Joint regression and classification via relational regularization for Parkinson's disease diagnosis

Classification of Parkinson's disease from smartphone recording data using time-frequency analysis and convolutional neural network

BACKGROUND

Parkinson's disease (PD) is a long-term neurodegenerative disease of the central nervous system. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affects most patients is voice impairment.

OBJECTIVE

Voice samples are non-invasive data that can be collected remotely for diagnosis and disease progression monitoring. In this study, we analyzed voice recording data from a smartphone as a possible medical self-diagnosis tool by using only one-second voice recording. The data from one of the largest mobile PD studies, the mPower study, was used.

METHODS

A total of 29,798 ten-second voice recordings on smartphone from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by participants saying /aa/ for ten seconds into an iPhone microphone. A dataset comprising 385,143 short one-second audio samples was generated from the original ten-second voice recordings. The samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples.

RESULTS

Classification accuracies of the proposed method with LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively.

CONCLUSIONS

We achieve a respectable classification performance using a generalized approach on a dataset with a large number of samples. The result emphasizes that an analysis based on one-second clip recorded on a smartphone could be a promising non-invasive and remotely available PD biomarker.

Investigating the relationship between the SNCA gene and cognitive abilities in idiopathic Parkinson's disease using machine learning

Cognitive impairments are prevalent in Parkinson's disease (PD), but the underlying mechanisms of their development are unknown. In this study, we aimed to predict global cognition (GC) in PD with machine learning (ML) using structural neuroimaging, genetics and clinical and demographic characteristics. As a post-hoc analysis, we aimed to explore the connection between novel selected features and GC more precisely and to investigate whether this relationship is specific to GC or is driven by specific cognitive domains. 101 idiopathic PD patients had a cognitive assessment, structural MRI and blood draw. ML was performed on 102 input features including demographics, cortical thickness and subcortical measures, and several genetic variants (APOE, MAPT, SNCA, etc.). Using the combination of RRELIEFF and Support Vector Regression, 11 features were found to be predictive of GC including sex, rs894280, Edinburgh Handedness Inventory, UPDRS-III, education, five cortical thickness measures (R-parahippocampal, L-entorhinal, R-rostral anterior cingulate, L-middle temporal, and R-transverse temporal), and R-caudate volume. The rs894280 of SNCA gene was selected as the most novel finding of ML. Post-hoc analysis revealed a robust association between rs894280 and GC, attention, and visuospatial abilities. This variant indicates a potential role for the SNCA gene in cognitive impairments of idiopathic PD.

GraphNet-based imaging biomarker model to explain levodopa-induced dyskinesia in Parkinson's disease

BACKGROUND AND OBJECTIVE

Levodopa-induced dyskinesia (LID) is a disabling complication of Parkinson's disease (PD). Imaging-based measurements, especially those related to the surface shape of the basal ganglia, have shown potential for explaining the severity of LID in PD. Here, we aimed to explore a novel application of the methodology to find biomarkers of LID severity in PD using regularization.

METHODS

We proposed an application of graph-constrained elastic net (GraphNet) regularization to detect surface-based shape biomarkers explaining the severity of LID and compared the approach with other conventional regularization methods. To examine the methods, we used two independent datasets, one as a training dataset to build the model, and the other dataset was used to validate the constructed model.

RESULTS

We found that the left striatum (putamen was the greatest and the caudate was second) was the most significant surface-based biomarker related to the severity of LID. Our results improved the interpretability of identified surface-based biomarkers compared to competing methods. We also found that GraphNet regularization improved prediction of the severity of LID better than the conventional regularization methods. Our model performed better in terms of root-mean-squared error and correlation coefficient between predicted and actual clinical scores.

CONCLUSION

The proposed algorithm offers an advantage of interpretable anatomical variations related to the deformation of the cortical surface. The experimental results showed that GraphNet regularization was robust to identify surface-based shape biomarkers related to both hypokinetic and hyperkinetic movement disorders.