Computational neuroimaging strategies for single patient predictions

Bayesian Workflow for Generative Modeling in Computational Psychiatry

Computational (generative) modelling of behaviour has considerable potential for clinical applications. In order to unlock the potential of generative models, reliable statistical inference is crucial. For this, Bayesian workflow has been suggested which, however, has rarely been applied in Translational Neuromodeling and Computational Psychiatry (TN/CP) so far. Here, we present a worked example of Bayesian workflow in the context of a typical application scenario for TN/CP. This application example uses Hierarchical Gaussian Filter (HGF) models, a family of computational models for hierarchical Bayesian belief updating. When equipped with a suitable response model, HGF models can be fit to behavioural data from cognitive tasks; these data frequently consist of binary responses and are typically univariate. This poses challenges for statistical inference due to the limited information contained in such data. We present a novel set of response models that allow for simultaneous inference from multivariate (here: two) behavioural data types. Using both simulations and empirical data from a speed-incentivised associative reward learning (SPIRL) task, we show that models harnessing information from two different data streams (binary responses and continuous response times) ensure robust inference (specifically, identifiability of parameters and models). Moreover, we find a linear relationship between log-transformed response times in the SPIRL task and participants' uncertainty about the outcome. Our analysis illustrates the benefits of Bayesian workflow for a typical use case in TN/CP. We argue that adopting Bayesian workflow for generative modelling helps increase the transparency and robustness of results, which in turn is of fundamental importance for the long-term success of TN/CP.

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis

Functional connectivity (FC), derived from resting-state functional magnetic resonance imaging (rs-fMRI), has been widely used to characterize brain abnormalities in disorders. FC is usually defined as a correlation matrix that is a symmetric positive definite (SPD) matrix lying on the Riemannian manifold. Recently, a number of learning-based methods have been proposed for FC analysis, while the geometric properties of Riemannian manifold have not yet been fully explored in previous studies. Also, most existing methods are designed to target one imaging site of fMRI data, which may result in limited training data for learning reliable and robust models. In this paper, we propose a novel Riemannian Manifold-based Disentangled Representation Learning (RM-DRL) framework which is capable of learning invariant representations from fMRI data across multiple sites for brain disorder diagnosis. In RM-DRL, we first employ an SPD-based encoder module to learn a latent unified representation of FC from different sites, which can preserve the Riemannian geometry of the SPD matrices. In latent space, a disentangled representation module is then designed to split the learned features into domain-specific and domain-invariant parts, respectively. Finally, a decoder module is introduced to ensure that sufficient information can be preserved during disentanglement learning. These designs allow us to introduce four types of training objectives to improve the disentanglement learning. Our RM-DRL method is evaluated on the public multi-site ABIDE dataset, showing superior performance compared with several state-of-the-art methods.

Predicting individual traits from models of brain dynamics accurately and reliably using the Fisher kernel

Predicting an individual's cognitive traits or clinical condition using brain signals is a central goal in modern neuroscience. This is commonly done using either structural aspects, such as structural connectivity or cortical thickness, or aggregated measures of brain activity that average over time. But these approaches are missing a central aspect of brain function: the unique ways in which an individual's brain activity unfolds over time. One reason why these dynamic patterns are not usually considered is that they have to be described by complex, high-dimensional models; and it is unclear how best to use these models for prediction. We here propose an approach that describes dynamic functional connectivity and amplitude patterns using a Hidden Markov model (HMM) and combines it with the Fisher kernel, which can be used to predict individual traits. The Fisher kernel is constructed from the HMM in a mathematically principled manner, thereby preserving the structure of the underlying model. We show here, in fMRI data, that the HMM-Fisher kernel approach is accurate and reliable. We compare the Fisher kernel to other prediction methods, both time-varying and time-averaged functional connectivity-based models. Our approach leverages information about an individual's time-varying amplitude and functional connectivity for prediction and has broad applications in cognitive neuroscience and personalised medicine.

