recurrence plot-based analysis of dynamic and static spiral tests of Parkinson’s disease patients

Parkinson’s disease (PD) is a chronic and progressive neurological illness affecting millions of people in the world. The cure for PD is not available. Drug therapies can handle some symptoms of disease like reducing tremor. PD is diagnosed with decrease in dopamine concentrations in the brain by using clinical tests. Early detection of the disease is important for the treatment. In this study, dynamic spiral test (DST) and static spiral test (SST) of PD patients were analyzed with pre-trained deep learning algorithms for early detection of PD. Fuzzy recurrence plot (FRP) technique was used to convert time-series signals to grayscale texture images. Several time-series signals were tested to observe the performances. The deep learning algorithms were employed as classifiers and feature extractors. Drawing and signal types’ performances for classifying PD were comprehensively investigated. In short, according to the experimental results Y signal produced the best results in DST approach and arithmetic combination of the Y and P signals performed better in SST method.

Non-motor Clinical and Biomarker Predictors Enable High Cross-Validated Accuracy Detection of Early PD but Lesser Cross-Validated Accuracy Detection of Scans Without Evidence of Dopaminergic Deficit.

Background: Early stage (preclinical) detection of Parkinson's disease (PD) remains challenged yet is crucial to both differentiate it from other disorders and facilitate timely administration of neuroprotective treatment as it becomes available.Objective: In a cross-validation paradigm, this work focused on two binary predictive probability analyses: classification of early PD vs. controls and classification of early PD vs. SWEDD (scans without evidence of dopamine deficit). It was hypothesized that five distinct model types using combined non-motor and biomarker features would distinguish early PD from controls with > 80% cross-validated (CV) accuracy, but that the diverse nature of the SWEDD category would reduce early PD vs. SWEDD CV classification accuracy and alter model-based feature selection.Methods: Cross-sectional, baseline data was acquired from the Parkinson's Progressive Markers Initiative (PPMI). Logistic regression, general additive (GAM), decision tree, random forest and XGBoost models were fitted using non-motor clinical and biomarker features. Randomized train and test data partitions were created. Model classification CV performance was compared using the area under the curve (AUC), sensitivity, specificity and the Kappa statistic.Results: All five models achieved >0.80 AUC CV accuracy to distinguish early PD from controls. The GAM (CV AUC 0.928, sensitivity 0.898, specificity 0.897) and XGBoost (CV AUC 0.923, sensitivity 0.875, specificity 0.897) models were the top classifiers. Performance across all models was consistently lower in the early PD/SWEDD analyses, where the highest performing models were XGBoost (CV AUC 0.863, sensitivity 0.905, specificity 0.748) and random forest (CV AUC 0.822, sensitivity 0.809, specificity 0.721). XGBoost detection of non-PD SWEDD matched 1–2 years curated diagnoses in 81.25% (13/16) cases. In both early PD/control and early PD/SWEDD analyses, and across all models, hyposmia was the single most important feature to classification; rapid eye movement behavior disorder (questionnaire) was the next most commonly high ranked feature. Alpha-synuclein was a feature of import to early PD/control but not early PD/SWEDD classification and the Epworth Sleepiness scale was antithetically important to the latter but not former.Interpretation: Non-motor clinical and biomarker variables enable high CV discrimination of early PD vs. controls but are less effective discriminating early PD from SWEDD.

MHealth Technologies Towards Parkinson's Disease Detection and Monitoring in Daily Life: A Comprehensive Review.

Parkinson's disease (PD) can gradually affect people's lives thus attracting tremendous attention. Early PD detection and treatment can help control the disease progress, relief from the symptoms and improve the patients' life quality. However, the current practice of PD diagnosis is conducted in a clinical setup and administrated by a PD specialist due to the early signs of PD are not noticeable in daily life. According to the report of CDC/NIH, the diagnosed time of PD ranges from 2-10 years after onset. Therefore, a more accessible PD diagnosis approach is urgently demanded. In recent years, mobile health (for short mHealth) technology has been intensively investigated for preventive medicine, particularly in chronic disease management. Notably, many types of research have explored the possibility of using mobile and wearable personal devices to detect the symptom of PD and shown promising results. It provides opportunities for transforming early PD detection from clinical to daily life. This survey paper attempts to conduct a comprehensive review of mHealth technologies for PD detection from 2000 to 2019, and compares their pros and cons in practical applications and provides insights to close the performance gap between state-of-the-art clinical approaches and mHealth technologies.

