Classifying spatial patterns of brain activity with machine learning methods: application to lie detection

Cognitive shifts in pain perception under moral enhancement conditions: Evidence from an EEG study

In social life, empathy and morality are often viewed as inseparable and mutually reinforcing. Pain empathy is a key form of empathy, and understanding how social moral factors affect pain empathy is an important challenge. This study uses various EEG analysis methods to explore the cognitive and neural mechanisms by which moral enhancement affects pain empathy. Behavioral results showed significantly higher ratings for painful stimuli compared to non-painful ones. ERP analysis revealed that, under moral enhancement, pain stimuli elicited more negative N1 amplitudes and more positive P3 amplitudes. Time-frequency analysis indicated that moral enhancement inhibited theta band activity in response to painful stimuli. Functional connectivity analysis showed stronger connections in the frontal, right temporal, and occipital regions under moral enhancement and in the frontal, right temporal, and parietal regions when viewing painful stimuli. Additionally, machine learning results indicated that functional connections between the right temporal and parietal regions have significant negative predictive power for moral enhancement during painful stimuli. This study reveals the complex effects of moral enhancement on pain-related stimuli, demonstrating that it not only increases adaptability to pain but also enhances moral judgment, offering new insights into the interaction between moral cognition and emotional responses with significant theoretical and practical implications.

Investigating the impact of climate variables on the organic honey yield in Turkey using XGBoost machine learning

BACKGROUND

The Turkish organic honey industry, a major player in the global market, faces challenges due to climate fluctuations. Understanding the influence of climate factors on honey production is vital for sustainable farming and economic stability.

METHOD

This study uses a machine learning approach with the XGBoost algorithm to analyze temperature, wind, humidity, precipitation and surface pressure over a 20-year period from 2004 to 2023.

RESULTS

The results show that these factors significantly impact organic honey production, with temperature, wind, humidity, precipitation and surface pressure having effects of 41.20%, 26.50%, 12.47%, 11.42% and 8.41%, respectively. Sensitivity analysis reveals the model's sensitivity to even minor fluctuations in these variables.

CONCLUSION

The results of this research underscore the necessity of integrating climate change mitigation and adaptation measures into agricultural policies and beekeeping practices. This study showcases the practical application of machine learning in deciphering the intricate relationship between climate change and the production of crops, emphasizing the importance of data-driven decision-making to guarantee long-term sustainability and financial stability in the sector. © 2024 The Author(s). Journal of the Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Distinguishing deception from its confounds by improving the validity of fMRI-based neural prediction

Deception is a universal human behavior. Yet longstanding skepticism about the validity of measures used to characterize the biological mechanisms underlying deceptive behavior has relegated such studies to the scientific periphery. Here, we address these fundamental questions by applying machine learning methods and functional magnetic resonance imaging (fMRI) to signaling games capturing motivated deception in human participants. First, we develop an approach to test for the presence of confounding processes and validate past skepticism by showing that much of the predictive power of neural predictors trained on deception data comes from processes other than deception. Specifically, we demonstrate that discriminant validity is compromised by the predictor's ability to predict behavior in a control task that does not involve deception. Second, we show that the presence of confounding signals need not be fatal and that the validity of the neural predictor can be improved by removing confounding signals while retaining those associated with the task of interest. To this end, we develop a "dual-goal tuning" approach in which, beyond the typical goal of predicting the behavior of interest, the predictor also incorporates a second compulsory goal that enforces chance performance in the control task. Together, these findings provide a firmer scientific foundation for understanding the neural basis of a neglected class of behavior, and they suggest an approach for improving validity of neural predictors.

Memory detection with concurrent behavioral, autonomic, and neuroimaging measures in a mock crime

Concealed information test (CIT) has been utilized for long to perform single measurements. The combination of multiple measures outperforms single measures because of the diverse cognitive processes they reflect and the reduction in random errors facilitated by multiple measures. To further explore the performance of the CIT with multiple measurements, 57 participants were recruited and randomly assigned into guilty and innocent groups. Subsequently, simultaneously recorded reaction time (RT), skin conductance responses (SCRs), heart rate (HR), and neuroimaging data were collected from functional near-infrared spectroscopy (fNIRS) to detect participants' concealed information in a standard CIT. The results demonstrated that all indicators including RT (area under the curve (AUC) = 0.87), SCRs (AUC = 0.79), HR (AUC = 0.78), and fNIRS (channel 8, AUC = 0.85) could differentiate guilty and innocent groups. Importantly, the use of multiple indicators achieved higher detection efficiency (AUC = 0.96) compared to the use of any single indicator. These results illustrate the effectiveness and feasibility of integrating multiple indicators for concealed information detection in CIT.

Specific static and dynamic functional network connectivity changes in thyroid-associated ophthalmopathy and it predictive values using machine learning

Background

Thyroid-associated ophthalmopathy (TAO) is a prevalent autoimmune disease characterized by ocular symptoms like eyelid retraction and exophthalmos. Prior neuroimaging studies have revealed structural and functional brain abnormalities in TAO patients, along with central nervous system symptoms such as cognitive deficits. Nonetheless, the changes in the static and dynamic functional network connectivity of the brain in TAO patients are currently unknown. This study delved into the modifications in static functional network connectivity (sFNC) and dynamic functional network connectivity (dFNC) among thyroid-associated ophthalmopathy patients using independent component analysis (ICA).

Methods

Thirty-two patients diagnosed with thyroid-associated ophthalmopathy and 30 healthy controls (HCs) underwent resting-state functional magnetic resonance imaging (rs-fMRI) scanning. ICA method was utilized to extract the sFNC and dFNC changes of both groups.

Results

In comparison to the HC group, the TAO group exhibited significantly increased intra-network functional connectivity (FC) in the right inferior temporal gyrus of the executive control network (ECN) and the visual network (VN), along with significantly decreased intra-network FC in the dorsal attentional network (DAN), the default mode network (DMN), and the left middle cingulum of the ECN. On the other hand, FNC analysis revealed substantially reduced connectivity intra- VN and inter- cerebellum network (CN) and high-level cognitive networks (DAN, DMN, and ECN) in the TAO group compared to the HC group. Regarding dFNC, TAO patients displayed abnormal connectivity across all five states, characterized by notably reduced intra-VN connectivity and CN connectivity with high-level cognitive networks (DAN, DMN, and ECN), alongside compensatory increased connectivity between DMN and low-level perceptual networks (VN and basal ganglia network). No significant differences were observed between the two groups for the three dynamic temporal metrics. Furthermore, excluding the classification outcomes of FC within VN (with an accuracy of 51.61% and area under the curve of 0.35208), the FC-based support vector machine (SVM) model demonstrated improved performance in distinguishing between TAO and HC, achieving accuracies ranging from 69.35 to 77.42% and areas under the curve from 0.68229 to 0.81667. The FNC-based SVM classification yielded an accuracy of 61.29% and an area under the curve of 0.57292.

Conclusion

In summary, our study revealed that significant alterations in the visual network and high-level cognitive networks. These discoveries contribute to our understanding of the neural mechanisms in individuals with TAO, offering a valuable target for exploring future central nervous system changes in thyroid-associated eye diseases.

A hybrid spatiotemporal deep belief network and sparse representation-based framework reveals multilevel core functional components in decoding multitask fMRI signals

Decoding human brain activity on various task-based functional brain imaging data is of great significance for uncovering the functioning mechanism of the human mind. Currently, most feature extraction model-based methods for brain state decoding are shallow machine learning models, which may struggle to capture complex and precise spatiotemporal patterns of brain activity from the highly noisy fMRI raw data. Moreover, although decoding models based on deep learning methods benefit from their multilayer structure that could extract spatiotemporal features at multiscale, the relatively large populations of fMRI datasets are indispensable, and the explainability of their results is elusive. To address the above problems, we proposed a computational framework based on hybrid spatiotemporal deep belief network and sparse representations to differentiate multitask fMRI (tfMRI) signals. Using a relatively small cohort of tfMRI data as a test bed, our framework can achieve an average classification accuracy of 97.86% and define the multilevel temporal and spatial patterns of multiple cognitive tasks. Intriguingly, our model can characterize the key components for differentiating the multitask fMRI signals. Overall, the proposed framework can identify the interpretable and discriminative fMRI composition patterns at multiple scales, offering an effective methodology for basic neuroscience and clinical research with relatively small cohorts.

A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis

BACKGROUND

Psychotic disorders are characterized by structural and functional abnormalities in brain networks. Neuroimaging techniques map and characterize such abnormalities using unique features (e.g., structural integrity, coactivation). However, it is unclear if a specific method, or a combination of modalities, is particularly effective in identifying differences in brain networks of someone with a psychotic disorder.

METHODS

A systematic meta-analysis evaluated machine learning classification of schizophrenia spectrum disorders in comparison to healthy control participants using various neuroimaging modalities (i.e., T1-weighted imaging (T1), diffusion tensor imaging (DTI), resting state functional connectivity (rs-FC), or some combination (multimodal)). Criteria for manuscript inclusion included whole-brain analyses and cross-validation to provide a complete picture regarding the predictive ability of large-scale brain systems in psychosis. For this meta-analysis, we searched Ovid MEDLINE, PubMed, PsychInfo, Google Scholar, and Web of Science published between inception and March 13th 2023. Prediction results were averaged for studies using the same dataset, but parallel analyses were run that included studies with pooled sample across many datasets. We assessed bias through funnel plot asymmetry. A bivariate regression model determined whether differences in imaging modality, demographics, and preprocessing methods moderated classification. Separate models were run for studies with internal prediction (via cross-validation) and external prediction.

RESULTS

93 studies were identified for quantitative review (30 T1, 9 DTI, 40 rs-FC, and 14 multimodal). As a whole, all modalities reliably differentiated those with schizophrenia spectrum disorders from controls (OR = 2.64 (95%CI = 2.33 to 2.95)). However, classification was relatively similar across modalities: no differences were seen across modalities in the classification of independent internal data, and a small advantage was seen for rs-FC studies relative to T1 studies in classification in external datasets. We found large amounts of heterogeneity across results resulting in significant signs of bias in funnel plots and Egger's tests. Results remained similar, however, when studies were restricted to those with less heterogeneity, with continued small advantages for rs-FC relative to structural measures. Notably, in all cases, no significant differences were seen between multimodal and unimodal approaches, with rs-FC and unimodal studies reporting largely overlapping classification performance. Differences in demographics and analysis or denoising were not associated with changes in classification scores.

CONCLUSIONS

The results of this study suggest that neuroimaging approaches have promise in the classification of psychosis. Interestingly, at present most modalities perform similarly in the classification of psychosis, with slight advantages for rs-FC relative to structural modalities in some specific cases. Notably, results differed substantially across studies, with suggestions of biased effect sizes, particularly highlighting the need for more studies using external prediction and large sample sizes. Adopting more rigorous and systematized standards will add significant value toward understanding and treating this critical population.

Multi-view manifold learning of human brain-state trajectories

The complexity of the human brain gives the illusion that brain activity is intrinsically high-dimensional. Nonlinear dimensionality-reduction methods such as uniform manifold approximation and t-distributed stochastic neighbor embedding have been used for high-throughput biomedical data. However, they have not been used extensively for brain activity data such as those from functional magnetic resonance imaging (fMRI), primarily due to their inability to maintain dynamic structure. Here we introduce a nonlinear manifold learning method for time-series data-including those from fMRI-called temporal potential of heat-diffusion for affinity-based transition embedding (T-PHATE). In addition to recovering a low-dimensional intrinsic manifold geometry from time-series data, T-PHATE exploits the data's autocorrelative structure to faithfully denoise and unveil dynamic trajectories. We empirically validate T-PHATE on three fMRI datasets, showing that it greatly improves data visualization, classification, and segmentation of the data relative to several other state-of-the-art dimensionality-reduction benchmarks. These improvements suggest many potential applications of T-PHATE to other high-dimensional datasets of temporally diffuse processes.

Machine learning based identification of structural brain alterations underlying suicide risk in adolescents

Suicide is the third leading cause of death for individuals between 15 and 19 years of age. The high suicide mortality rate and limited prior success in identifying neuroimaging biomarkers indicate that it is crucial to improve the accuracy of clinical neural signatures underlying suicide risk. The current study implements machine-learning (ML) algorithms to examine structural brain alterations in adolescents that can discriminate individuals with suicide risk from typically developing (TD) adolescents at the individual level. Structural MRI data were collected from 79 adolescents who demonstrated clinical levels of suicide risk and 79 demographically matched TD adolescents. Region-specific cortical/subcortical volume (CV/SCV) was evaluated following whole-brain parcellation into 1000 cortical and 12 subcortical regions. CV/SCV parameters were used as inputs for feature selection and three ML algorithms (i.e., support vector machine [SVM], K-nearest neighbors, and ensemble) to classify adolescents at suicide risk from TD adolescents. The highest classification accuracy of 74.79% (with sensitivity = 75.90%, specificity = 74.07%, and area under the receiver operating characteristic curve = 87.18%) was obtained for CV/SCV data using the SVM classifier. Identified bilateral regions that contributed to the classification mainly included reduced CV within the frontal and temporal cortices but increased volume within the cuneus/precuneus for adolescents at suicide risk relative to TD adolescents. The current data demonstrate an unbiased region-specific ML framework to effectively assess the structural biomarkers of suicide risk. Future studies with larger sample sizes and the inclusion of clinical controls and independent validation data sets are needed to confirm our findings.