Revisiting the role of computational neuroimaging in the era of integrative neuroscience

Computational models have become integral to human neuroimaging research, providing both mechanistic insights and predictive tools for human cognition and behavior. However, concerns persist regarding the ecological validity of lab-based neuroimaging studies and whether their spatiotemporal resolution is not sufficient for capturing neural dynamics. This review aims to re-examine the utility of computational neuroimaging, particularly in light of the growing prominence of alternative neuroscientific methods and the growing emphasis on more naturalistic behaviors and paradigms. Specifically, we will explore how computational modeling can both enhance the analysis of high-dimensional imaging datasets and, conversely, how neuroimaging, in conjunction with other data modalities, can inform computational models through the lens of neurobiological plausibility. Collectively, this evidence suggests that neuroimaging remains critical for human neuroscience research, and when enhanced by computational models, imaging can serve an important role in bridging levels of analysis and understanding. We conclude by proposing key directions for future research, emphasizing the development of standardized paradigms and the integrative use of computational modeling across neuroimaging techniques.

Neuroimaging Biomarkers for Drug Discovery and Development in Schizophrenia

Schizophrenia is a chronic mental illness that affects up to 1% of the population. While efficacious therapies are available for positive symptoms, effective treatment of cognitive and negative symptoms remains an unmet need after decades of research. New developments in the field of neuroimaging are accelerating our knowledge gain regarding the underlying pathophysiology of symptoms in schizophrenia and psychosis spectrum disorders, inspiring new targets for drug development. However, no validated and qualified biomarkers are currently available to support the development of new therapeutics. This review summarizes the current use of neuroimaging technology in clinical drug development for psychotic disorders. As exemplified by drug development programs that target NMDA receptor hypofunction, neuroimaging results play a critical role in target discovery and establishing target engagement and dose selection. Furthermore, pharmacological neuroimaging may provide response biomarkers that allow for early decision making in proof-of-concept studies that leverage pharmacological challenge models in healthy volunteers. That said, while response and predictive biomarkers are starting to be evaluated in patient populations, they continue to play a limited role. Novel approaches to neuroimaging data acquisition and analysis may aid the establishment of biomarkers that are predictive at the individual level in the future. Nevertheless, various gaps in knowledge need to be addressed and biomarkers need to be validated to establish them as "fit for purpose" in drug development.

Test-retest reliability of reinforcement learning parameters

It has recently been suggested that parameter estimates of computational models can be used to understand individual differences at the process level. One area of research in which this approach, called computational phenotyping, has taken hold is computational psychiatry. One requirement for successful computational phenotyping is that behavior and parameters are stable over time. Surprisingly, the test-retest reliability of behavior and model parameters remains unknown for most experimental tasks and models. The present study seeks to close this gap by investigating the test-retest reliability of canonical reinforcement learning models in the context of two often-used learning paradigms: a two-armed bandit and a reversal learning task. We tested independent cohorts for the two tasks (N = 69 and N = 47) via an online testing platform with a between-test interval of five weeks. Whereas reliability was high for personality and cognitive measures (with ICCs ranging from .67 to .93), it was generally poor for the parameter estimates of the reinforcement learning models (with ICCs ranging from .02 to .52 for the bandit task and from .01 to .71 for the reversal learning task). Given that simulations indicated that our procedures could detect high test-retest reliability, this suggests that a significant proportion of the variability must be ascribed to the participants themselves. In support of that hypothesis, we show that mood (stress and happiness) can partly explain within-participant variability. Taken together, these results are critical for current practices in computational phenotyping and suggest that individual variability should be taken into account in the future development of the field.

