Deep learning reveals personalized spatial spectral abnormalities of high delta and low alpha bands in EEG of patients with early Parkinson’s disease

2021 ◽  
Author(s):  
Chunguang Chu ◽  
Zhen Zhang ◽  
Jiang Wang ◽  
Shang Liu ◽  
Fei Wang ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Spectral Characteristics ◽  
Clinical Problem ◽  
Detection Algorithm ◽  
Control Group ◽  
Optimal Frequency ◽  
Frequency Bands ◽  
Spectrum Characteristics

Abstract Objective. Parkinson's disease (PD) is one of the most common neurodegenerative diseases, and early diagnosis is crucial to delay disease progression. The diagnosis of early PD has always been a difficult clinical problem due to the lack of reliable biomarkers. Electroencephalogram (EEG) is the most common clinical detection method, and studies have attempted to discover the EEG spectrum characteristics of early PD, but the reported conclusions are not uniform due to the heterogeneity of early PD patients. There is an urgent need for a more advanced algorithm to extract spectrum characteristics from EEG to satisfy the personalized requirements. Approach. The structured power spectral density with spatial distribution was used as the input of convolutional neural network (CNN). A visualization technique called gradient-weighted class activation mapping (Grad-CAM) was used to extract the optimal frequency bands for identifying early PD. Based on the model visualization, we proposed a novel quantitative index of spectral characteristics, spatial-mapping relative power (SRP), to detect personalized abnormalities in the spatial spectral characteristics of EEG in early PD. Main results. We demonstrated the feasibility of applying CNN to identify the patients with early PD with an accuracy of 99.87% ± 0.03%. The models indicated the characteristic frequency bands (high-delta (3.5-4.5 Hz) and low-alpha (7.5-11 Hz) frequency bands) that are used to identify the early PD. The SRP of these two characteristic bands in early PD patients was significantly higher than that in the control group, and the abnormalities were consistent at the group and individual levels. Significance. This study provides a novel personalized detection algorithm based on deep learning to reveal the optimal frequency bands for identifying early PD and obtain the spatial frequency characteristics of early PD. The findings of this study will provide an effective reference for the auxiliary diagnosis of early PD in clinical practice.

scholarly journals Application of deep learning in detecting neurological disorders from magnetic resonance images: a survey on the detection of Alzheimer’s disease, Parkinson’s disease and schizophrenia

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Manan Binth Taj Noor ◽  
Nusrat Zerin Zenia ◽  
M Shamim Kaiser ◽  
Shamim Al Mamun ◽  
Mufti Mahmud
Keyword(s):  
Alzheimer’S Disease ◽  
Parkinson’S Disease ◽  
Alzheimer's Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Neurological Disorders ◽  
Magnetic Resonance Images ◽  
Future Research ◽  
Comparative Performance

Abstract Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.

scholarly journals Study of cognitive impairment and genetic polymorphism of SLC41A1 (rs11240569 allele) in Parkinson’s disease in Upper Egypt: case-control study

2021 ◽  
Vol 57 (1) ◽  
Author(s):  
Hamdy N. El-Tallawy ◽  
Tahia H. Saleem ◽  
Wafaa M. Farghaly ◽  
Heba Mohamed Saad Eldien ◽  
Ashraf Khodaery ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
Case Control Study ◽  
Case Control ◽  
Control Group ◽  
Motor Symptoms ◽  
And Control ◽  
Non Motor Symptoms ◽  
Control Study

Abstract Background Parkinson’s disease is one of the neurodegenerative disorders that is caused by genetic and environmental factors or interaction between them. Solute carrier family 41 member 1 within the PARK16 locus has been reported to be associated with Parkinson’s disease. Cognitive impairment is one of the non-motor symptoms that is considered a challenge in Parkinson’s disease patients. This study aimed to investigate the association of rs11240569 polymorphism; a synonymous coding variant in SLC41A1 in Parkinson’s disease patients in addition to the assessment of cognitive impairment in those patients. Results In a case -control study, rs11240569 single nucleotide polymorphisms in SLC41A1, genes were genotyped in 48 Parkinson’s disease patients and 48 controls. Motor and non-motor performance in Parkinson's disease patients were assessed by using the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). The genotype and allele frequencies were compared between the two groups and revealed no significant differences between case and control groups for rs11240569 in SLC41A1 gene with P value .523 and .54, respectively. Cognition was evaluated and showed the mean ± standard deviation (SD) of WAIS score of PD patients 80.4 ± 9.13 and the range was from 61 to 105, in addition to MMSE that showed mean ± SD 21.96 ± 3.8. Conclusion Genetic testing of the present study showed that rs11240569 polymorphism of SLC41A1 gene has no significant differences in distributions of alleles and genotypes between cases and control group, in addition to cognitive impairment that is present in a large proportion of PD patients and in addition to the strong correlation between cognitive impairment and motor and non-motor symptoms progression.