Detecting Emotions from Illustrator Gestures—The Italian Case

The evolution of computers in recent years has given a strong boost to research techniques aimed at improving human–machine interaction. These techniques tend to simulate the dynamics of the human–human interaction process, which is based on our innate ability to understand the emotions of other humans. In this work, we present the design of a classifier to recognize the emotions expressed by human beings, and we discuss the results of its testing in a culture-specific case study. The classifier relies exclusively on the gestures people perform, without the need to access additional information, such as facial expressions, the tone of a voice, or the words spoken. The specific purpose is to test whether a computer can correctly recognize emotions starting only from gestures. More generally, it is intended to allow interactive systems to be able to automatically change their behaviour based on the recognized mood, such as adapting the information contents proposed or the flow of interaction, in analogy to what normally happens in the interaction between humans. The document first introduces the operating context, giving an overview of the recognition of emotions and the approach used. Subsequently, the relevant bibliography is described and analysed, highlighting the strengths of the proposed solution. The document continues with a description of the design and implementation of the classifier and of the study we carried out to validate it. The paper ends with a discussion of the results and a short overview of possible implications.

Effective connectivity in cortical networks during deception: A lie detection study using EEG

Previous studies have identified activated regions associated with deceptive tasks and most of them utilized time, frequency, or temporal features to identify deceptive responses. However, when deception behaviors occur, the functional connectivity pattern and the communication between different brain areas remain largely unclear. In this study, we explored the most important information flows between different brain cortices during deception. First, we employed the guilty knowledge test protocol and recorded on 64 electrodes electroencephalogram (EEG) signals from 30 subjects (15 guilty and 15 innocent). EEG source estimation was then performed to compute the cortical activities on the 24 regions of interest (ROIs). Next, effective connectivity was calculated by partial directed coherence (PDC) analysis applied to the cortical signals. Furthermore, based on the graph-theoretical analysis, the network parameters with significant differences were extracted as features to identify two groups of subjects. In addition, the ROIs frequently involved in the above network parameters were selected, and based on the difference in the group mean of PDC values of all the edges connected with the selected ROIs, we presented the strongest information flows (MIIF) in the guilty group relative to the innocent group. Experimental results first show that the optimal classification features are mainly in-degree and out-degree measures of the ROI and the high classification accuracy for four bands demonstrated that the proposed method is suitable for lie detection. In addition, the frontoparietal network was found to be most prominent among all the MIIFs in four bands. Finally, combining the neurophysiology signification of four frequency bands, respectively, we analyzed the roles of all the important information flows to uncover the underlying cognitive processes and mechanisms used in deception.

Machine learning in medical applications: A review of state-of-the-art methods

Applications of machine learning (ML) methods have been used extensively to solve various complex challenges in recent years in various application areas, such as medical, financial, environmental, marketing, security, and industrial applications. ML methods are characterized by their ability to examine many data and discover exciting relationships, provide interpretation, and identify patterns. ML can help enhance the reliability, performance, predictability, and accuracy of diagnostic systems for many diseases. This survey provides a comprehensive review of the use of ML in the medical field highlighting standard technologies and how they affect medical diagnosis. Five major medical applications are deeply discussed, focusing on adapting the ML models to solve the problems in cancer, medical chemistry, brain, medical imaging, and wearable sensors. Finally, this survey provides valuable references and guidance for researchers, practitioners, and decision-makers framing future research and development directions.

Detecting spontaneous deception in the brain

Deception detection can be of great value during the juristic investigation. Although the neural signatures of deception have been widely documented, most prior studies were biased by difficulty levels. That is, deceptive behavior typically required more effort, making deception detection possibly effort detection. Furthermore, no study has examined the generalizability across instructed and spontaneous responses and across participants. To explore these issues, we used a dual‐task paradigm, where the difficulty level was balanced between truth‐telling and lying, and the instructed and spontaneous truth‐telling and lying were collected independently. Using Multivoxel pattern analysis, we were able to decode truth‐telling versus lying with a balanced difficulty level. Results showed that the angular gyrus (AG), inferior frontal gyrus (IFG), and postcentral gyrus could differentiate lying from truth‐telling. Critically, linear classifiers trained to distinguish instructed truthful and deceptive responses could correctly differentiate spontaneous truthful and deceptive responses in AG and IFG with above‐chance accuracy. In addition, with a leave‐one‐participant‐out analysis, multivoxel neural patterns from AG could classify if the left‐out participant was lying or not in a trial. These results indicate the commonality of neural responses subserved instructed and spontaneous deceptive behavior as well as the feasibility of cross‐participant deception validation.

Abnormal global-brain functional connectivity and its relationship with cognitive deficits in drug-naive first-episode adolescent-onset schizophrenia

Abnormal functional connectivity (FC) has been reported in drug-naive first-episode adolescent-onset schizophrenia (AOS) with inconsistent results due to differently selected regions of interest. The voxel-wise global-brain functional connectivity (GFC) analysis can help explore abnormal FC in an unbiased way in AOS. A total of 48 drug-naive first-episode AOS as well as 31 sex-, age- and education-matched healthy controls were collected. Data were subjected to GFC, correlation analysis and support vector machine analyses. Compared with healthy controls, the AOS group exhibited increased GFC in the right middle frontal gyrus (MFG), and decreased GFC in the right inferior temporal gyrus, left superior temporal gyrus (STG)/precentral gyrus/postcentral gyrus, right posterior cingulate cortex /precuneus and bilateral cuneus. After the Benjamini-Hochberg correction, significantly negative correlations between GFC in the bilateral cuneus and Trail-Making Test: Part A (TMT-A) scores (r=-0.285, p=0.049), between GFC in the left STG/precentral gyrus/postcentral gyrus and TMT-A scores (r=-0.384, p=0.007), and between GFC in the right MFG and the fluency scores (r=-0.335, p=0.020) in the patients. GFC in the left STG/precentral gyrus/postcentral gyrus has a satisfactory accuracy (up to 86.08%) in classifying patients from controls. AOS shows abnormal GFC in the brain areas of multiple networks, which bears cognitive significance. These findings suggest potential abnormalities in processing self-monitoring and sensory prediction, which further elucidate the pathophysiology of AOS.

Functional magnetic resonance imaging progressive deformable registration based on a cascaded convolutional neural network

Background

Intersubject registration of functional magnetic resonance imaging (fMRI) is necessary for group analysis. Accurate image registration can significantly improve the results of statistical analysis. Traditional methods are achieved by using high-resolution structural images or manually extracting functional information. However, structural alignment does not necessarily lead to functional alignment, and manually extracting functional features is complicated and time-consuming. Recent studies have shown that deep learning-based methods can be used for deformable image registration.

Methods

We proposed a deep learning framework with a three-cascaded multi-resolution network (MR-Net) to achieve deformable image registration. MR-Net separately extracts the features of moving and fixed images via a two-stream path, predicts a sub-deformation field, and is cascaded three times. The moving and fixed images' deformation field is composed of all sub-deformation fields predicted by the MR-Net. We imposed large smoothness constraints on all sub-deformation fields to ensure their smoothness. Our proposed architecture can complete the progressive registration process to ensure the topology of the deformation field.

Results

We implemented our method on the 1000 Functional Connectomes Project (FCP) and Eyes Open Eyes Closed fMRI datasets. Our method increased the peak t values in six brain functional networks to 19.8, 17.8, 15.0, 16.4, 17.0, and 13.2. Compared with traditional methods [i.e., FMRIB Software Library (FSL) and Statistical Parametric Mapping (SPM)] and deep learning networks [i.e., VoxelMorph (VM) and Volume Tweening Network (VTN)], our method improved 47.58%, 11.88%, 18.60%, and 15.16%, respectively.

Conclusions

Our three-cascaded MR-Net can achieve statistically significant improvement in functional consistency across subjects.

Brain Fingerprinting and Lie Detection: A Study of Dynamic Functional Connectivity Patterns of Deception Using EEG Phase Synchrony Analysis

This study investigated the brain functional connectivity (FC) patterns related to lie detection (LD) tasks with the purpose of analyzing the underlying cognitive processes and mechanisms in deception. Using the guilty knowledge test protocol, 30 subjects were divided randomly into guilty and innocent groups, and their electroencephalogram (EEG) signals were recorded on 32 electrodes. Phase synchrony of EEG was analyzed between different brain regions. A few-trials-based relative phase synchrony (FTRPS) measure was proposed to avoid the false synchronization that occurs due to volume conduction. FTRPS values with a significantly statistical difference between two groups were employed to construct FC patterns of deception, and the FTRPS values from the FC networks were extracted as the features for the training and testing of the support vector machine. Finally, four more intuitive brain fingerprinting graphs (BFG) on delta, theta, alpha and beta bands were respectively proposed. The experimental results reveal that deceptive responses elicited greater oscillatory synchronization than truthful responses between different brain regions, which plays an important role in executing lying tasks. The functional connectivity in the BFG are mainly implicated in the visuo-spatial imagery, bottom-top attention and memory systems, work memory and episodic encoding, and top-down attention and inhibition processing. These may, in part, underlie the mechanism of communication between different brain cortices during lying. High classification accuracy demonstrates the validation of BFG to identify deception behavior, and suggests that the proposed FTRPS could be a sensitive measure for LD in the real application.

What Deception Tasks Used in the Lab Really Do: Systematic Review and Meta-analysis of Ecological Validity of fMRI Deception Tasks

Interpretation of the neural findings of deception without considering the ecological validity of the experimental tasks could lead to biased conclusions. In this study we classified the experimental tasks according to their inclusion of three essential components required for ecological validity: intention to lie, social interaction and motivation. First, we carried out a systematic review to categorize fMRI deception tasks and to weigh the degree of ecological validity of each one. Second, we performed a meta-analysis to identify if each type of task involves a different neural substrate and to distinguish the neurocognitive contribution of each component of ecological validity essential to deception. We detected six categories of deception tasks. Intention to lie was the component least frequently included, followed by social interaction. Monetary reward was the most frequent motivator. The results of the meta-analysis, including 59 contrasts, revealed that intention to lie is associated with activation in the left lateral occipital cortex (superior division) whereas the left angular gyrus and right inferior frontal gyrus (IFG) are engaged during lying under instructions. Additionally, the right IFG appears to participate in the social aspect of lying including simulated and real interactions. We found no effect of monetary reward in our analysis. Finally, tasks with high ecological validity recruited fewer brain areas (right insular cortex and bilateral anterior cingulate cortex (ACC)) compared to less ecological tasks, perhaps because they are more natural and realistic, and engage a wide network of brain mechanisms, as opposed to specific tasks that demand more centralized processes.

Penalized model-based clustering of fMRI data

Functional magnetic resonance imaging (fMRI) data have become increasingly available and are useful for describing functional connectivity (FC), the relatedness of neuronal activity in regions of the brain. This FC of the brain provides insight into certain neurodegenerative diseases and psychiatric disorders, and thus is of clinical importance. To help inform physicians regarding patient diagnoses, unsupervised clustering of subjects based on FC is desired, allowing the data to inform us of groupings of patients based on shared features of connectivity. Since heterogeneity in FC is present even between patients within the same group, it is important to allow subject-level differences in connectivity, while still pooling information across patients within each group to describe group-level FC. To this end, we propose a random covariance clustering model (RCCM) to concurrently cluster subjects based on their FC networks, estimate the unique FC networks of each subject, and to infer shared network features. Although current methods exist for estimating FC or clustering subjects using fMRI data, our novel contribution is to cluster or group subjects based on similar FC of the brain while simultaneously providing group- and subject-level FC network estimates. The competitive performance of RCCM relative to other methods is demonstrated through simulations in various settings, achieving both improved clustering of subjects and estimation of FC networks. Utility of the proposed method is demonstrated with application to a resting-state fMRI data set collected on 43 healthy controls and 61 participants diagnosed with schizophrenia.

Density-based clustering of static and dynamic functional MRI connectivity features obtained from subjects with cognitive impairment

Various machine-learning classification techniques have been employed previously to classify brain states in healthy and disease populations using functional magnetic resonance imaging (fMRI). These methods generally use supervised classifiers that are sensitive to outliers and require labeling of training data to generate a predictive model. Density-based clustering, which overcomes these issues, is a popular unsupervised learning approach whose utility for high-dimensional neuroimaging data has not been previously evaluated. Its advantages include insensitivity to outliers and ability to work with unlabeled data. Unlike the popular k-means clustering, the number of clusters need not be specified. In this study, we compare the performance of two popular density-based clustering methods, DBSCAN and OPTICS, in accurately identifying individuals with three stages of cognitive impairment, including Alzheimer’s disease. We used static and dynamic functional connectivity features for clustering, which captures the strength and temporal variation of brain connectivity respectively. To assess the robustness of clustering to noise/outliers, we propose a novel method called recursive-clustering using additive-noise (R-CLAN). Results demonstrated that both clustering algorithms were effective, although OPTICS with dynamic connectivity features outperformed in terms of cluster purity (95.46%) and robustness to noise/outliers. This study demonstrates that density-based clustering can accurately and robustly identify diagnostic classes in an unsupervised way using brain connectivity.

Machine learning for suicidology: A practical review of exploratory and hypothesis-driven approaches

Machine learning is being used to discover models to predict the progression from suicidal ideation to action in clinical populations. While quantifiable improvements in prediction accuracy have been achieved over theory-driven efforts, models discovered through machine learning continue to fall short of clinical relevance. Thus, the value of machine learning for reaching this objective is hotly contested. We agree that machine learning, treated as a "black box" approach antithetical to theory-building, will not discover clinically relevant models of suicide. However, such models may be developed through deliberate synthesis of data- and theory-driven approaches. By providing an accessible overview of essential concepts and common methods, we highlight how generalizable models and scientific insight may be obtained by incorporating prior knowledge and expectations to machine learning research, drawing examples from suicidology. We then discuss challenges investigators will face when using machine learning to discover models of low prevalence outcomes, such as suicide.

Distinction of Students and Expert Therapists Based on Therapeutic Motions on a Robotic Device Using Support Vector Machine

Purpose

To clarify the feature values of exercise therapy that can differentiate students and expert therapists and use this information as a reference for exercise therapy education.

Methods

The participants were therapists with 5 or more years of clinical experience and 4th year students at occupational therapist training schools who had completed their clinical practices. The exercise therapy task included Samothrace (code name, SAMO) exercises implemented on the elbow joint based on the elbow flexion angle, angular velocity, and exercise interval recordings. For analyses and student/therapist comparisons, the peak flexion angle, peak velocity, and movement time were calculated using data on elbow angle changes acquired via SAMO. Subsequently, bootstrap data were generated to differentiate between the exercise therapy techniques adopted by therapists and students, and a support vector machine was used to generate four types of data combinations with the peak flexion angle, peak velocity, and movement time values. These data were used to estimate and compare the respective accuracies with the Friedman test.

Results

The peak flexion angles were significantly smaller in the case of students. Furthermore, the peak velocities were larger, the peak flexion angles were smaller, and the movement times were shorter compared with those of therapists. The combination of peak velocity and peak flexion angle yielded the highest diagnostic accuracies.

Conclusion

When students and therapists performed upper limb exercise therapy techniques based on the kinematics movement of a robot arm, the movement speeds and joint angles differed. The combination of peak velocity and peak flexion angle was the most effective classifier used for the differentiation of the abilities of students and therapists. The peak velocity and peak flexion angle of the therapist group can be used as a reference for students when they learn upper limb therapeutic exercise techniques.

Machine-learning classification using neuroimaging data in schizophrenia, autism, ultra-high risk and first-episode psychosis

Neuropsychiatric disorders are diagnosed based on behavioral criteria, which makes the diagnosis challenging. Objective biomarkers such as neuroimaging are needed, and when coupled with machine learning, can assist the diagnostic decision and increase its reliability. Sixty-four schizophrenia, 36 autism spectrum disorder (ASD), and 106 typically developing individuals were analyzed. FreeSurfer was used to obtain the data from the participant's brain scans. Six classifiers were utilized to classify the subjects. Subsequently, 26 ultra-high risk for psychosis (UHR) and 17 first-episode psychosis (FEP) subjects were run through the trained classifiers. Lastly, the classifiers' output of the patient groups was correlated with their clinical severity. All six classifiers performed relatively well to distinguish the subject groups, especially support vector machine (SVM) and Logistic regression (LR). Cortical thickness and subcortical volume feature groups were most useful for the classification. LR and SVM were highly consistent with clinical indices of ASD. When UHR and FEP groups were run with the trained classifiers, majority of the cases were classified as schizophrenia, none as ASD. Overall, SVM and LR were the best performing classifiers. Cortical thickness and subcortical volume were most useful for the classification, compared to surface area. LR, SVM, and DT's output were clinically informative. The trained classifiers were able to help predict the diagnostic category of both UHR and FEP Individuals.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

‘Munchausen's syndrome by proxy’ or a ‘miscarriage of justice’? An initial application of functional neuroimaging to the question of guilt versus innocence

‘Munchausen's syndrome by proxy’ characteristically describes women alleged to have fabricated or induced illnesses in children under their care, purportedly to attract attention. Where conclusive evidence exists the condition's aetiology remains speculative, where such evidence is lacking diagnosis hinges upon denial of wrong-doing (conduct also compatible with innocence). How might investigators obtain objective evidence of guilt or innocence? Here, we examine the case of a woman convicted of poisoning a child. She served a prison sentence but continues to profess her innocence. Using a modified fMRI protocol (previously published in 2001) we scanned the subject while she affirmed her account of events and that of her accusers. We hypothesized that she would exhibit longer response times in association with greater activation of ventrolateral prefrontal and anterior cingulate cortices when endorsing those statements she believed to be false (i.e., when she ‘lied’). The subject was scanned 4 times at 3 Tesla. Results revealed significantly longer response times and relatively greater activation of ventrolateral prefrontal and anterior cingulate cortices when she endorsed her accusers' version of events. Hence, while we have not ‘proven’ that this subject is innocent, we demonstrate that her behavioural and functional anatomical parameters behave as if she were.

Neuroprediction and A.I. in Forensic Psychiatry and Criminal Justice: A Neurolaw Perspective

Advances in the use of neuroimaging in combination with A.I., and specifically the use of machine learning techniques, have led to the development of brain-reading technologies which, in the nearby future, could have many applications, such as lie detection, neuromarketing or brain-computer interfaces. Some of these could, in principle, also be used in forensic psychiatry. The application of these methods in forensic psychiatry could, for instance, be helpful to increase the accuracy of risk assessment and to identify possible interventions. This technique could be referred to as 'A.I. neuroprediction,' and involves identifying potential neurocognitive markers for the prediction of recidivism. However, the future implications of this technique and the role of neuroscience and A.I. in violence risk assessment remain to be established. In this paper, we review and analyze the literature concerning the use of brain-reading A.I. for neuroprediction of violence and rearrest to identify possibilities and challenges in the future use of these techniques in the fields of forensic psychiatry and criminal justice, considering legal implications and ethical issues. The analysis suggests that additional research is required on A.I. neuroprediction techniques, and there is still a great need to understand how they can be implemented in risk assessment in the field of forensic psychiatry. Besides the alluring potential of A.I. neuroprediction, we argue that its use in criminal justice and forensic psychiatry should be subjected to thorough harms/benefits analyses not only when these technologies will be fully available, but also while they are being researched and developed.

Predicting instructed simulation and dissimulation when screening for depressive symptoms

The intentional distortion of test results presents a fundamental problem to self-report-based psychiatric assessment, such as screening for depressive symptoms. The first objective of the study was to clarify whether depressed patients like healthy controls possess both the cognitive ability and motivation to deliberately influence results of commonly used screening measures. The second objective was the construction of a method derived directly from within the test takers' responses to systematically detect faking behavior. Supervised machine learning algorithms posit the potential to empirically learn the implicit interconnections between responses, which shape detectable faking patterns. In a standardized design, faking bad and faking good were experimentally induced in a matched sample of 150 depressed and 150 healthy subjects. Participants completed commonly used questionnaires to detect depressive and associated symptoms. Group differences throughout experimental conditions were evaluated using linear mixed-models. Machine learning algorithms were trained on the test results and compared regarding their capacity to systematically predict distortions in response behavior in two scenarios: (1) differentiation of authentic patient responses from simulated responses of healthy participants; (2) differentiation of authentic patient responses from dissimulated patient responses. Statistically significant convergence of the test scores in both faking conditions suggests that both depressive patients and healthy controls have the cognitive ability as well as the motivational compliance to alter their test results. Evaluation of the algorithmic capability to detect faking behavior yielded ideal predictive accuracies of up to 89%. Implications of the findings, as well as future research objectives are discussed. Trial Registration The study was pre-registered at the German registry for clinical trials (Deutsches Register klinischer Studien, DRKS; DRKS00007708).

Machine-learning prediction of self-care activity by grip strengths of both hands in poststroke hemiplegia

To investigate the relationships between grip strengths and self-care activities in stroke patients using a non-linear support vector machine (SVM).Overall, 177 inpatients with poststroke hemiparesis were enrolled. Their grip strengths were measured using the Jamar dynamometer on the first day of rehabilitation training. Self-care activities were assessed by therapists using Functional Independence Measure (FIM), including items for eating, grooming, dressing the upper body, dressing the lower body, and bathing at the time of discharge. When each FIM item score was ≥6 points, the subject was considered independent. One thousand bootstrap grip strength datasets for each independence and dependence in self-care activities were generated from the actual grip strength. Thereafter, we randomly assigned the total bootstrap datasets to 90% training and 10% testing datasets and inputted the bootstrap training data into a non-linear SVM. After training, we used the SVM algorithm to predict a testing dataset for cross-validation. This validation procedure was repeated 10 times.The SVM with grip strengths more accurately predicted independence or dependence in self-care activities than the chance level (mean ± standard deviation of accuracy rate: eating, 0.71 ± 0.04, P < .0001; grooming, 0.77 ± 0.03, P < .0001; upper-body dressing, 0.75 ± 0.03, P < .0001; lower-body dressing, 0.72 ± 0.05, P < .0001; bathing, 0.68 ± 0.03, P < .0001).Non-linear SVM based on grip strengths can prospectively predict self-care activities.

Interview based connectivity analysis of EEG in order to detect deception

Deception is mentioned as an expression or action which hides the truth and deception detection as a concept to uncover the truth. In this research, a connectivity analysis of Electro Encephalography study is presented regarding cognitive processes of an instructed liar/truth-teller about identity during an interview. In this survey, connectivity analysis is applied because it can provide unique information about brain activity patterns of lying and interaction among brain regions. The novelty of this paper lies in applying an open-ended questions interview protocol during EEG recording. We recruited 40 healthy participants to record EEG signal during the interview. For each subject, whole-brain functional and effective connectivity networks such as coherence, generalized partial direct coherence and directed directed transfer function, are constructed for the lie-telling and truth-telling conditions. The classification results demonstrate that lying could be differentiated from truth-telling with an accuracy of 86.25% with the leave-one-person-out method. Results show functional and effective connectivity patterns of lying for the average of all frequency bands are different in regions from that of truth-telling. The current study may shed new light on neural patterns of deception from connectivity analysis view point.

Precision diagnostics based on machine learning-derived imaging signatures

The complexity of modern multi-parametric MRI has increasingly challenged conventional interpretations of such images. Machine learning has emerged as a powerful approach to integrating diverse and complex imaging data into signatures of diagnostic and predictive value. It has also allowed us to progress from group comparisons to imaging biomarkers that offer value on an individual basis. We review several directions of research around this topic, emphasizing the use of machine learning in personalized predictions of clinical outcome, in breaking down broad umbrella diagnostic categories into more detailed and precise subtypes, and in non-invasively estimating cancer molecular characteristics. These methods and studies contribute to the field of precision medicine, by introducing more specific diagnostic and predictive biomarkers of clinical outcome, therefore pointing to better matching of treatments to patients.

Interpretable, highly accurate brain decoding of subtly distinct brain states from functional MRI using intrinsic functional networks and long short-term memory recurrent neural networks

Decoding brain functional states underlying cognitive processes from functional MRI (fMRI) data using multivariate pattern analysis (MVPA) techniques has achieved promising performance for characterizing brain activation patterns and providing neurofeedback signals. However, it remains challenging to decode subtly distinct brain states for individual fMRI data points due to varying temporal durations and dependency among different cognitive processes. In this study, we develop a deep learning based framework for brain decoding by leveraging recent advances in intrinsic functional network modeling and sequence modeling using long short-term memory (LSTM) recurrent neural networks (RNNs). Particularly, subject-specific intrinsic functional networks (FNs) are computed from resting-state fMRI data and are used to characterize functional signals of task fMRI data with a compact representation for building brain decoding models, and LSTM RNNs are adopted to learn brain decoding mappings between functional profiles and brain states. Validation results on fMRI data from the HCP dataset have demonstrated that brain decoding models built on training data using the proposed method could learn discriminative latent feature representations and effectively distinguish subtly distinct working memory tasks of different subjects with significantly higher accuracy than conventional decoding models. Informative FNs of the brain decoding models identified as brain activation patterns of working memory tasks were largely consistent with the literature. The method also obtained promising decoding performance on motor and social cognition tasks. Our results suggest that LSTM RNNs in conjunction with FNs could build interpretable, highly accurate brain decoding models.

Support Vector Machine-Based Classifier for the Assessment of Finger Movement of Stroke Patients Undergoing Rehabilitation

Purpose

Traditionally, clinical evaluation of motor paralysis following stroke has been of value to physicians and therapists because it allows for immediate pathophysiological assessment without the need for specialized tools. However, current clinical methods do not provide objective quantification of movement; therefore, they are of limited use to physicians and therapists when assessing responses to rehabilitation. The present study aimed to create a support vector machine (SVM)-based classifier to analyze and validate finger kinematics using the leap motion controller. Results were compared with those of 24 stroke patients assessed by therapists.

Methods

A non-linear SVM was used to classify data according to the Brunnstrom recovery stages of finger movements by focusing on peak angle and peak velocity patterns during finger flexion and extension. One thousand bootstrap data values were generated by randomly drawing a series of sample data from the actual normalized kinematics-related data. Bootstrap data values were randomly classified into training (940) and testing (60) datasets. After establishing an SVM classification model by training with the normalized kinematics-related parameters of peak angle and peak velocity, the testing dataset was assigned to predict classification of paralytic movements.

Results

High separation accuracy was obtained (mean 0.863; 95% confidence interval 0.857–0.869; p = 0.006).

Conclusion

This study highlights the ability of artificial intelligence to assist physicians and therapists evaluating hand movement recovery of stroke patients.

The effect of mental countermeasures on neuroimaging-based concealed information tests

During the last decade and a half, functional magnetic resonance imaging (fMRI) has been used to determine whether it is possible to detect concealed knowledge by examining brain activation patterns, with mixed results. Concealed information tests rely on the logic that a familiar item (probe) elicits a stronger response than unfamiliar, but otherwise comparable items (irrelevants). Previous work has shown that physical countermeasures can artificially modulate neural responses in concealed information tests, decreasing the accuracy of these methods. However, the question remains as to whether purely mental countermeasures, which are much more difficult to detect than physical ones, can also be effective. An fMRI study was conducted to address this question by assessing the effect of attentional countermeasures on the accuracy of the classification between knowledge and no-knowledge cases using both univariate and multivariate analyses. Results replicate previous work and show reliable group activation differences between the probe and the irrelevants in fronto-parietal networks. Critically, classification accuracy was generally reduced by the mental countermeasures, but only significantly so with region of interest analyses (both univariate and multivariate). For whole-brain analyses, classification accuracy was relatively low, but it was not significantly reduced by the countermeasures. These results indicate that mental countermeasure need to be addressed before these paradigms can be used in applied settings and that methods to defeat countermeasures, or at least to detect their use, need to be developed. HIGHLIGHTS: FMRI-based concealed information tests are vulnerable to mental countermeasures Measures based on regions of interest are affected by mental countermeasures Whole-brain analyses may be more robust than region of interest ones Methods to detect mental countermeasure use are needed for forensic applications.

Pattern classification differentiates decision of intertemporal choices using multi-voxel pattern analysis

In daily life, individuals frequently make trade-offs between the small-but-immediate benefits and large-but-delayed profits. This type of decision is known as intertemporal choice. Previous studies have uncovered the neurobiological mechanism of the intertemporal choice, but it still remains unclear how the patterns of brain activity predict the decisions of intertemporal choices. To fill this gap, we used functional magnetic resonance imaging (fMRI), in conjunction with the machine learning technique of multi-voxel pattern analysis (MVPA), to ascertain the predictive capability of the neuronal pattern for classifying individuals' intertemporal decisions across two independent samples. To further probe how this neuronal pattern worked in predicting individual intertemporal decision, we drew on the Power Atlas to examine the accuracies of classification within each regional mask as well. Classification findings showed that the pattern of neuronal activity over the whole-brain can correctly classify the accuracies of individual decisions up to 84.3%. Encouragingly, further analysis shows that the neuronal information encoded in three brain functional networks can predict individuals' decisions with significant discriminative power in cross-samples, namely the valuation network (e.g., striatum), the cognitive control network (e.g., dorsolateral prefrontal cortex) and the episodic prospection network (e.g., amygdala, parahippocampus gyrus, insula). Collectively, these findings advance our comprehension of the neuronal mechanism of human intertemporal decisions, and substantially reshape our understanding for this cardinal behaviour from behavioural-brain scheme to brain-behavioural configuration.

Deconstructing multivariate decoding for the study of brain function

Multivariate decoding methods were developed originally as tools to enable accurate predictions in real-world applications. The realization that these methods can also be employed to study brain function has led to their widespread adoption in the neurosciences. However, prior to the rise of multivariate decoding, the study of brain function was firmly embedded in a statistical philosophy grounded on univariate methods of data analysis. In this way, multivariate decoding for brain interpretation grew out of two established frameworks: multivariate decoding for predictions in real-world applications, and classical univariate analysis based on the study and interpretation of brain activation. We argue that this led to two confusions, one reflecting a mixture of multivariate decoding for prediction or interpretation, and the other a mixture of the conceptual and statistical philosophies underlying multivariate decoding and classical univariate analysis. Here we attempt to systematically disambiguate multivariate decoding for the study of brain function from the frameworks it grew out of. After elaborating these confusions and their consequences, we describe six, often unappreciated, differences between classical univariate analysis and multivariate decoding. We then focus on how the common interpretation of what is signal and noise changes in multivariate decoding. Finally, we use four examples to illustrate where these confusions may impact the interpretation of neuroimaging data. We conclude with a discussion of potential strategies to help resolve these confusions in interpreting multivariate decoding results, including the potential departure from multivariate decoding methods for the study of brain function.

Brain Decoding from Functional MRI Using Long Short-Term Memory Recurrent Neural Networks

Decoding brain functional states underlying different cognitive processes using multivariate pattern recognition techniques has attracted increasing interests in brain imaging studies. Promising performance has been achieved using brain functional connectivity or brain activation signatures for a variety of brain decoding tasks. However, most of existing studies have built decoding models upon features extracted from imaging data at individual time points or temporal windows with a fixed interval, which might not be optimal across different cognitive processes due to varying temporal durations and dependency of different cognitive processes. In this study, we develop a deep learning based framework for brain decoding by leveraging recent advances in sequence modeling using long short-term memory (LSTM) recurrent neural networks (RNNs). Particularly, functional profiles extracted from task functional imaging data based on their corresponding subject-specific intrinsic functional networks are used as features to build brain decoding models, and LSTM RNNs are adopted to learn decoding mappings between functional profiles and brain states. We evaluate the proposed method using task fMRI data from the HCP dataset, and experimental results have demonstrated that the proposed method could effectively distinguish brain states under different task events and obtain higher accuracy than conventional decoding models.

Deception Processing by Third-Party Observers: The Role of Speaker Intent

Deception studies typically focus on the deceiver (or the deceived), with lie detection of paramount concern. Consequently, little attention has been paid to the experience of third-party observers of deceptive communications. In the current study, therefore, we investigated the impact of deception priming on the subsequent information processing of outsiders, with a primary focus on the intent to deceive. Participants read pairs of stories (A and B) depicting everyday interpersonal interactions. In Story A, a phrase was rendered truthful, intentionally deceptive, or unintentionally misleading by context. In Story B, this same phrase was initially presented ambiguously, but followed by a sentence revealing it to be intentionally deceptive. Reading about an intentionally deceptive (as opposed to truthful) speaker (Experiment 1) and an unintentionally deceptive (as opposed to unintentionally misleading) speaker (Experiment 2) in Story A primed faster reading of the “deception” sentence in Story B. These results support the possibility of deception priming and suggest that observers are sensitive to intent (and not mere falsity) when exposed to misinformation scenarios.

Deception Decreases Brain Complexity

Extensive evidence suggests the feasibility of lie detection using electroencephalograms (EEGs). However, it is largely unknown whether there are any differences in the nonlinear features of EEGs between guilty and innocent subjects. In this study, we proposed a complexity-based method to distinguish lying from truth telling. A total of 35 participants were randomly divided into two groups, and their EEG signals were recorded with 14 electrodes. Averages for sequential sets of five trials were first calculated for the probe responses within each subject. Next, a common wavelet entropy (WE) measure and an improved one were used to quantify complexity from each five-trial average. The results show that for both measures, the WE values in the guilty subjects are statistically lower than those in the innocent subjects for most of the 14 electrodes. More importantly, using the improved measure, the difference in WE between the two groups of subjects significantly increases for 11 brain regions compared with the values from the common measure. Finally, the highest balanced classification accuracy, 89.64%, is achieved when using the combined WE feature vector in five brain regions from the sites of Pz, P3, C4, Cz, and C3. Our findings indicate that the lying task elicits a more ordered brain activity in some specific brain regions than the task of telling the truth. This study not only demonstrates that improved WE measurements could be a powerful quantitative index for detecting lying but also sheds light on the brain mechanisms underlying deceptive behaviors.

