Brain activity during walking in older adults: Implications for compensatory versus dysfunctional accounts
فعالیت مغز در طول پیاده روی در بزرگسالان سالمند: پیامدهای جبران خسارت در برابر حسابهای ناکارآمد-2021
A prominent trend in the functional brain imaging literature is that older adults exhibit increased brain activity compared to young adults to perform a given task. This phenomenon has been extensively stud- ied for cognitive tasks, with the ﬁeld converging on interpretations described in two alternative accounts. One account interprets over-activation in older adults as reﬂecting neural dysfunction (increased brain activity – indicates poorer performance), whereas another interprets it as neural compensation (in- creased brain activity - supports better performance). Here we review studies that have recorded brain activity and walking measurements in older adults, and we categorize their ﬁndings as reﬂecting either neural dysfunction or neural compensation. Based on this synthesis, we recommend including multiple task diﬃculty levels in future work to help differentiate if and when compensation fails as the locomo- tion task becomes more diﬃcult. Using multiple task diﬃculty levels with neuroimaging will lead to a more advanced understanding of how age-related changes in locomotor brain activity ﬁt with existing accounts of brain aging and support the development of targeted neural rehabilitation techniques.
keywords: فعالیت مغز | پیاده روی | سالخورده | جبران خسارت | اختلال عملکرد | کنترل عصبی | Brain activity | Walking | Aging | Compensation | Dysfunction | Neural control
Towards the interpretation of complex visual hallucinations in termsof self-reorganization of neural networks
به سمت تفسیر توهمات پیچیده بصری از نظر خود سازماندهی مجدد شبکه های عصبی-2020
Patients suffering from dementia with Lewy body (DLB) often see complex visual hallucinations (CVH).Despite many pathological, clinical, and neuroimaging studies, the mechanism of CVH remains unknown.One possible scenario is that top-down information is being used to compensate for the lack of bottom-up information. To investigate this possibility and understand the underlying mathematical structureof the CVH mechanism, we propose a simple computational model of synaptic plasticity with particu-lar focus on the effect of selective damage to the bottom-up network on self-reorganization. We showneurons that undergo a change in activity from a bottom-up to a top-down network framework duringthe reorganization process, which can be understood in terms of state transitions. Assuming that thepre-reorganization representation of this neuron remains after reorganization, it is possible to interpretneural response induced by top-down information as the sensation of bottom-up information. This sit-uation might correspond to a hallucinatory situation in DLB patients. Our results agree with existingexperimental evidence and provide new insights into data that have hitherto not been experimentallyvalidated on patients with DLB.
Keywords : Network self-reorganization | Complex visual hallucinations| Synaptic plasticity | State transition | Oscillology
French magistrates perception of the introduction of neuroscientific data in expert reports: Effects on the assessment of the expert’s report and criminal case
تصور دادرسان فرانسوی از معرفی داده های علوم اعصاب در گزارش های کارشناسی : تأثیرات ارزیابی گزارش کارشناسی و پرونده جنایی-2020
Objective. – To analyze whether the judge’s perception of the quality, and scientific basis of a psychiatric expert report of a criminal defendant can vary according to whether or not this evaluation includes neuroscientific data (a written description of a structural neuroimaging MRI scan) and their effects on the decisions made by judges. Experimental psychology has demonstrated a number of cognitive effects arising from exposure to neuroscientific explanations and/or neuroimaging data and which may bias judgments and lead to (mis)interpretations that can affect decisions. This research suggests that including neuroscience evidence in an expert report may impact they way the report is assessed by nonspecialists, such as judges, whose work requires them to take into account such reports. Method. – We conducted a study on 41 French judges in order to determine whether their perceptions of the expert report (objectivity, reliability, scientific basis, quality, relevance, credibility, and persuasiveness) and their assessment of risk of recidivism, link between the disorder and offense and the influence of expert report on their