Dataset Information

Decomposed Temporal Complexity Analysis of Neural Oscillations and Machine Learning Applied to Alzheimer's Disease Diagnosis.

ABSTRACT: Despite growing evidence of aberrant neuronal complexity in Alzheimer's disease (AD), it remains unclear how this variation arises. Neural oscillations reportedly comprise different functions depending on their own properties. Therefore, in this study, we investigated details of the complexity of neural oscillations by decomposing the oscillations into frequency, amplitude, and phase for AD patients. We applied resting-state magnetoencephalography (MEG) to 17 AD patients and 21 healthy control subjects. We first decomposed the source time series of the MEG signal into five intrinsic mode functions using ensemble empirical mode decomposition. We then analyzed the temporal complexities of these time series using multiscale entropy. Results demonstrated that AD patients had lower complexity on short time scales and higher complexity on long time scales in the alpha band in temporal regions of the brain. We evaluated the alpha band complexity further by decomposing it into amplitude and phase using Hilbert spectral analysis. Consequently, we found lower amplitude complexity and higher phase complexity in AD patients. Correlation analyses between spectral complexity and decomposed complexities revealed scale-dependency. Specifically, amplitude complexity was positively correlated with spectral complexity on short time scales, whereas phase complexity was positively correlated with spectral complexity on long time scales. Regarding the relevance of cognitive function to the complexity measures, the phase complexity on the long time scale was found to be correlated significantly with the Mini-Mental State Examination score. Additionally, we examined the diagnostic utility of the complexity characteristics using machine learning (ML) methods. We prepared a feature pool using multiple sparse autoencoders (SAEs), chose some discriminating features, and applied them to a support vector machine (SVM). Compared to the simple SVM and the SVM after feature selection (FS + SVM), the SVM with multiple SAEs (SAE + FS + SVM) had improved diagnostic accuracy. Through this study, we 1) advanced the understanding of neuronal complexity in AD patients using decomposed temporal complexity analysis and 2) demonstrated the effectiveness of combining ML methods with information about signal complexity for the diagnosis of AD.

SUBMITTER: Furutani N

PROVIDER: S-EPMC7495507 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Decomposed Temporal Complexity Analysis of Neural Oscillations and Machine Learning Applied to Alzheimer's Disease Diagnosis.

Furutani Naoki N Nariya Yuta Y Takahashi Tetsuya T Noto Sarah S Yang Albert C AC Hirosawa Tetsu T Kameya Masafumi M Minabe Yoshio Y Kikuchi Mitsuru M

Frontiers in psychiatry 20200903

Despite growing evidence of aberrant neuronal complexity in Alzheimer's disease (AD), it remains unclear how this variation arises. Neural oscillations reportedly comprise different functions depending on their own properties. Therefore, in this study, we investigated details of the complexity of neural oscillations by decomposing the oscillations into frequency, amplitude, and phase for AD patients. We applied resting-state magnetoencephalography (MEG) to 17 AD patients and 21 healthy control s ...[more]

PMID: 33101073

Similar Datasets

Project description:Alzheimer's Disease (AD) is the most common neurodegenerative disease, with 10% prevalence in the elder population. Conventional Machine Learning (ML) was proven effective in supporting the diagnosis of AD, while very few studies investigated the performance of deep learning and transfer learning in this complex task. In this paper, we evaluated the potential of ensemble transfer-learning techniques, pretrained on generic images and then transferred to structural brain MRI, for the early diagnosis and prognosis of AD, with respect to a fusion of conventional-ML approaches based on Support Vector Machine directly applied to structural brain MRI. Specifically, more than 600 subjects were obtained from the ADNI repository, including AD, Mild Cognitive Impaired converting to AD (MCIc), Mild Cognitive Impaired not converting to AD (MCInc), and cognitively-normal (CN) subjects. We used T1-weighted cerebral-MRI studies to train: (1) an ensemble of five transfer-learning architectures pretrained on generic images; (2) a 3D Convolutional Neutral Network (CNN) trained from scratch on MRI volumes; and (3) a fusion of two conventional-ML classifiers derived from different feature extraction/selection techniques coupled to SVM. The AD-vs-CN, MCIc-vs-CN, MCIc-vs-MCInc comparisons were investigated. The ensemble transfer-learning approach was able to effectively discriminate AD from CN with 90.2% AUC, MCIc from CN with 83.2% AUC, and MCIc from MCInc with 70.6% AUC, showing comparable or slightly lower results with the fusion of conventional-ML systems (AD from CN with 93.1% AUC, MCIc from CN with 89.6% AUC, and MCIc from MCInc with AUC in the range of 69.1-73.3%). The deep-learning network trained from scratch obtained lower performance than either the fusion of conventional-ML systems and the ensemble transfer-learning, due to the limited sample of images used for training. These results open new prospective on the use of transfer learning combined with neuroimages for the automatic early diagnosis and prognosis of AD, even if pretrained on generic images.

Project description:BackgroundEarly and accurate diagnosis of Alzheimer's disease (AD) is essential for disease management and therapeutic choices that can delay disease progression. Machine learning (ML) approaches have been extensively used in attempts to develop algorithms for reliable early diagnosis of AD, although clinical usefulness, interpretability, and generalizability of the classifiers across datasets and MRI protocols remain limited.MethodsWe report a multi-diagnostic and generalizable approach for mild cognitive impairment (MCI) and AD diagnosis using structural MRI and ML. Classifiers were trained and tested using subjects from the AD Neuroimaging Initiative (ADNI) database (n = 570) and the Open Access Series of Imaging Studies (OASIS) project database (n = 531). Several classifiers are compared and combined using voting for a decision. Additionally, we report tests of generalizability across datasets and protocols (IR-SPGR and MPRAGE), the impact of using graph theory measures on diagnostic classification performance, the relative importance of different brain regions on classification for better interpretability, and an evaluation of the potential for clinical applicability of the classifier.ResultsOur "healthy controls (HC) vs. AD" classifier trained and tested on the combination of ADNI and OASIS datasets obtained a balanced accuracy (BAC) of 90.6% and a Matthew's correlation coefficient (MCC) of 0.811. Our "HC vs. MCI vs. AD" classifier trained and tested on the ADNI dataset obtained a 62.1% BAC (33.3% being the by-chance cut-off) and 0.438 MCC. Hippocampal features were the strongest contributors to the classification decisions (approx. 25-45%), followed by temporal (approx. 13%), cingulate, and frontal regions (approx. 8-13% each), which is consistent with our current understanding of AD and its progression. Classifiers generalized well across both datasets and protocols. Finally, using graph theory measures did not improve classification performance.ConclusionsIn sum, we present a diagnostic tool for MCI and AD trained using baseline scans and a follow-up diagnosis regardless of progression, which is multi-diagnostic, generalizable across independent data sources and acquisition protocols, and with transparently reported performance. Rated as potentially clinically applicable, our tool may be clinically useful to inform diagnostic decisions in dementia, if successful in real-world prospective clinical trials.

Dataset Information

Decomposed Temporal Complexity Analysis of Neural Oscillations and Machine Learning Applied to Alzheimer's Disease Diagnosis.

Publications

Decomposed Temporal Complexity Analysis of Neural Oscillations and Machine Learning Applied to Alzheimer's Disease Diagnosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets