scholarly journals MMDD-Ensemble: A Multimodal Data–Driven Ensemble Approach for Parkinson's Disease Detection

2021 ◽  
Vol 15 ◽  
Author(s):  
Liaqat Ali ◽  
Zhiquan He ◽  
Wenming Cao ◽  
Hafiz Tayyab Rauf ◽  
Yakubu Imrana ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Area Under The Curve ◽  
Smart Phone ◽  
Data Driven ◽  
Medical Test ◽  
Multimodal Data ◽  
Ensemble Approach ◽  
Voice Data ◽  
Sensitivity Specificity

Parkinson's disease (PD) is the second most common neurological disease having no specific medical test for its diagnosis. In this study, we consider PD detection based on multimodal voice data that was collected through two channels, i.e., Smart Phone (SP) and Acoustic Cardioid (AC). Four types of data modalities were collected through each channel, namely sustained phonation (P), speech (S), voiced (V), and unvoiced (U) modality. The contributions of this paper are twofold. First, it explores optimal data modality and features having better information about PD. Second, it proposes a MultiModal Data–Driven Ensemble (MMDD-Ensemble) approach for PD detection. The MMDD-Ensemble has two levels. At the first level, different base classifiers are developed that are driven by multimodal voice data. At the second level, the predictions of the base classifiers are fused using blending and voting methods. In order to validate the robustness of the propose method, six evaluation measures, namely accuracy, sensitivity, specificity, Matthews correlation coefficient (MCC), and area under the curve (AUC), are adopted. The proposed method outperformed the best results produced by optimal unimodal framework from both the key evaluation aspects, i.e., accuracy and AUC. Furthermore, the proposed method also outperformed other state-of-the-art ensemble models. Experimental results show that the proposed multimodal approach yields 96% accuracy, 100% sensitivity, 88.88% specificity, 0.914 of MCC, and 0.986 of AUC. These results are promising compared to the recently reported results for PD detection based on multimodal voice data.

scholarly journals Detection of Dermal Alpha-Synuclein Deposits as a Biomarker for Parkinson’s Disease

2021 ◽  
pp. 1-11
Author(s):  
Kathrin Doppler
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Immunohistochemical Staining ◽  
Outcome Measure ◽  
Alpha Synuclein ◽  
Good Sensitivity ◽  
Promising Tool ◽  
Skin Biopsies ◽  
Methodological Problems ◽  
Sensitivity Specificity

Alpha-synuclein deposits are detectable in skin biopsies of patients with Parkinson’s disease and other synucleinopathies like multiple system atrophy by immunohistochemical staining. As they are easily to obtain, they appear a promising tool for the pre-mortem histopathological confirmation of the disease and as a potential outcome measure in studies targeting alpha-synuclein aggregates. Good sensitivity, specificity, and practicability are the most important requirements of a biomarker. The review gives an overview on all three aspects, addresses methodological problems and the lack of standardized procedures as a major problem and gives an outlook on the future of skin biopsy as a potential diagnostic tool in synucleinopathies.

scholarly journals A mobile app for tracking non-motor symptoms of people with Parkinson’s disease: A usability study

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 890-890
Author(s):  
JuHee Lee ◽  
Yujin Suh ◽  
Yielin Kim
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Tracking System ◽  
Smart Phone ◽  
Telephone Counseling ◽  
Mobile App ◽  
Motor Symptoms ◽  
Hand Tremor ◽  
Non Motor Symptoms

Abstract Smart phone-based technology for people with Parkinson’s disease has been developed worldwide. Unmonitored non-motor symptoms decrease quality of life of people with Parkinson’s disease, so the needs for technology to manage non-motor symptoms are increasing. The technology is needed to detect subtle changes in non-motor symptoms by healthcare professional. There is no mobile app which manage comprehensive symptoms of Parkinson’s disease including non-motor symptoms. It is necessary to develop a new tracking system that can effectively manage non-motor symptoms as well as motor symptoms of Parkinson’s disease. We developed a prototype of mobile app for Android smartphones, with cooperation with Mazelone company. we also have shaped functions for monitoring of motor symptoms and medication adherence. It also provided a section for caregivers to use on behalf of people with Parkinson’s disease who have difficulty to use app due to hand tremor. Through Delphi technique, we obtained content validity from eight medical and nursing experts on the contents of the application. We provided regular telephone counseling to improve and encourage their app usage. Fifteen participants used the app for 6 weeks. To evaluate usability of mobile app, we provided constructed questionnaire and conducted individual telephone interview. A mobile app for tracking non-motor symptoms demonstrated high usability and satisfaction. We learned lessons about facilitators and barriers when implementing an app such as perception and acceptance of mobile technology. The mobile app will improve continuum of care. Future studies need to improve the contents and refine technical approach for people with Parkinson’s disease.

Motor patterns in Parkinson's disease: A data-driven approach

2009 ◽  
Vol 24 (7) ◽  
pp. 1042-1047 ◽  
Author(s):  
Stephanie M. van Rooden ◽  
Martine Visser ◽  
Dagmar Verbaan ◽  
Johan Marinus ◽  
Jacobus J. van Hilten
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Data Driven ◽  
Motor Patterns ◽  
Data Driven Approach

scholarly journals Stability of MDS-UPDRS Motor Subtypes Over Three Years in Early Parkinson's Disease

2021 ◽  
Vol 12 ◽  
Author(s):  
Abhijeet K. Kohat ◽  
Samuel Y. E. Ng ◽  
Aidan S. Y. Wong ◽  
Nicole S. Y. Chia ◽  
Xinyi Choi ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Rating Scale ◽  
Area Under The Curve ◽  
Baseline Factors ◽  
Prospective Cohorts ◽  
The Mean ◽  
The Stability ◽  
Early Parkinson’S Disease ◽  
Levodopa Equivalent Daily Dose

Background: Various classifications have been proposed to subtype Parkinson's disease (PD) based on their motor phenotypes. However, the stability of these subtypes has not been properly evaluated.Objective: The goal of this study was to understand the distribution of PD motor subtypes, their stability over time, and baseline factors that predicted subtype stability.Methods: Participants (n = 170) from two prospective cohorts were included: the Early PD Longitudinal Singapore (PALS) study and the National Neuroscience Institute Movement Disorders Database. Early PD patients were classified into tremor-dominant (TD), postural instability and gait difficulty (PIGD), and indeterminate subtypes according to the Movement Disorder Society's Unified PD Rating Scale (MDS-UPDRS) criteria and clinically evaluated for three consecutive years.Results: At baseline, 60.6% patients were TD, 12.4% patients were indeterminate, and 27.1% patients were PIGD subtypes (p < 0.05). After 3 years, only 62% of patients in TD and 50% of patients in PIGD subtypes remained stable. The mean levodopa equivalent daily dose (LEDD) was higher in the PIGD subtype (276.92 ± 232.91 mg; p = 0.01). Lower LEDD [p < 0.05, odds ratio (OR) 0.99, 95% confidence interval (CI): 0.98–0.99] and higher TD/PIGD ratios (p < 0.05, OR 1.77, 95% CI: 1.29–2.43) were independent predictors of stability of TD subtype with an area under the curve (AUC) of 0.787 (95%CI: 0.669–0.876), sensitivity = 57.8%, and specificity = 89.7%.Conclusion: Only 50–62% of PD motor subtypes as defined by MDS-UPDRS remained stable over 3 years. TD/PIGD ratio and baseline LEDD were independent predictors for TD subtype stability over 3 years.

scholarly journals Laboratory versus daily life gait characteristics in patients with multiple sclerosis, Parkinson’s disease, and matched controls

2020 ◽  
Vol 17 (1) ◽  
Author(s):  
Vrutangkumar V. Shah ◽  
James McNames ◽  
Martina Mancini ◽  
Patricia Carlson-Kuhta ◽  
Rebecca I. Spain ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neurological Disease ◽  
Inertial Sensors ◽  
Daily Life ◽  
Area Under The Curve ◽  
Gait Characteristics ◽  
Discrete Moment ◽  
Healthy Control

Abstract Background and purpose  Recent findings suggest that a gait assessment at a discrete moment in a clinic or laboratory setting may not reflect functional, everyday mobility. As a step towards better understanding gait during daily life in neurological populations, we compared gait measures that best discriminated people with multiple sclerosis (MS) and people with Parkinson’s Disease (PD) from their respective, age-matched, healthy control subjects (MS-Ctl, PD-Ctl) in laboratory tests versus a week of daily life monitoring. Methods  We recruited 15 people with MS (age mean ± SD: 49 ± 10 years), 16 MS-Ctl (45 ± 11 years), 16 people with idiopathic PD (71 ± 5 years), and 15 PD-Ctl (69 ± 7 years). Subjects wore 3 inertial sensors (one each foot and lower back) in the laboratory followed by 7 days during daily life. Mann–Whitney U test and area under the curve (AUC) compared differences between PD and PD-Ctl, and between MS and MS-Ctl in the laboratory and in daily life. Results  Participants wore sensors for 60–68 h in daily life. Measures that best discriminated gait characteristics in people with MS and PD from their respective control groups were different between the laboratory gait test and a week of daily life. Specifically, the toe-off angle best discriminated MS versus MS-Ctl in the laboratory (AUC [95% CI] = 0.80 [0.63–0.96]) whereas gait speed in daily life (AUC = 0.84 [0.69–1.00]). In contrast, the lumbar coronal range of motion best discriminated PD versus PD-Ctl in the laboratory (AUC = 0.78 [0.59–0.96]) whereas foot-strike angle in daily life (AUC = 0.84 [0.70–0.98]). AUCs were larger in daily life compared to the laboratory. Conclusions Larger AUC for daily life gait measures compared to the laboratory gait measures suggest that daily life monitoring may be more sensitive to impairments from neurological disease, but each neurological disease may require different gait outcome measures.