scholarly journals Donepezil for mild cognitive impairment in Parkinson’s disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kyoungwon Baik ◽  
Seon Myeong Kim ◽  
Jin Ho Jung ◽  
Yang Hyun Lee ◽  
Seok Jong Chung ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Treatment Group ◽  
Outcome Measures ◽  
Rating Scale ◽  
Secondary Outcome ◽  
Control Group ◽  
Significant Difference

AbstractWe investigated the efficacy of donepezil for mild cognitive impairment in Parkinson’s disease (PD-MCI). This was a prospective, non-randomized, open-label, two-arm study. Eighty PD-MCI patients were assigned to either a treatment or control group. The treatment group received donepezil for 48 weeks. The primary outcome measures were the Korean version of Mini-Mental State Exam and Montreal Cognitive Assessment scores. Secondary outcome measures were the Clinical Dementia Rating, Unified Parkinson’s Disease Rating Scale part III, Clinical Global Impression scores. Progression of dementia was assessed at 48-week. Comprehensive neuropsychological tests and electroencephalography (EEG) were performed at baseline and after 48 weeks. The spectral power ratio of the theta to beta2 band (TB2R) in the electroencephalogram was analyzed. There was no significant difference in the primary and secondary outcome measures between the two groups. However, the treatment group showed a significant decrease in TB2R at bilateral frontotemporoparietal channels compared to the control group. Although we could not demonstrate improvements in the cognitive functions, donepezil treatment had a modulatory effect on the EEG in PD-MCI patients. EEG might be a sensitive biomarker for detecting changes in PD-MCI after donepezil treatment.

Deep learning‐based scheme to diagnose Parkinson's disease

2021 ◽  
Author(s):  
Tarjni Vyas ◽  
Raj Yadav ◽  
Chitra Solanki ◽  
Rutvi Darji ◽  
Shivani Desai ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning

scholarly journals Integrated network analysis identifying potential novel drug candidates and targets for Parkinson's disease

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Pusheng Quan ◽  
Kai Wang ◽  
Shi Yan ◽  
Shirong Wen ◽  
Chengqun Wei ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Drug Target ◽  
Target Genes ◽  
Enrichment Analysis ◽  
Gene Set Enrichment Analysis ◽  
Functional Enrichment ◽  
Control Group ◽  
Drug Candidates ◽  
Novel Drug

AbstractThis study aimed to identify potential novel drug candidates and targets for Parkinson’s disease. First, 970 genes that have been reported to be related to PD were collected from five databases, and functional enrichment analysis of these genes was conducted to investigate their potential mechanisms. Then, we collected drugs and related targets from DrugBank, narrowed the list by proximity scores and Inverted Gene Set Enrichment analysis of drug targets, and identified potential drug candidates for PD treatment. Finally, we compared the expression distribution of the candidate drug-target genes between the PD group and the control group in the public dataset with the largest sample size (GSE99039) in Gene Expression Omnibus. Ten drugs with an FDR < 0.1 and their corresponding targets were identified. Some target genes of the ten drugs significantly overlapped with PD-related genes or already known therapeutic targets for PD. Nine differentially expressed drug-target genes with p < 0.05 were screened. This work will facilitate further research into the possible efficacy of new drugs for PD and will provide valuable clues for drug design.

scholarly journals Validation of Cognitive Rehabilitation as a Balance Rehabilitation Strategy in Patients with Parkinson’s Disease: Study Protocol for a Randomized Controlled Trial

Medicina ◽  
2021 ◽  
Vol 57 (4) ◽  
pp. 314
Author(s):  
Aida Arroyo-Ferrer ◽  
Francisco José Sánchez-Cuesta ◽  
Yeray González-Zamorano ◽  
María Dolores del Castillo ◽  
Carolina Sastre-Barrios ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Cognitive Therapy ◽  
Cognitive Processing ◽  
Processing Speed ◽  
Cognitive Rehabilitation ◽  
Neurodegenerative Disorder ◽  
Control Group ◽  
Motor Symptoms ◽  
The Impact

