An Early Stage Researcher's Primer on Systems Medicine Terminology.

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.

Association of the use of hearing aids with the conversion from mild cognitive impairment to dementia and progression of dementia: A longitudinal retrospective study.

INTRODUCTION: Hearing aid usage has been linked to improvements in cognition, communication, and socialization, but the extent to which it can affect the incidence and progression of dementia is unknown. Such research is vital given the high prevalence of dementia and hearing impairment in older adults, and the fact that both conditions often coexist. In this study, we examined for the first time the effect of the use of hearing aids on the conversion from mild cognitive impairment (MCI) to dementia and progression of dementia. METHODS: We used a large referral-based cohort of 2114 hearing-impaired patients obtained from the National Alzheimer's Coordinating Center. Survival analyses using multivariable Cox proportional hazards regression model and weighted Cox regression model with censored data were performed to assess the effect of hearing aid use on the risk of conversion from MCI to dementia and risk of death in hearing-impaired participants. Disease progression was assessed with Clinical Dementia Rating Sum of Boxes (CDR-SB) scores. Three types of sensitivity analyses were performed to validate the robustness of the results. RESULTS: MCI participants that used hearing aids were at significantly lower risk of developing all-cause dementia compared to those not using hearing aids (hazard ratio [HR] 0.73, 95% confidence interval [CI], 0.61 to 0.89; false discovery rate [FDR] P = 0.004). The mean annual rate of change (standard deviation) in CDR-SB scores for hearing aid users with MCI was 1.3 (1.45) points and significantly lower than for individuals not wearing hearing aids with a 1.7 (1.95) point increase in CDR-SB per year (P = 0.02). No association between hearing aid use and risk of death was observed. Our findings were robust subject to sensitivity analyses. DISCUSSION: Among hearing-impaired adults, hearing aid use was independently associated with reduced dementia risk. The causality between hearing aid use and incident dementia should be further tested.

A review of learning in biologically plausible spiking neural networks.

Artificial neural networks have been used as a powerful processing tool in various areas such as pattern recognition, control, robotics, and bioinformatics. Their wide applicability has encouraged researchers to improve artificial neural networks by investigating the biological brain. Neurological research has significantly progressed in recent years and continues to reveal new characteristics of biological neurons. New technologies can now capture temporal changes in the internal activity of the brain in more detail and help clarify the relationship between brain activity and the perception of a given stimulus. This new knowledge has led to a new type of artificial neural network, the Spiking Neural Network (SNN), that draws more faithfully on biological properties to provide higher processing abilities. A review of recent developments in learning of spiking neurons is presented in this paper. First the biological background of SNN learning algorithms is reviewed. The important elements of a learning algorithm such as the neuron model, synaptic plasticity, information encoding and SNN topologies are then presented. Then, a critical review of the state-of-the-art learning algorithms for SNNs using single and multiple spikes is presented. Additionally, deep spiking neural networks are reviewed, and challenges and opportunities in the SNN field are discussed.

A practical computerized decision support system for predicting the severity of Alzheimer's disease of an individual.

Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R 2 = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we then designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.

A Supervised Learning Algorithm for Learning Precise Timing of Multiple Spikes in Multilayer Spiking Neural Networks.

There is a biological evidence to prove information is coded through precise timing of spikes in the brain. However, training a population of spiking neurons in a multilayer network to fire at multiple precise times remains a challenging task. Delay learning and the effect of a delay on weight learning in a spiking neural network (SNN) have not been investigated thoroughly. This paper proposes a novel biologically plausible supervised learning algorithm for learning precisely timed multiple spikes in a multilayer SNNs. Based on the spike-timing-dependent plasticity learning rule, the proposed learning method trains an SNN through the synergy between weight and delay learning. The weights of the hidden and output neurons are adjusted in parallel. The proposed learning method captures the contribution of synaptic delays to the learning of synaptic weights. Interaction between different layers of the network is realized through biofeedback signals sent by the output neurons. The trained SNN is used for the classification of spatiotemporal input patterns. The proposed learning method also trains the spiking network not to fire spikes at undesired times which contribute to misclassification. Experimental evaluation on benchmark data sets from the UCI machine learning repository shows that the proposed method has comparable results with classical rate-based methods such as deep belief network and the autoencoder models. Moreover, the proposed method can achieve higher classification accuracies than single layer and a similar multilayer SNN.

SPANNER: A Self-Repairing Spiking Neural Network Hardware Architecture.

Recent research has shown that a glial cell of astrocyte underpins a self-repair mechanism in the human brain, where spiking neurons provide direct and indirect feedbacks to presynaptic terminals. These feedbacks modulate the synaptic transmission probability of release (PR). When synaptic faults occur, the neuron becomes silent or near silent due to the low PR of synapses; whereby the PRs of remaining healthy synapses are then increased by the indirect feedback from the astrocyte cell. In this paper, a novel hardware architecture of Self-rePAiring spiking Neural NEtwoRk (SPANNER) is proposed, which mimics this self-repairing capability in the human brain. This paper demonstrates that the hardware can self-detect and self-repair synaptic faults without the conventional components for the fault detection and fault repairing. Experimental results show that SPANNER can maintain the system performance with fault densities of up to 40%, and more importantly SPANNER has only a 20% performance degradation when the self-repairing architecture is significantly damaged at a fault density of 80%.

Corrigendum: Multi-Kernel Learning with Dartel Improves Combined MRI-PET Classification of Alzheimer's Disease in AIBL Data: Group and Individual Analyses.

[This corrects the article on p. 380 in vol. 11, PMID: 28790908.].

Multi-Kernel Learning with Dartel Improves Combined MRI-PET Classification of Alzheimer's Disease in AIBL Data: Group and Individual Analyses.

Magnetic resonance imaging (MRI) and positron emission tomography (PET) are neuroimaging modalities typically used for evaluating brain changes in Alzheimer's disease (AD). Due to their complementary nature, their combination can provide more accurate AD diagnosis or prognosis. In this work, we apply a multi-modal imaging machine-learning framework to enhance AD classification and prediction of diagnosis of subject-matched gray matter MRI and Pittsburgh compound B (PiB)-PET data related to 58 AD, 108 mild cognitive impairment (MCI) and 120 healthy elderly (HE) subjects from the Australian imaging, biomarkers and lifestyle (AIBL) dataset. Specifically, we combined a Dartel algorithm to enhance anatomical registration with multi-kernel learning (MKL) technique, yielding an average of >95% accuracy for three binary classification problems: AD-vs.-HE, MCI-vs.-HE and AD-vs.-MCI, a considerable improvement from individual modality approach. Consistent with t-contrasts, the MKL weight maps revealed known brain regions associated with AD, i.e., (para)hippocampus, posterior cingulate cortex and bilateral temporal gyrus. Importantly, MKL regression analysis provided excellent predictions of diagnosis of individuals by r2 = 0.86. In addition, we found significant correlations between the MKL classification and delayed memory recall scores with r2 = 0.62 (p < 0.01). Interestingly, outliers in the regression model for diagnosis were mainly converter samples with a higher likelihood of converting to the inclined diagnostic category. Overall, our work demonstrates the successful application of MKL with Dartel on combined neuromarkers from different neuroimaging modalities in the AIBL data. This lends further support in favor of machine learning approach in improving the diagnosis and risk prediction of AD.

SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks With Adaptive Structure.

This paper presents an enhanced rank-order-based learning algorithm, called SpikeTemp, for spiking neural networks (SNNs) with a dynamically adaptive structure. The trained feed-forward SNN consists of two layers of spiking neurons: 1) an encoding layer which temporally encodes real-valued features into spatio-temporal spike patterns and 2) an output layer of dynamically grown neurons which perform spatio-temporal classification. Both Gaussian receptive fields and square cosine population encoding schemes are employed to encode real-valued features into spatio-temporal spike patterns. Unlike the rank-order-based learning approach, SpikeTemp uses the precise times of the incoming spikes for adjusting the synaptic weights such that early spikes result in a large weight change and late spikes lead to a smaller weight change. This removes the need to rank all the incoming spikes and, thus, reduces the computational cost of SpikeTemp. The proposed SpikeTemp algorithm is demonstrated on several benchmark data sets and on an image recognition task. The results show that SpikeTemp can achieve better classification performance and is much faster than the existing rank-order-based learning approach. In addition, the number of output neurons is much smaller when the square cosine encoding scheme is employed. Furthermore, SpikeTemp is benchmarked against a selection of existing machine learning algorithms, and the results demonstrate the ability of SpikeTemp to classify different data sets after just one presentation of the training samples with comparable classification performance.

DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons.

Recent research has shown the potential capability of spiking neural networks (SNNs) to model complex information processing in the brain. There is biological evidence to prove the use of the precise timing of spikes for information coding. However, the exact learning mechanism in which the neuron is trained to fire at precise times remains an open problem. The majority of the existing learning methods for SNNs are based on weight adjustment. However, there is also biological evidence that the synaptic delay is not constant. In this paper, a learning method for spiking neurons, called delay learning remote supervised method (DL-ReSuMe), is proposed to merge the delay shift approach and ReSuMe-based weight adjustment to enhance the learning performance. DL-ReSuMe uses more biologically plausible properties, such as delay learning, and needs less weight adjustment than ReSuMe. Simulation results have shown that the proposed DL-ReSuMe approach achieves learning accuracy and learning speed improvements compared with ReSuMe.

Novelty detection using level set methods.

This paper presents a level set boundary description (LSBD) approach for novelty detection that treats the nonlinear boundary directly in the input space. The proposed approach consists of level set function (LSF) construction, boundary evolution, and termination of the training process. It employs kernel density estimation to construct the LSF of the initial boundary for the training data set. Then, a sign of the LSF-based algorithm is proposed to evolve the boundary and make it fit more tightly in the data distribution. The training process terminates when an expected fraction of rejected normal data is reached. The evolution process utilizes the signs of the LSF values at all training data points to decide whether to expand or shrink the boundary. Extensive experiments are conducted on benchmark data sets to evaluate the proposed LSBD method and compare it against four representative novelty detection methods. The experimental results demonstrate that the novelty detector modeled with the proposed LSBD can effectively detect anomalies.

Spiking neural network model of sound localization using the interaural intensity difference.

In this paper, a spiking neural network (SNN) architecture to simulate the sound localization ability of the mammalian auditory pathways using the interaural intensity difference cue is presented. The lateral superior olive was the inspiration for the architecture, which required the integration of an auditory periphery (cochlea) model and a model of the medial nucleus of the trapezoid body. The SNN uses leaky integrate-and-fire excitatory and inhibitory spiking neurons, facilitating synapses and receptive fields. Experimentally derived head-related transfer function (HRTF) acoustical data from adult domestic cats were employed to train and validate the localization ability of the architecture, training used the supervised learning algorithm called the remote supervision method to determine the azimuthal angles. The experimental results demonstrate that the architecture performs best when it is localizing high-frequency sound data in agreement with the biology, and also shows a high degree of robustness when the HRTF acoustical data is corrupted by noise.

Investigating the neural correlates of pathological cortical networks in Alzheimer's disease using heterogeneous neuronal models.

This paper describes an investigation into the pathophysiological causes of abnormal cortical oscillations in Alzheimer's disease (AD) using two heterogeneous neuronal network models. The effect of excitatory circuit disruption on the beta band power (13-30 Hz) using a conductance-based network model of 200 neurons is assessed. Then, the neural correlates of abnormal cortical oscillations in different frequency bands based on a larger network model of 1000 neurons consisting of different types of cortical neurons are also analyzed. EEG studies in AD patients have shown that beta band power (13-30 Hz) decreased in the early stages of the disease with a parallel increase in theta band power (4-7 Hz). This abnormal change progresses with the later stages of the disease but with decreased power spectra in other fast frequency bands plus an increase in delta band power (1-3 Hz). Our results show that, despite the heterogeneity of the network models, the beta band power is significantly affected by excitatory neural and synaptic loss. Second, the results of modeling a functional impairment in the excitatory circuit shows that beta band power exhibits the most decrease compared with other bands. Previous biological experiments on different types of cultural excitatory neurons show that cortical neuronal death is mediated by dysfunctional ionic behavior that might specifically contribute to the pathogenesis of ß-amyloid-peptide-induced neuronal death in AD. Our study also shows that beta band power was the first affected component when the modeled excitatory circuit begins to lose neurons and synapses.