Recent Progress in Brain Network Models for Medical Applications: A Review

Importance: Pathological perturbations of the brain often spread via connectome to fundamentally alter functional consequences. By integrating multimodal neuroimaging data with mathematical neural mass modeling, brain network models (BNMs) enable to quantitatively characterize aberrant network dynamics underlying multiple neurological and psychiatric disorders. We delved into the advancements of BNM-based medical applications, discussed the prevalent challenges within this field, and provided possible solutions and future directions. Highlights: This paper reviewed the theoretical foundations and current medical applications of computational BNMs. Composed of neural mass models, the BNM framework allows to investigate large-scale brain dynamics behind brain diseases by linking the simulated functional signals to the empirical neurophysiological data, and has shown promise in exploring neuropathological mechanisms, elucidating therapeutic effects, and predicting disease outcome. Despite that several limitations existed, one promising trend of this research field is to precisely guide clinical neuromodulation treatment based on individual BNM simulation. Conclusion: BNM carries the potential to help understand the mechanism underlying how neuropathology affects brain network dynamics, further contributing to decision-making in clinical diagnosis and treatment. Several constraints must be addressed and surmounted to pave the way for its utilization in the clinic.

Active reinforcement learning versus action bias and hysteresis: control with a mixture of experts and nonexperts

Active reinforcement learning enables dynamic prediction and control, where one should not only maximize rewards but also minimize costs such as of inference, decisions, actions, and time. For an embodied agent such as a human, decisions are also shaped by physical aspects of actions. Beyond the effects of reward outcomes on learning processes, to what extent can modeling of behavior in a reinforcement-learning task be complicated by other sources of variance in sequential action choices? What of the effects of action bias (for actions per se) and action hysteresis determined by the history of actions chosen previously? The present study addressed these questions with incremental assembly of models for the sequential choice data from a task with hierarchical structure for additional complexity in learning. With systematic comparison and falsification of computational models, human choices were tested for signatures of parallel modules representing not only an enhanced form of generalized reinforcement learning but also action bias and hysteresis. We found evidence for substantial differences in bias and hysteresis across participants-even comparable in magnitude to the individual differences in learning. Individuals who did not learn well revealed the greatest biases, but those who did learn accurately were also significantly biased. The direction of hysteresis varied among individuals as repetition or, more commonly, alternation biases persisting from multiple previous actions. Considering that these actions were button presses with trivial motor demands, the idiosyncratic forces biasing sequences of action choices were robust enough to suggest ubiquity across individuals and across tasks requiring various actions. In light of how bias and hysteresis function as a heuristic for efficient control that adapts to uncertainty or low motivation by minimizing the cost of effort, these phenomena broaden the consilient theory of a mixture of experts to encompass a mixture of expert and nonexpert controllers of behavior.

White matter predictors of PTSD: Testing different machine learning models in a sample of Black American women

BACKGROUND

Machine learning neuroimaging studies of posttraumatic stress disorder (PTSD) show promise for identifying neurobiological signatures of PTSD. However, studies to date, have largely evaluated a single machine learning approach, and few studies have examined white matter microstructure as a predictor of PTSD. Further, individuals from minoritized racial groups, specifically, Black individuals, who experience disproportionate trauma frequency, and have relatively higher rates of PTSD, have been underrepresented in these studies. We used four different machine learning models to test white matter microstructure classifiers of PTSD in a sample of trauma-exposed Black American women with and without PTSD.

METHOD

Participants included 45 Black women with PTSD and 89 trauma-exposed controls recruited from an ongoing trauma study. Current PTSD presence was estimated using the Clinician-Administered PTSD Scale. Average fractional anisotropy of 53 white matter tracts served as input features. Additional exploratory analysis incorporated estimates of interpersonal and structural racism exposure. Classification models included linear support vector machine, radial basis function support vector machine, multilayer perceptron, and random forest.

RESULTS

Performance varied notably between models. With white matter features along, linear support vector machine demonstrated the best model fit and reached an average AUC = 0.643. Inclusion of estimates of exposure to racism increased linear support vector machine performance (AUC = 0.808).

CONCLUSIONS

White matter microstructure had limited ability to predict PTSD presence in this sample. These results may indicate that the relationship between white matter microstructure and PTSD may be nuanced across race and gender spectrums.