scholarly journals Relationship between serum homocysteine level and cognitive impairment in patients with Parkinson‘s disease

Pteridines ◽  
2019 ◽  
Vol 30 (1) ◽  
pp. 177-182
Author(s):  
Xuejuan Liu ◽  
Tong Dong ◽  
Yi Zhang ◽  
Yumei Zhao ◽  
Jingwen Yang ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
High Performance ◽  
Serum Folate ◽  
Enzyme Linked Immunosorbent Assay ◽  
Serum Homocysteine ◽  
Folate And Vitamin B12 ◽  
Sensitivity Specificity ◽  
Clinical Characteristic

Abstract OBJECTIVE To investigate the correlation between serum homocysteine (Hcy) and cognitive impairment (CI) in patients with Parkinson’s disease (PD). METHODS Eighty-one PD patients were prospectively recruited in this study from Feb 2015 to Jan 2018 in Gansu Provincial Hospital. Of the subjects, 41 were diagnosed with cognitive impairment (PD-CI) vs. the 40 others without PD (PDN). The clinical characteristic and demographic features were recorded for the two groups. The serum Hcy, folate and vitamin B12 (VitB12) were examined by high-performance liquid chromatography (HPLC) and enzyme-linked immunosorbent assay (ELISA). RESULTS The serum Hcy, folate, VitB12 concentration were 21.7±6.2 (μmol/L), 9.2±3.7 (ng/mL), 354.1±123.5 (pg/mL) for PD-CI group and 14.1±5.7 (μmol/L), 12.4±4.5 (ng/mL), 378.7±128.2 (pg/mL) for PDN group respectively. The serum level of Hcy in PD-CI group was significantly higher than that of PDN group (p<0.05), serum folate was significantly lower than PDN group (p<0.05). The diagnostic sensitivity, specificity and AUC were 77.5% (95%CI:61.6%-89.2%), 78.1% (95%CI:62.4%-89.4%), 0.82 (95%CI:0.73-0.91) for serum Hcy and 72.5% (95%CI:56.1%-85.4%), 63.4% (95%CI:46.9%-77.9%), 0.71(95%CI:0060-0.83) for serum folate respectively as serological markers for cognitive impairment diagnosis in patients with PD. Conclusion Serum Hcy and folate were different between PD-CI and PDN patients, which may play an important role in cognitive impairment development in patients with PD and can be used as promising serological diagnostic marker.

scholarly journals Alpha-Synuclein Protofibrils in Cerebrospinal Fluid: A Potential Biomarker for Parkinson's Disease

2020 ◽  
Vol 10 (4) ◽  
pp. 1429-1442
Author(s):  
Marianne von Euler Chelpin ◽  
Linda Söderberg ◽  
Johanna Fälting ◽  
Christer Möller ◽  
Marco Giorgetti ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cerebrospinal Fluid ◽  
Single Molecule ◽  
Area Under The Curve ◽  
Corticobasal Degeneration ◽  
Alpha Synuclein ◽  
Cross Reactivity ◽  
Potential Biomarker ◽  
Csf Levels

Background: Currently, there is no established biomarker for Parkinson's disease (PD) and easily accessible biomarkers are crucial for developing disease-modifying treatments. Objective: To develop a novel method to quantify cerebrospinal fluid (CSF) levels of α-synuclein protofibrils (α-syn PF) and apply it to clinical cohorts of patients with PD and atypical parkinsonian disorders. Methods: A cohort composed of 49 patients with PD, 12 with corticobasal degeneration (CBD), 22 with progressive supranuclear palsy, and 33 controls, that visited the memory clinic but had no biomarker signs of Alzheimer’s disease (AD, tau<350 pg/mL, amyloid-beta 42 (Aβ42)>530 pg/mL, and phosphorylated tau (p-tau)<60 pg/mL) was used in this study. The CSF samples were analyzed with the Single molecule array (Simoa) technology. Total α-synuclein (α-syn) levels were analyzed with a commercial ELISA-kit. Results: The assay is specific to α-syn PF, with no cross-reactivity to monomeric α-syn, or the β- and γ-synuclein variants. CSF α-syn PF levels were increased in PD compared with controls (62.1 and 40.4 pg/mL, respectively, p = 0.03), and CBD (62.1 and 34.2 pg/mL, respectively, p = 0.02). The accuracy of predicting PD using α-syn PF is significantly different from controls (area under the curve 0.68, p = 0.0097) with a sensitivity of 62.8% and specificity of 67.7%. Levels of total α-syn were significantly different between the PD and CBD groups (p = 0.04). Conclusion: The developed method specifically quantifies α-syn PF in human CSF with increased concentrations in PD, but with an overlap with asymptomatic elderly controls.

Sign in / Sign up

Export Citation Format

Share Document