Alpha and theta rhythm abnormality in Alzheimer's Disease: a study using a computational model.

Electroencephalography (EEG) studies in Alzheimer's Disease (AD) patients show an attenuation of average power within the alpha band (7.5-13 Hz) and an increase of power in the theta band (4-7 Hz). Significant body of evidence suggest that thalamocortical circuitry underpin the generation and modulation of alpha and theta rhythms. The research presented in this chapter is aimed at gaining a better understanding of the neuronal mechanisms underlying EEG band power changes in AD which may in the future provide useful biomarkers towards early detection of the disease and for neuropharmaceutical investigations. The study is based on a classic computational model of the thalamocortical circuitry which exhibits oscillation within the theta and the alpha bands. We are interested in the change in model oscillatory behaviour corresponding with changes in the connectivity parameters in the thalamocortical as well as sensory input pathways. The synaptic organisation as well as the connectivity parameter values in the model are modified based on recent experimental data from the cat thalamus. We observe that the inhibitory population in the model plays a crucial role in mediating the oscillatory behaviour of the model output. Further, increase in connectivity parameters in the afferent and efferent pathways of the inhibitory population induces a slowing of the output power spectra. These observations may have implications for extending the model for further AD research.

A thalamo-cortico-thalamic neural mass model to study alpha rhythms in Alzheimer's disease.

We present a lumped computational model of the thalamo-cortico-thalamic circuitry. The model essentially consists of two modules: a thalamic module and a cortical module. The thalamic module circuitry is a modified version of a classic neural mass computational model of the thalamic circuitry to simulate cortical alpha rhythms and which we have used in previous research to study EEG abnormality associated with Alzheimer's Disease (AD). Here, we introduce a modified synaptic structure representing a neuronal population in the thalamic model. Furthermore, the synaptic organisation and connectivity parameter values in the model are based on experimental data reported from the dorsal Lateral Geniculate Nucleus of different species. The cortical module circuitry is based on a recent work studying cortical brain rhythms. We vary the synaptic connectivity parameters in the thalamic module of the model to simulate the effects of AD on brain synaptic circuitry and study power within the alpha frequency bands. The power and dominant frequencies of the model output are studied in three sub-bands within the alpha band: lower alpha (7-9 Hz), middle alpha (9-11 Hz) and upper alpha (11-13 Hz). Such an analytical method conforms to recent comparative EEG studies on young adults, healthy aged adults and MCI or early stage AD patients. The results show a remarkable role of the synaptic connectivities in the inhibitory thalamic cell populations on the alpha band power and frequency. Furthermore, the total number of active synapses in the thalamic cell populations produces the slowing of alpha rhythms and a simultaneous decrease of alpha band power in the brain as a result of AD.

A spiking neural network model of the medial superior olive using spike timing dependent plasticity for sound localization.

Sound localization can be defined as the ability to identify the position of an input sound source and is considered a powerful aspect of mammalian perception. For low frequency sounds, i.e., in the range 270 Hz-1.5 KHz, the mammalian auditory pathway achieves this by extracting the Interaural Time Difference between sound signals being received by the left and right ear. This processing is performed in a region of the brain known as the Medial Superior Olive (MSO). This paper presents a Spiking Neural Network (SNN) based model of the MSO. The network model is trained using the Spike Timing Dependent Plasticity learning rule using experimentally observed Head Related Transfer Function data in an adult domestic cat. The results presented demonstrate how the proposed SNN model is able to perform sound localization with an accuracy of 91.82% when an error tolerance of +/-10 degrees is used. For angular resolutions down to 2.5 degrees , it will be demonstrated how software based simulations of the model incur significant computation times. The paper thus also addresses preliminary implementation on a Field Programmable Gate Array based hardware platform to accelerate system performance.