Orthonasal, but not Retronasal Olfaction Is Specifically Impaired in Parkinson's Disease.

Olfactory dysfunction (OD) in Parkinson's disease (PD) appears several years before the presence of motor disturbance. Olfactory testing has the potential to serve as a tool for early detection of PD, but OD is not specific to PD as it affects up to 20% of the general population. Olfaction includes an orthonasal and a retronasal components; in some forms of OD, retronasal olfactory function is preserved. We aimed to evaluate whether combined testing components allows for discriminating between PD-related OD and non-Parkinsonian OD (NPOD). The objective of this study is to orthonasal and retronasal olfactory function in PD patients and compare them to a NPOD group and to healthy controls. We hypothesized that this combined testing allows to distinguish PD patients from both other groups. We included 32 PD patients, 25 NPOD patients, and 15 healthy controls. Both olfactory components were impaired in PD and NPOD patients, compared with controls; however, NPOD patients had significantly better orthonasal scores than PD patients. Furthermore, the ratio of retronasal/orthonasal score was higher in PD than in both other groups. In the NPOD group, orthonasal and retronasal scores were significantly correlated; no such correlation could be observed in PD patients. In summary, PD patients seem to rely on compensatory mechanisms for flavor perception. Combined orthonasal and retronasal olfactory testing may contribute to differentiate PD patients from patients with NPOD.

Unawareness of hyposmia in patients with idiopathic Parkinson’s disease

BACKGROUND: Loss of olfaction is a hallmark of neurodegenerative disorders such as idiopathic Parkinson’s disease (PD) and it may precede the clinical syndrome of PD by many years. Olfactory bulb is probably the earliest site of pathology in PD. This study examines the frequency of unawareness of hyposmia in study cohorts with and without PD and its correlation with cognitive impairment. The objective of this study was to assess olfactory function using the Indian Smell Identification Test (INSIT), which evaluates the unawareness of hyposmia in patients with idiopathic PD. MATERIALS AND METHODS: Olfaction was assessed in 30 PD patients and 30 healthy controls by using INSIT. During this test, the subjects were asked to identify smell from a set of choices and were scored out of 10. The cutoff used for hyposmia was an INSIT score of ≤4. Unawareness was defined as reporting a normal sense of smell in the setting of a low INSIT. Cognitive status was assessed by using Mini Mental State Examination (MMSE) to study the effect of cognitive status on unawareness of hyposmia in PD cases. RESULTS: The mean age for the PD and control groups was 64.3± 10.6 years and 63.9 ± 10.2 years, respectively. Most of the participants were males: 53% and 56% in the PD and control groups, respectively. Out of the 30 patients in each group, 18 patients were unaware of hyposmia in the PD group as compared with 4 patients in the control group. The mean smell identification score using INSIT was 4.13 ± 2.42 in the PD group and 6.86 ± 2.3 in the control group, which was found to be significant with a p value of <0.0001. In the PD group, the mean MMSE score in subjects who were unaware of hyposmia was 27.89, whereas the mean MMSE score in subjects who were aware of smell was 29.25. This was found to be not statistically significant with a p value of 0.1087. CONCLUSION: Unawareness of hyposmia in patients with PD is high as compared with that in the elderly without PD. Under-reporting of hyposmia is seen in patients with PD. There is no increase in the unawareness of hyposmia in patients with PD who exhibit dementia. All these lead to a premise whereby population screening using INSIT could be used for the early detection of PD in those who already harbor the earliest pathology of neurodegeneration.

Investigating voice as a biomarker: Deep phenotyping methods for early detection of Parkinson's disease.