decision-making, vary according to whether or not the evaluation includes neuroscientific data. The magistrates had to read a clinical case, summarizing an expertise, with or without neuroscientific data, and then answer various closed (criteria were evaluated using 7-point Likert-scales) and open-ended questions (asking respondents to indicate the reasons underlying their Likert-scale responses). Half of the magistrates received report containing neuroscientific data and the other half a similar report, without this type of data. Quantitative analyses were carried out to assess the effect of the sample’s characteristics on the responses given and to compare the results between the two conditions (correlation analyses and Student T). Qualitative analyses, terminological and thematic, were also carried out. Results. – Quantitative and qualitative results show that the presence of neuroscience data in an expert report affects judges’ perceptions of the report and the magistrates’ perceptions of the link between disorder and offense. The judges considered the expert report including neuroscientific data to be more relevant, more objective, better quality, and more reliable than the report without such data. Furthermore, they found the expert’s arguments to be more persuasive and that these arguments had a greater scientific basis when the report included neuroscientific data than when such data was absent. Moreover, this phenomenon was stronger in more experienced magistrates than in less experienced magistrates. The qualitative finding shows a greater ability to recognize shortcomings in expert reports when they do not contain neuroscience data. The Expert reports including neuroscience data are perceived as more scientific and objective. Conclusion. – The presence of neuroscience data in an expert report affects judges’ perceptions of that report. These effects may be related to cognitive biases described in the literature, in particular the perceived scientific nature of neuroscience data. If judges are aware of their limits when it comes to assessing technical data, they appear relatively unaware that scientific data can induce cognitive biases and thereby affect their perceptions of expert reports.
Keywords: Criminal liability | Evaluation | Justice decision | Magistrate | Neuroscience | Psychiatric expertise
Emotions as discrete patterns of systemic activity
احساسات به عنوان الگوهای گسسته فعالیت سیستماتیک-2019
Emotions organize human and animal behaviour by automatically adjusting their actions at multiple physiological and behavioural scales. Recently, pattern recognition techniques have emerged as an important tool for quantifying the neural, physiological, and phenomenological organization of emotions in humans. Here we review recent advances in our understanding of the human emotion system from the viewpoint of pattern recognition studies, focussing on neuroimaging experiments. These studies suggest, in general, clear and consistent categorical structure of emotions across multiple levels of analysis spanning expressive behaviour, subjective experiences, physiological activity, and neural activation patterns. In particular, the neurophysiological data support the view of multiple discrete emotion systems that are organized in a distributed fashion across the brain, with no clear one-to-one mapping between emotions and brain regions. However, these techniques are inherently limited by the choice of a priori emotion categories used in the studies, and cannot provide direct causal evidence for brain activity-emotion relationships.
Keywords: Emotion | Decoding | Affect | Pattern recognition | fMRI | MVPA | Classification
Personalised modelling with spiking neural networks integrating temporal and static information
مدل سازی شخصی شبکه های عصبی spiking با یکپارچه سازی اطلاعات موقت و استاتیک-2019
This paper proposes a new personalised prognostic/diagnostic system that supports classification, prediction and pattern recognition when both static and dynamic/spatiotemporal features are presented in a dataset. The system is based on a proposed clustering method (named d2WKNN) for optimal selection of neighbouring samples to an individual with respect to the integration of both static (vector-based) and temporal individual data. The most relevant samples to an individual are selected to train a Personalised Spiking Neural Network (PSNN) that learns from sets of streaming data to capture the space and time association patterns. The generated time-dependant patterns resulted in a higher accuracy of classification/prediction (80% to 93%) when compared with global modelling and conventional methods. In addition, the PSNN models can support interpretability by creating personalised profiling of an individual. This contributes to a better understanding of the interactions between features. Therefore, an end-user can comprehend what interactions in the model have led to a certain decision (outcome). The proposed PSNN model is an analytical tool, applicable to several real-life health applications, where different data domains describe a person’s health condition. The system was applied to two case studies: (1) classification of spatiotemporal neuroimaging data for the investigation of individual response to treatment and (2) prediction of risk of stroke with respect to temporal environmental data. For both datasets, besides the temporal data, static health data were also available. The hyper-parameters of the proposed system, including the PSNN models and the d2WKNN clustering parameters, are optimised for each individual
Keywords: Integrated data domains | Prediction | Classification | Personalised modelling | Spiking neural networks | Pattern recognition
Neurobiological divergence of the positive and negative schizophrenia subtypes identified upon a new factor-structure of psychopathology using non-negative factorization: An international machine-learning study
واگرایی عصبی از زیرگروه های اسکیزوفرنی مثبت و منفی مشخص شده بر یک ساختار جدید از روانشناسی با استفاده از فاکتورسازی غیر منفی: یک مطالعه بین المللی یادگیری ماشین-2019
Objective: Disentangling psychopathological heterogeneity in schizophrenia is challenging and previous results remain inconclusive. We employed advanced machine-learning to identify a stable and generalizable factorization of the “Positive and Negative Syndrome Scale (PANSS)”, and used it to identify psychopathological subtypes as well as their neurobiological differentiations. Methods: PANSS data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients, 586 followed up after 1.35±0.70 years) were used for learning the factor-structure by an orthonormal projective non-negative factorization. An international sample, pooled from nine medical centers across Europe, USA, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor-structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional MRI connectivity patterns. Results: A four-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original PANSS subscales and previously proposed factor-models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventro-medial frontal cortex, temporoparietal junction, and precuneus. Conclusions: Machine-learning applied to multi-site data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia
Keywords: non-negative factorization | brain imaging | subtyping | machine learning | multivariate classification | schizophrenia
A deep learning model for early prediction of Alzheimers disease dementia based on hippocampal magnetic resonance imaging data
یک مدل یادگیری عمیق برای پیش بینی اولیه زوال عقل بیماری آلزایمر بر اساس داده های تصویربرداری رزونانس مغناطیسی هیپوکامپ-2019
It is challenging at baseline to predict when and which individuals who meet criteria for mild cognitive impairment (MCI) will ultimately progress to Alzheimer’s disease (AD) dementia. Methods: A deep learning method is developed and validated based on magnetic resonance imaging scans of 2146 subjects (803 for training and 1343 for validation) to predict MCI subjects’ progression to AD dementia in a time-to-event analysis setting. Results: The deep-learning time-to-event model predicted individual subjects’ progression to AD dementia with a concordance index of 0.762 on 439 Alzheimer’s Disease Neuroimaging Initiative testing MCI subjects with follow-up duration from 6 to 78 months (quartiles: [24, 42, 54]) and a concordance index of 0.781 on 40 Australian Imaging Biomarkers and Lifestyle Study of Aging testing MCI subjects with follow-up duration from 18 to 54 months (quartiles: [18, 36, 54]). The predicted progression risk also clustered individual subjects into subgroups with significant differences in their progression time to AD dementia (P ,.0002). Improved performance for predicting progression to AD dementia (concordance index 5 0.864) was obtained when the deep learning–based progression risk was combined with baseline clinical measures. Discussion: Our method provides a cost effective and accurate means for prognosis and potentially to facilitate enrollment in clinical trials with individuals likely to progress within a specific temporal period.
