ABSTRACT
Humans learn from a lot of information sources to make decisions. Once this information is learned in the brain, spatio-temporal associations are made, connecting all these sources (variables) in space and time represented as brain connectivity. In reality, to make a decision, we usually have only part of the information, either as a limited number of variables, limited time to make the decision, or both. The brain functions as a spatio-temporal associative memory. Inspired by the ability of the human brain, a brain-inspired spatio-temporal associative memory was proposed earlier that utilized the NeuCube brain-inspired spiking neural network framework. Here we applied the STAM framework to develop STAM for neuroimaging data, on the cases of EEG and fMRI, resulting in STAM-EEG and STAM-fMRI. This paper showed that once a NeuCube STAM classification model was trained on a complete spatio-temporal EEG or fMRI data, it could be recalled using only part of the time series, or/and only part of the used variables. We evaluated both temporal and spatial association and generalization accuracy accordingly. This was a pilot study that opens the field for the development of classification systems on other neuroimaging data, such as longitudinal MRI data, trained on complete data but recalled on partial data. Future research includes STAM that will work on data, collected across different settings, in different labs and clinics, that may vary in terms of the variables and time of data collection, along with other parameters. The proposed STAM will be further investigated for early diagnosis and prognosis of brain conditions and for diagnostic/prognostic marker discovery.
ABSTRACT
BACKGROUND: Longitudinal neuroimaging provides spatiotemporal brain data (STBD) measurement that can be utilised to understand dynamic changes in brain structure and/or function underpinning cognitive activities. Making sense of such highly interactive information is challenging, given that the features manifest intricate temporal, causal relations between the spatially distributed neural sources in the brain. METHODS: The current paper argues for the advancement of deep learning algorithms in brain-inspired spiking neural networks (SNN), capable of modelling structural data across time (longitudinal measurement) and space (anatomical components). The paper proposes a methodology and a computational architecture based on SNN for building personalised predictive models from longitudinal brain data to accurately detect, understand, and predict the dynamics of an individual's functional brain state. The methodology includes finding clusters of similar data to each individual, data interpolation, deep learning in a 3-dimensional brain-template structured SNN model, classification and prediction of individual outcome, visualisation of structural brain changes related to the predicted outcomes, interpretation of results, and individual and group predictive marker discovery. RESULTS: To demonstrate the functionality of the proposed methodology, the paper presents experimental results on a longitudinal magnetic resonance imaging (MRI) dataset derived from 175 older adults of the internationally recognised community-based cohort Sydney Memory and Ageing Study (MAS) spanning 6 years of follow-up. SIGNIFICANCE: The models were able to accurately classify and predict 2 years ahead of cognitive decline, such as mild cognitive impairment (MCI) and dementia with 95% and 91% accuracy, respectively. The proposed methodology also offers a 3-dimensional visualisation of the MRI models reflecting the dynamic patterns of regional changes in white matter hyperintensity (WMH) and brain volume over 6 years. CONCLUSION: The method is efficient for personalised predictive modelling on a wide range of neuroimaging longitudinal data, including also demographic, genetic, and clinical data. As a case study, it resulted in finding predictive markers for MCI and dementia as dynamic brain patterns using MRI data.
Subject(s)
Cognitive Dysfunction , Dementia , Aged , Brain/diagnostic imaging , Dementia/diagnostic imaging , Humans , Magnetic Resonance Imaging , Neural Networks, Computer , NeuroimagingABSTRACT
BACKGROUND: Depression is a common problem in older adults. The 15-item Geriatric Depression Scale (GDS-15) is a widely used psychometric tool for measuring depression in the elderly, but its psychometric properties have not been yet rigorously investigated. The aim was to evaluate psychometric properties of the GDS-15 and improve precision of the instrument by applying Rasch analysis and deriving conversion tables for transformation of raw scores into interval level data. METHODS: The data was extracted from the prospective cohort Sydney Memory and Ageing Study of initially not demented individuals aged 70 years and older. The GDS-15 items scores of 212 participants (47.2% males) were analysed using the dichotomous Rasch model. RESULTS: Initially poor reliability of the GDS-15, Person Separation Index (PSI) = 0.68, was improved by combining locally dependent items into seven super-items. These modifications improved reliability of the GDS-15 (PSI = 0.78) and resulted in the best Rasch model fit (χ2(28)=37.72, p = =0.104), strict unidimensionality and scale invariance across personal factors such as gender, diagnostic and language background. LIMITATIONS: Presence of participants with cognitive impairment may be a potential limitation. CONCLUSIONS: Reliability and psychometric characteristics of the GDS-15 were improved by minor modifications and now satisfy expectations of the unidimensional Rasch model. By using Rasch transformation tables published here psychiatrists, psychologists and researchers can transform GDS raw scores into interval-level data, which improves reliability of the GDS-15 without the need to modify its original response format. These findings increase accuracy of clinical psychometric assessments, leading to more precise diagnosis of depression in the elderly.