Voice technology has grown tremendously in recent years and using voice as a biomarker has also been gaining evidence. We demonstrate the potential of voice in serving as a deep phenotype for Parkinson's Disease (PD), the second most common neurodegenerative disorder worldwide, by presenting methodology for voice signal processing for clinical analysis. Detection of PD symptoms typically requires an exam by a movement disorder specialist and can be hard to access and inconsistent in findings. A vocal digital biomarker could supplement the cumbersome existing manual exam by detecting and quantifying symptoms to guide treatment. Specifically, vocal biomarkers of PD are a potentially effective method of assessing symptoms and severity in daily life, which is the focus of the current research. We analyzed a database of PD patient and non-PD subjects containing voice recordings that were used to extract paralinguistic features, which served as inputs to machine learning models to predict PD severity. The results are presented here and the limitations are discussed given the nature of the recordings. We note that our methodology only advances biomarker research and is not cleared for clinical use. Specifically, we demonstrate that conventional machine learning models applied to voice signals can be used to differentiate participants with PD who exhibit little to no symptoms from healthy controls. This work highlights the potential of voice to be used for early detection of PD and indicates that voice may serve as a deep phenotype for PD, enabling precision medicine by improving the speed, accuracy, accessibility, and cost of PD management.

Different Circulating Trace Amine Profiles in De Novo and Treated Parkinson\u2019s Disease Patients

Early diagnosis of Parkinson’s disease (PD) remains a challenge to date. New evidence highlights the potential clinical value of circulating trace amines (TAs) in early-stage PD and their involvement in disease progression. A new ultra performance chromatography mass spectrometry (UPLC-MS/MS) method was developed to quantify plasmatic TAs, and the catecholamines and indolamines pertaining to the same biochemical pathways. Three groups of subjects were recruited: 21 de novo, drug untreated, PD patients, 27 in treatment PD patients and 10 healthy subjects as controls. Multivariate and univariate data analyses were applied to reveal metabolic changes among the groups in attempt to discover new putative markers for early PD detection and disease progression. Different circulating levels of tyrosine (p = 0.002), tyramine (p < 0.001), synephrine (p = 0.015), norepinephrine (p = 0.012), metanephrine (p = 0.001), β-phenylethylamine (p = 0.001) and serotonin (p = 0.006) were found among the three groups. While tyramine behaves as a putative biomarker for early-stage PD (AUC = 0.90) tyramine, norepinephrine, and tyrosine appear to act as biomarkers of disease progression (AUC > 0.75). The findings of this pilot cross-sectional study suggest that biochemical anomalies of the aminergic and indolic neurotransmitters occur in PD patients. Compounds within the TAs family may constitute putative markers for early stage detection and progression of PD.

Thomson Multitaper MFCC and PLP voice features for early detection of Parkinson disease

Abstract In this paper, MFCC and PLP voice features extracted using Single Taper Smooth (STS) window and Thomson Multitaper (TMT) windowing technique together with a neural network classifier is used in the classification of Healthy people from early stage Parkinson diseased patients and a performance comparison of the two techniques is reported. Parkinson disease in their early stages, not only affects the muscular movements of the human body but also influences the articulatory process of the speech production mechanism. This signifies change in the shape of the vocal tract which manifests itself in the short time power spectrum. The MFCC and PLP features used in this investigation, which represent the vocal tract parameters are derived from the short time spectrum. It is therefore crucial to estimate this short time power spectrum accurately. Generally, the short time speech power spectrum is estimated using STS window. But this power spectrum computed manifests large variance in the spectral estimates. Hence a variance reduced power spectrum is attained by computing the weighted average of the short time speech spectra obtained using a set of TMT windows. This spectrum is then used to compute the PLP and MFCC features. In this paper, extraction of both these voice features using STS window as well as TMT technique with three different weights namely Uniform, Eigen value (EV) and Adaptive weights is implemented using the speech samples of healthy and Parkinson diseased individuals. The experiment was carried out for several Thomson tapers ranging from 1 to 12 and the optimal number of tapers needed for the application and dataset is reported. A comparative performance analysis of the techniques implemented using both MFCC and PLP as features is then carried out in terms of classification accuracy, Equal Error Rate, sensitivity, selectivity and F1 score for the optimal taper value. The results obtained show that in comparison with the STS window a maximum improvement in the classification accuracy was obtained to be 6.6% for nine tapers, adaptive weights using MFCC as features and 6.9% for five tapers, EV weights using PLP as features for experimental dataset 1 and 6.0% using MFCC and 6.4% using PLP for experimental dataset 2. A performance improvement in other measures for the optimal taper value is also observed and reported for experimental dataset 1.

Sensor Array for Detection of Early Stage Parkinson's Disease before Medication.

Early diagnosis of Parkinson's disease (PD) is important because it affects the choice of therapy and is subject to a relatively high degree of error. In addition, early detection of PD can potentially enable the start of neuroprotective therapy before extensive loss of dopaminergic neurons of the substantia nigra occurs. However, until now, studies for early detection of PD using volatile biomarkers sampled only treated and medicated patients. Therefore, there is a great need to evaluate untreated patients for establishing a real world screening and diagnostic technology. Here we describe for the first time a clinical trial to distinguish between de novo PD and control subjects using an electronic system for detection of volatile molecules in exhaled breath (sensor array). We further determine for the first time the association to other common tests for PD diagnostics as smell, ultrasound, and nonmotor symptoms. The test group consisted of 29 PD patients after initial diagnosis by an experienced neurologist, compared with 19 control subjects of similar age. The sensitivity, specificity, and accuracy values of the sensor array to detect PD from controls were 79%, 84%, and 81% respectively, in comparison with midbrain ultrasonography (93%, 90%, 92%) and smell detection (62%, 89%, 73%). The results confirm previous data showing the potential of sensor arrays to detect PD.

An Intelligent Parkinson's Disease Diagnostic System Based on a Chaotic Bacterial Foraging Optimization Enhanced Fuzzy KNN Approach.

Parkinson's disease (PD) is a common neurodegenerative disease, which has attracted more and more attention. Many artificial intelligence methods have been used for the diagnosis of PD. In this study, an enhanced fuzzy k-nearest neighbor (FKNN) method for the early detection of PD based upon vocal measurements was developed. The proposed method, an evolutionary instance-based learning approach termed CBFO-FKNN, was developed by coupling the chaotic bacterial foraging optimization with Gauss mutation (CBFO) approach with FKNN. The integration of the CBFO technique efficiently resolved the parameter tuning issues of the FKNN. The effectiveness of the proposed CBFO-FKNN was rigorously compared to those of the PD datasets in terms of classification accuracy, sensitivity, specificity, and AUC (area under the receiver operating characteristic curve). The simulation results indicated the proposed approach outperformed the other five FKNN models based on BFO, particle swarm optimization, Genetic algorithms, fruit fly optimization, and firefly algorithm, as well as three advanced machine learning methods including support vector machine (SVM), SVM with local learning-based feature selection, and kernel extreme learning machine in a 10-fold cross-validation scheme. The method presented in this paper has a very good prospect, which will bring great convenience to the clinicians to make a better decision in the clinical diagnosis.

Structural Studies of Alpha-Synuclein Amyloid Filaments

Amyloid filaments of the alpha-synuclein (alpha-Syn) protein are considered the hallmark of Parkinson's disease (PD) and no biomarkers for early diagnosis have yet been developed. Thioflavin T (ThT) is the most frequently used dye to detect amyloids. We are using cryo-EM of ThT-bound alpha-Syn fibrils of PD familial variants (e.g., A30P, E46K and, A53T) to understand its mechanism of binding. The heterogeneity of amyloid filaments has been one of the greatest obstacles to structural studies. We used the fluorescence of ThT to follow the kinetics of alpha-Syn fibril formation at different ionic strengths to control fibril length and sample homogeneity for cryo-EM studies. The results show we can modulate secondary nucleation events involved in filament growth (i.e., the fragmentation rate) using sodium chloride concentrations below 1mM. Controlled proteinase-K digestion coupled with electron-spray ionization mass spectrometry of the fibril variants revealed distinctly different filament structures. Additionally, the power spectra of A30P and A53T filaments showed the 1/4.7 Å-1 layer line typical of cross-beta amyloids but the two have distinctly different helical organization. The A53T power spectrum revealed that the 1/4.7 Å-1 layer line is not a meridional but arises from a 1-start helix. This shows that the two strands in the filament are staggered, with a rise per subunit of 4.7 Å within each protofilament. We have confirmed this symmetry using the Iterative Helical Real Space Reconstruction (IHRSR) method to generate near-atomic resolution density maps of these amyloid filaments. Understanding the molecular mechanism in which ThT binds to amyloids represents a first step for structure-guided design of small molecules that may act as biomarkers for early PD detection.