Keywords: Deep learning | Hippocampus | Time-to-event analysis | Alzheimer’s disease
Toward Robust Anxiety Biomarkers: A Machine Learning Approach in a Large-Scale Sample
به سمت نشانگرهای زیستی قوی اضطراب: یک رویکرد یادگیری ماشینی در یک نمونه مقیاس بزرگ-2019
BACKGROUND: The field of psychiatry has long sought biomarkers that can objectively diagnose patients, predict treatment response, or identify individuals at risk of illness onset. However, reliable psychiatric biomarkers have yet to emerge. The recent application of machine learning techniques to develop neuroimaging-based biomarkers has yielded promising preliminary results. However, much of the work in this domain has not met best practice standards from the field of machine learning. This is especially true for studies of anxiety, creating uncertainty about the potential for anxiety biomarker development. METHODS: We applied machine learning tools to predict trait anxiety from neuroimaging measurements in humans. Using publicly available data from the Brain Genomics Superstruct Project, we compared a suite of neuroimagingbased machine learning models predicting anxiety within a discovery sample (n = 531, 307 women) via k-fold cross-validation, and we tested the final model (a stacked model incorporating region-to-region functional connectivity, amygdala seed-to-voxel connectivity, and volumetric and cortical thickness data) in a held-out, unseen test sample (n = 348, 209 women). RESULTS: Though the best model was able to predict anxiety within the discovery sample (cross-validated R2 of .06, permutation test p , .001), the generalization test within the holdout sample failed (R2 of 2.04, permutation test p . .05). CONCLUSIONS: In this study, we did not find evidence of a generalizable anxiety biomarker. However, we encourage other researchers to investigate this topic, utilizing large samples and proper methodology, to clarify the potential of neuroimaging-based anxiety biomarkers.
Keywords: Anxiety | Biomarker | fMRI | Functional connectivity | Machine learning | Predictive modeling
Visual representation decoding from human brain activity using machine learning: A baseline study
رمزگشایی نمایش تصویری از فعالیت مغز انسان با استفاده از یادگیری ماشین: یک مطالعه پایه-2019
Visual representation decoding refers to the task of deciphering what a subject is seeing or visualizing by observing the brain state via neuroimaging. In recent years, there is an increasing interest towards tackling the aforementioned task through the use of machine learning approaches. This study provides an extensive evaluation that will serve as a baseline for visual representation decoding, by exploring a wide range of model configurations, feature representations and evaluation setups. In this way, this work lays the groundwork for developing more sophisticated and accurate decoding pipelines. The evaluation results suggest that neural networks provide, on average, the best performance, while choosing the most appropriate similarity metric for the class decoding process depends mostly on the task at hand. Finally, this work may also assist domain experts to gain high-level insights about the brain’s function, through several interesting observations, e.g., our findings hint brain regions that are dominant for specific tasks and back up related claims about potential correspondence of the cortical hierarchy with deep visual representations.
Keywords: Neural decoding | Machine learning | Deep visual representations
Transfer learning of deep neural network representations for fMRI decoding
انتقال یادگیری بازنمایی های شبکه عصبی عمیق برای رمزگشایی fMRI-2019
Background: Deep neural networks have revolutionised machine learning, with unparalleled performance in object classification. However, in brain imaging (e.g., fMRI), the direct application of Convolutional Neural Networks (CNN) to decoding subject states or perception from imaging data seems impractical given the scarcity of available data. New method: In this work we propose a robust method to transfer information from deep learning (DL) features to brain fMRI data with the goal of decoding. By adopting Reduced Rank Regression with Ridge Regularisation we establish a multivariate link between imaging data and the fully connected layer (fc7) of a CNN. We exploit the reconstructed fc7 features by performing an object image classification task on two datasets: one of the largest fMRI databases, taken from different scanners from more than two hundred subjects watching different movie clips, and another with fMRI data taken while watching static images. Results: The fc7 features could be significantly reconstructed from the imaging data, and led to significant decoding performance. Comparison with existing methods: The decoding based on reconstructed fc7 outperformed the decoding based on imaging data alone. Conclusion: In this work we show how to improve fMRI-based decoding benefiting from the mapping between functional data and CNN features. The potential advantage of the proposed method is twofold: the extraction of stimuli representations by means of an automatic procedure (unsupervised) and the embedding of high-dimensional neuroimaging data onto a space designed for visual object discrimination, leading to a more manageable space from dimensionality point of view.
Keywords: Deep learning | Convolutional Neural Network | Transfer learning | Brain decoding | fMRI | MultiVoxel Pattern Analysis