MIDAS: Regionally linear multivariate discriminative statistical mapping

Statistical parametric maps formed via voxel-wise mass-univariate tests, such as the general linear model, are commonly used to test hypotheses about regionally specific effects in neuroimaging cross-sectional studies where each subject is represented by a single image. Despite being informative, these techniques remain limited as they ignore multivariate relationships in the data. Most importantly, the commonly employed local Gaussian smoothing, which is important for accounting for registration errors and making the data follow Gaussian distributions, is usually chosen in an ad hoc fashion. Thus, it is often suboptimal for the task of detecting group differences and correlations with non-imaging variables. Information mapping techniques, such as searchlight, which use pattern classifiers to exploit multivariate information and obtain more powerful statistical maps, have become increasingly popular in recent years. However, existing methods may lead to important interpretation errors in practice (i.e., misidentifying a cluster as informative, or failing to detect truly informative voxels), while often being computationally expensive. To address these issues, we introduce a novel efficient multivariate statistical framework for cross-sectional studies, termed MIDAS, seeking highly sensitive and specific voxel-wise brain maps, while leveraging the power of regional discriminant analysis. In MIDAS, locally linear discriminative learning is applied to estimate the pattern that best discriminates between two groups, or predicts a variable of interest. This pattern is equivalent to local filtering by an optimal kernel whose coefficients are the weights of the linear discriminant. By composing information from all neighborhoods that contain a given voxel, MIDAS produces a statistic that collectively reflects the contribution of the voxel to the regional classifiers as well as the discriminative power of the classifiers. Critically, MIDAS efficiently assesses the statistical significance of the derived statistic by analytically approximating its null distribution without the need for computationally expensive permutation tests. The proposed framework was extensively validated using simulated atrophy in structural magnetic resonance imaging (MRI) and further tested using data from a task-based functional MRI study as well as a structural MRI study of cognitive performance. The performance of the proposed framework was evaluated against standard voxel-wise general linear models and other information mapping methods. The experimental results showed that MIDAS achieves relatively higher sensitivity and specificity in detecting group differences. Together, our results demonstrate the potential of the proposed approach to efficiently map effects of interest in both structural and functional data.

An Optimized Framework for Cancer Prediction Using Immunosignature

Background:

Cancer is a complex disease which can engages the immune system of the patient. In this regard, determination of distinct immunosignatures for various cancers has received increasing interest recently. However, prediction accuracy and reproducibility of the computational methods are limited. In this article, we introduce a robust method for predicting eight types of cancers including astrocytoma, breast cancer, multiple myeloma, lung cancer, oligodendroglia, ovarian cancer, advanced pancreatic cancer, and Ewing sarcoma.

Methods:

In the proposed scheme, at first, the database is normalized with a dictionary of normalization methods that are combined with particle swarm optimization (PSO) for selecting the best normalization method for each feature. Then, statistical feature selection methods are used to separate discriminative features and they were further improved by PSO with appropriate weights as the inputs of the classification system. Finally, the support vector machines, decision tree, and multilayer perceptron neural network were used as classifiers.

Results:

The performance of the hybrid predictor was assessed using the holdout method. According to this method, the minimum sensitivity, specificity, precision, and accuracy of the proposed algorithm were 92.4 ± 1.1, 99.1 ± 1.1, 90.6 ± 2.1, and 98.3 ± 1.0, respectively, among the three types of classification that are used in our algorithm.

Conclusion:

The proposed algorithm considers all the circumstances and works with each feature in its special way. Thus, the proposed algorithm can be used as a promising framework for cancer prediction with immunosignature.

Integrating Brain Science and Law: Neuroscientific Evidence and Legal Perspectives on Protecting Individual Liberties

Advances in neuroscientific techniques have found increasingly broader applications, including in legal neuroscience (or “neurolaw”), where experts in the brain sciences are called to testify in the courtroom. But does the incursion of neuroscience into the legal sphere constitute a threat to individual liberties? And what legal protections are there against such threats? In this paper, we outline individual rights as they interact with neuroscientific methods. We then proceed to examine the current uses of neuroscientific evidence, and ultimately determine whether the rights of the individual are endangered by such approaches. Based on our analysis, we conclude that while federal evidence rules constitute a substantial hurdle for the use of neuroscientific evidence, more ethical safeguards are needed to protect against future violations of fundamental rights. Finally, we assert that it will be increasingly imperative for the legal and neuroscientific communities to work together to better define the limits, capabilities, and intended direction of neuroscientific methods applicable for use in law.

Neural correlates of deception: lying about past events and personal beliefs

Although a growing body of literature suggests that cognitive control processes are involved in deception, much about the neural correlates of lying remains unknown. In this study, we tested whether brain activation associated with deception, as measured by functional magnetic resonance imaging (fMRI), can be detected either in preparation for or during the execution of a lie, and whether they depend on the content of the lie. We scanned participants while they lied or told the truth about either their personal experiences (episodic memories) or personal beliefs. Regions in the frontal and parietal cortex showed higher activation when participants lied compared with when they were telling the truth, regardless of whether they were asked about their past experiences or opinions. In contrast, lie-related activation in the right temporal pole, precuneus and the right amygdala differed by the content of the lie. Preparing to lie activated parietal and frontal brain regions that were distinct from those activated while participants executed lies. Our findings concur with previous reports on the involvement of frontal and parietal regions in deception, but specify brain regions involved in the preparation vs execution of deception, and those involved in deceiving about experiences vs opinions.

Addressing Confounding in Predictive Models with an Application to Neuroimaging

Understanding structural changes in the brain that are caused by a particular disease is a major goal of neuroimaging research. Multivariate pattern analysis (MVPA) comprises a collection of tools that can be used to understand complex disease efxcfects across the brain. We discuss several important issues that must be considered when analyzing data from neuroimaging studies using MVPA. In particular, we focus on the consequences of confounding by non-imaging variables such as age and sex on the results of MVPA. After reviewing current practice to address confounding in neuroimaging studies, we propose an alternative approach based on inverse probability weighting. Although the proposed method is motivated by neuroimaging applications, it is broadly applicable to many problems in machine learning and predictive modeling. We demonstrate the advantages of our approach on simulated and real data examples.

Recursive feature elimination for biomarker discovery in resting-state functional connectivity

Biomarker discovery involves finding correlations between features and clinical symptoms to aid clinical decision. This task is especially difficult in resting state functional magnetic resonance imaging (rs-fMRI) data due to low SNR, high-dimensionality of images, inter-subject and intra-subject variability and small numbers of subjects compared to the number of derived features. Traditional univariate analysis suffers from the problem of multiple comparisons. Here, we adopt an alternative data-driven method for identifying population differences in functional connectivity. We propose a machine-learning approach to down-select functional connectivity features associated with symptom severity in mild traumatic brain injury (mTBI). Using this approach, we identified functional regions with altered connectivity in mTBI. including the executive control, visual and precuneus networks. We compared functional connections at multiple resolutions to determine which scale would be more sensitive to changes related to patient recovery. These modular network-level features can be used as diagnostic tools for predicting disease severity and recovery profiles.

Clinically useful brain imaging for neuropsychiatry: How can we get there?

Despite decades of research, visions of transforming neuropsychiatry through the development of brain imaging-based "growth charts" or "lab tests" have remained out of reach. In recent years, there is renewed enthusiasm about the prospect of achieving clinically useful tools capable of aiding the diagnosis and management of neuropsychiatric disorders. The present work explores the basis for this enthusiasm. We assert that there is no single advance that currently has the potential to drive the field of clinical brain imaging forward. Instead, there has been a constellation of advances that, if combined, could lead to the identification of objective brain imaging-based markers of illness. In particular, we focus on advances that are helping to (1) elucidate the research agenda for biological psychiatry (e.g., neuroscience focus, precision medicine), (2) shift research models for clinical brain imaging (e.g., big data exploration, standardization), (3) break down research silos (e.g., open science, calls for reproducibility and transparency), and (4) improve imaging technologies and methods. Although an arduous road remains ahead, these advances are repositioning the brain imaging community for long-term success.