Background: Parkinson’s disease (PD) is the second most common neurodegenerative disorder. This disease is characterized by motor symptoms, such as bradykinesia, tremor, and rigidity. Although balance impairment is characteristic of advanced stages, it can be present with less intensity since the beginning of the disease. Approximately 60% of PD patients fall once a year and 40% recurrently. On the other hand, cognitive symptoms affect up to 20% of patients with PD in early stages and can even precede the onset of motor symptoms. There are cognitive requirements for balance and can be challenged when attention is diverted or reduced, linking a worse balance and a higher probability of falls with a slower cognitive processing speed and attentional problems. Cognitive rehabilitation of attention and processing speed can lead to an improvement in postural stability in patients with Parkinson’s. Methods: We present a parallel and controlled randomized clinical trial (RCT) to assess the impact on balance of a protocol based on cognitive rehabilitation focused on sustained attention through the NeuronUP platform (Neuronup SI, La Rioja, Spain) in patients with PD. For 4 weeks, patients in the experimental group will receive cognitive therapy three days a week while the control group will not receive any therapy. The protocol has been registered at trials.gov NCT04730466. Conclusions: Cognitive therapy efficacy on balance improvement may open the possibility of new rehabilitation strategies for prevention of falls in PD, reducing morbidity, and saving costs to the health care system.

scholarly journals Early Detection of Parkinson’s Disease Using Deep Learning and Machine Learning

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 147635-147646 ◽  
Author(s):  
Wu Wang ◽  
Junho Lee ◽  
Fouzi Harrou ◽  
Ying Sun
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Early Detection

scholarly journals Feasibility Aspects of Exploring Exercise-Induced Neuroplasticity in Parkinson’s Disease: A Pilot Randomized Controlled Trial

2020 ◽  
Vol 2020 ◽  
pp. 1-12 ◽  
Author(s):  
Hanna Johansson ◽  
Malin Freidle ◽  
Urban Ekman ◽  
Ellika Schalling ◽  
Breiffni Leavy ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Dual Task ◽  
Trial Design ◽  
Controlled Trial ◽  
Recruitment Rate ◽  
Blood Sampling ◽  
Assessment Process ◽  
Control Group ◽  
Exercise Induced

Background. Recent studies indicate that exercise can induce neuroplastic changes in people with Parkinson’s disease (PwPD). Reports of feasibility outcomes from existing pilot trials however are, of date, insufficient to enable replication by others in larger definitive trials. Objective. To evaluate trial design for a definitive trial by exploring process and scientific feasibility. Methods. The trial design was a parallel-group RCT pilot with a 1 : 1 allocation ratio to either HiBalance or an active control group (HiCommunication). Both groups received one-hour sessions twice weekly, plus home exercises weekly, for 10 weeks. Participants with mild-to-moderate Parkinson’s disease (PD) were recruited via advertisement. Assessment included physical performance, structural and functional MRI, blood sampling, neuropsychological assessment, and speech/voice assessment. Process and scientific feasibility were monitored throughout the study. Process feasibility involved recruitment, participant acceptability of assessments and interventions, assessment procedures (focus on imaging, blood sampling, and dual-task gait analysis), and blinding procedures. Scientific feasibility involved trends in outcome response and safety during group training and home exercises. Data are presented in median, minimum, and maximum values. Changes from pre- to postintervention are reported descriptively. Results. Thirteen participants were included (4 women, mean age 69.7 years), with a recruitment rate of 31%. Attendance rates and follow-up questionnaires indicated that both groups were acceptable to participate. Image quality was acceptable; however, diplopia and/or sleepiness were observed in several participants during MRI. With regard to dual-task gait performance, there appeared to be a ceiling effect of the cognitive tasks with seven participants scoring all correct answers at pretest. Blinding of group allocation was successful for one assessor but was broken for half of participants for the other. Conclusions. The overall trial design proved feasible to perform, but further strengthening ahead of the definitive RCT is recommended, specifically with respect to MRI setup, cognitive dual-tasks during gait, and blinding procedures. This trial is registered with NCT03213873.

Sign in / Sign up

Export Citation Format

Share Document