Perspective of artificial intelligence in healthcare data management: A journey towards precision medicine

Mounting evidence has highlighted the implementation of big data handling and management in the healthcare industry to improve the clinical services. Various private and public companies have generated, stored, and analyzed different types of big healthcare data, such as omics data, clinical data, electronic health records, personal health records, and sensing data with the aim to move in the direction of precision medicine. Additionally, with the advancement in technologies, researchers are curious to extract the potential involvement of artificial intelligence and machine learning on big healthcare data to enhance the quality of patient's lives. However, seeking solutions from big healthcare data requires proper management, storage, and analysis, which imposes hinderances associated with big data handling. Herein, we briefly discuss the implication of big data handling and the role of artificial intelligence in precision medicine. Further, we also highlighted the potential of artificial intelligence in integrating and analyzing the big data that offer personalized treatment. In addition, we briefly discuss the applications of artificial intelligence in personalized treatment, especially in neurological diseases. Lastly, we discuss the challenges and limitations imposed by artificial intelligence in big data management and analysis to hinder precision medicine.

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Suicide prevention and ketamine: insights from computational modeling

Suicide is a pressing public health issue, with over 700,000 individuals dying each year. Ketamine has emerged as a promising treatment for suicidal thoughts and behaviors (STBs), yet the complex mechanisms underlying ketamine's anti-suicidal effect are not fully understood. Computational psychiatry provides a promising framework for exploring the dynamic interactions underlying suicidality and ketamine's therapeutic action, offering insight into potential biomarkers, treatment targets, and the underlying mechanisms of both. This paper provides an overview of current computational theories of suicidality and ketamine's mechanism of action, and discusses various computational modeling approaches that attempt to explain ketamine's anti-suicidal effect. More specifically, the therapeutic potential of ketamine is explored in the context of the mismatch negativity and the predictive coding framework, by considering neurocircuits involved in learning and decision-making, and investigating altered connectivity strengths and receptor densities targeted by ketamine. Theory-driven computational models offer a promising approach to integrate existing knowledge of suicidality and ketamine, and for the extraction of model-derived mechanistic parameters that can be used to identify patient subgroups and personalized treatment approaches. Future computational studies on ketamine's mechanism of action should optimize task design and modeling approaches to ensure parameter reliability, and external factors such as set and setting, as well as psychedelic-assisted therapy should be evaluated for their additional therapeutic value.

Adaptive data-driven selection of sequences of biological and cognitive markers in pre-clinical diagnosis of dementia

Effective clinical decision procedures must balance multiple competing objectives such as time-to-decision, acquisition costs, and accuracy. We describe and evaluate POSEIDON, a data-driven method for PrOspective SEquentIal DiagnOsis with Neutral zones to individualize clinical classifications. We evaluated the framework with an application in which the algorithm sequentially proposes to include cognitive, imaging, or molecular markers if a sufficiently more accurate prognosis of clinical decline to manifest Alzheimer's disease is expected. Over a wide range of cost parameter data-driven tuning lead to quantitatively lower total cost compared to ad hoc fixed sets of measurements. The classification accuracy based on all longitudinal data from participants that was acquired over 4.8 years on average was 0.89. The sequential algorithm selected 14 percent of available measurements and concluded after an average follow-up time of 0.74 years at the expense of 0.05 lower accuracy. Sequential classifiers were competitive from a multi-objective perspective since they could dominate fixed sets of measurements by making fewer errors using less resources. Nevertheless, the trade-off of competing objectives depends on inherently subjective prescribed cost parameters. Thus, despite the effectiveness of the method, the implementation into consequential clinical applications will remain controversial and evolve around the choice of cost parameters.

Predicting Future Depressive Episodes from Resting-State fMRI with Generative Embedding

After a first episode of major depressive disorder (MDD), there is substantial risk for a long-term remitting-relapsing course. Prevention and early interventions are thus critically important. Various studies have examined the feasibility of detecting at-risk individuals based on out-of-sample predictions about the future occurrence of depression. However, functional magnetic resonance imaging (MRI) has received very little attention for this purpose so far. Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N=906) of task-free ("resting state") fMRI data from the UK Biobank. Connectivity analyses were conducted using timeseries from pre-computed spatially independent components of different dimensionalities. Over a three year period, 50% of participants showed indications of at least one depressive episode, while the other 50% did not. Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers. We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best predictions, both on the training set (0.63 accuracy, 0.66 area under the curve, AUC) and the test set (0.62 accuracy, 0.64 AUC; p<0.001). However, on the test set, rDCM was only slightly superior to predictions based on FC (0.59 accuracy, 0.61 AUC). Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks. Overall, our analyses suggest (i) ways of improving future fMRI-based generative embedding approaches for the early detection of individuals at-risk for depression and that (ii) achieving accuracies of clinical utility may require combination of fMRI with other data modalities.

Individual differences in computational psychiatry: a review of current challenges

Bringing precision to the understanding and treatment of mental disorders requires instruments for studying clinically relevant individual differences. One promising approach is the development of computational assays: integrating computational models with cognitive tasks to infer latent patient-specific disease processes in brain computations. While recent years have seen many methodological advancements in computational modelling and many cross-sectional patient studies, much less attention has been paid to basic psychometric properties (reliability and construct validity) of the computational measures provided by the assays. In this review, we assess the extent of this issue by examining emerging empirical evidence. We find that many computational measures suffer from poor psychometric properties, which poses a risk of invalidating previous findings and undermining ongoing research efforts using computational assays to study individual (and even group) differences. We provide recommendations for how to address these problems and, crucially, embed them within a broader perspective on key developments that are needed for translating computational assays to clinical practice.

The challenging quest of neuroimaging: From clinical to molecular-based subtyping of Parkinson disease and atypical parkinsonisms

The current framework of Parkinson disease (PD) focuses on phenotypic classification despite its considerable heterogeneity. We argue that this method of classification has restricted therapeutic advances and therefore limited our ability to develop disease-modifying interventions in PD. Advances in neuroimaging have identified several molecular mechanisms relevant to PD, variation within and between clinical phenotypes, and potential compensatory mechanisms with disease progression. Magnetic resonance imaging (MRI) techniques can detect microstructural changes, disruptions in neural pathways, and metabolic and blood flow alterations. Positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging have informed the neurotransmitter, metabolic, and inflammatory dysfunctions that could potentially distinguish disease phenotypes and predict response to therapy and clinical outcomes. However, rapid advancements in imaging techniques make it challenging to assess the significance of newer studies in the context of new theoretical frameworks. As such, there needs to not only be a standardization of practice criteria in molecular imaging but also a rethinking of target approaches. In order to harness precision medicine, a coordinated shift is needed toward divergent rather than convergent diagnostic approaches that account for interindividual differences rather than similarities within an affected population, and focus on predictive patterns rather than already lost neural activity.

IABC: A Toolbox for Intelligent Analysis of Brain Connectivity

Brain functional networks and connectivity have played an important role in exploring brain function for understanding the brain and disclosing the mechanisms of brain disorders. Independent component analysis (ICA) is one of the most widely applied data-driven methods to extract brain functional networks/connectivity. However, it is hard to guarantee the reliability of networks/connectivity due to the randomness of component order and the difficulty in selecting an optimal component number in ICA. To facilitate the analysis of brain functional networks and connectivity using ICA, we developed a MATLAB toolbox called Intelligent Analysis of Brain Connectivity (IABC). IABC incorporates our previously proposed group information guided independent component analysis (GIG-ICA), NeuroMark, and splitting-merging assisted reliable ICA (SMART ICA) methods, which can estimate reliable individual-subject neuroimaging measures for further analysis. After user inputs functional magnetic resonance imaging (fMRI) data of multiple subjects that are regularly organized (e.g., in Brain Imaging Data Structure (BIDS)) and clicks a few buttons to set parameters, IABC automatically outputs brain functional networks, their related time courses, and functional network connectivity of each subject. All these neuroimaging measures are promising for providing clues in understanding brain function and differentiating brain disorders.

From promise to practice: towards the realisation of AI-informed mental health care

In this Series paper, we explore the promises and challenges of artificial intelligence (AI)-based precision medicine tools in mental health care from clinical, ethical, and regulatory perspectives. The real-world implementation of these tools is increasingly considered the prime solution for key issues in mental health, such as delayed, inaccurate, and inefficient care delivery. Similarly, machine-learning-based empirical strategies are becoming commonplace in psychiatric research because of their potential to adequately deconstruct the biopsychosocial complexity of mental health disorders, and hence to improve nosology of prognostic and preventive paradigms. However, the implementation steps needed to translate these promises into practice are currently hampered by multiple interacting challenges. These obstructions range from the current technology-distant state of clinical practice, over the lack of valid real-world databases required to feed data-intensive AI algorithms, to model development and validation considerations being disconnected from the core principles of clinical utility and ethical acceptability. In this Series paper, we provide recommendations on how these challenges could be addressed from an interdisciplinary perspective to pave the way towards a framework for mental health care, leveraging the combined strengths of human intelligence and AI.

Computational approaches to treatment response prediction in major depression using brain activity and behavioral data: A systematic review

Major depressive disorder is a heterogeneous diagnostic category with multiple available treatments. With the goal of optimizing treatment selection, researchers are developing computational models that attempt to predict treatment response based on various pretreatment measures. In this paper, we review studies that use brain activity data to predict treatment response. Our aim is to highlight and clarify important methodological differences between various studies that relate to the incorporation of domain knowledge, specifically within two approaches delineated as data-driven and theory-driven. We argue that theory-driven generative modeling, which explicitly models information processing in the brain and thus can capture disease mechanisms, is a promising emerging approach that is only beginning to be utilized in treatment response prediction. The predictors extracted via such models could improve interpretability, which is critical for clinical decision-making. We also identify several methodological limitations across the reviewed studies and provide suggestions for addressing them. Namely, we consider problems with dichotomizing treatment outcomes, the importance of investigating more than one treatment in a given study for differential treatment response predictions, the need for a patient-centered approach for defining treatment outcomes, and finally, the use of internal and external validation methods for improving model generalizability.

Four-Class Classification of Neuropsychiatric Disorders by Use of Functional Near-Infrared Spectroscopy Derived Biomarkers

Diagnosis of most neuropsychiatric disorders relies on subjective measures, which makes the reliability of final clinical decisions questionable. The aim of this study was to propose a machine learning-based classification approach for objective diagnosis of three disorders of neuropsychiatric or neurological origin with functional near-infrared spectroscopy (fNIRS) derived biomarkers. Thirteen healthy adolescents and sixty-seven patients who were clinically diagnosed with migraine, obsessive compulsive disorder, or schizophrenia performed a Stroop task, while prefrontal cortex hemodynamics were monitored with fNIRS. Hemodynamic and cognitive features were extracted for training three supervised learning algorithms (naïve bayes (NB), linear discriminant analysis (LDA), and support vector machines (SVM)). The performance of each algorithm in correctly predicting the class of each participant across the four classes was tested with ten runs of a ten-fold cross-validation procedure. All algorithms achieved four-class classification performances with accuracies above 81% and specificities above 94%. SVM had the highest performance in terms of accuracy (85.1 ± 1.77%), sensitivity (84 ± 1.7%), specificity (95 ± 0.5%), precision (86 ± 1.6%), and F1-score (85 ± 1.7%). fNIRS-derived features have no subjective report bias when used for automated classification purposes. The presented methodology might have significant potential for assisting in the objective diagnosis of neuropsychiatric disorders associated with frontal lobe dysfunction.

Auditory mismatch responses are differentially sensitive to changes in muscarinic acetylcholine versus dopamine receptor function

The auditory mismatch negativity (MMN) has been proposed as a biomarker of NMDA receptor (NMDAR) dysfunction in schizophrenia. Such dysfunction may be caused by aberrant interactions of different neuromodulators with NMDARs, which could explain clinical heterogeneity among patients. In two studies (N = 81 each), we used a double-blind placebo-controlled between-subject design to systematically test whether auditory mismatch responses under varying levels of environmental stability are sensitive to diminishing and enhancing cholinergic vs. dopaminergic function. We found a significant drug × mismatch interaction: while the muscarinic acetylcholine receptor antagonist biperiden delayed and topographically shifted mismatch responses, particularly during high stability, this effect could not be detected for amisulpride, a dopamine D2/D3 receptor antagonist. Neither galantamine nor levodopa, which elevate acetylcholine and dopamine levels, respectively, exerted significant effects on MMN. This differential MMN sensitivity to muscarinic versus dopaminergic receptor function may prove useful for developing tests that predict individual treatment responses in schizophrenia.

Changes in Brain Functional and Effective Connectivity After Treatment for Breast Cancer and Implications for Intervention Targets

Background: Patients with breast cancer frequently report cognitive impairment both during and after completion of therapy. Evidence suggests that cancer-related cognitive impairments are related to widespread neural network dysfunction. The default mode network (DMN) is a large conserved network that plays a critical role in integrating the functions of various neural systems. Disruption of the network may play a key role in the development of cognitive impairment. Methods: We compared neuroimaging and neurocognitive data from 43 newly diagnosed primary breast cancer patients (mean age = 48, standard deviation [SD] = 8.9 years) and 50 frequency-matched healthy female controls (mean age = 50, SD = 10 years) before treatment and 1 year after treatment completion. Functional and effective connectivity measures of the DMN were obtained using graph theory and Bayesian network analysis methods, respectively. Results: Compared with healthy females, the breast cancer group displayed higher global efficiency and path length post-treatment (p < 0.03, corrected). Breast cancer survivors showed significantly lower performance on measures of verbal memory, attention, and verbal fluency (p < 0.05) at both time points. Within the DMN, local brain network organization, as measured by edge-betweenness centralities, was significantly altered in the breast cancer group compared with controls at both time points (p < 0.0001, corrected), with several connections showing a significant group-by-time effect (p < 0.003, corrected). Effective connectivity demonstrated significantly altered patterns of neuronal coupling in patients with breast cancer (p < 0.05). Significant correlations were seen between hormone blockade therapy, radiation therapy, chemotherapy cycles, memory, and verbal fluency test and edge-betweenness centralities. Discussion: This pattern of altered network organization in the default mode is believed to result in reduced network efficiency and disrupted communication. Subregions of the DMN, the orbital prefrontal cortex and posterior memory network, appear to be at the center of this disruption and this could inform future interventions. Impact statement This prospective study is the first to investigate how post-treatment changes in functional and effective connectivity in the regions of default mode network are related to cancer therapy and measures of memory and verbal learning in breast cancer patients. We demonstrate that the interactions between treatment, brain connectivity, and neurocognitive outcomes coalesce around a subgroup of brain structures in the orbital frontal and parietal lobe. This would suggest that interventions that target these regions may improve neurocognitive outcomes in breast cancer survivors.

AI ethics in computational psychiatry: From the neuroscience of consciousness to the ethics of consciousness

Methods used in artificial intelligence (AI) overlap with methods used in computational psychiatry (CP). Hence, considerations from AI ethics are also relevant to ethical discussions of CP. Ethical issues include, among others, fairness and data ownership and protection. Apart from this, morally relevant issues also include potential transformative effects of applications of AI-for instance, with respect to how we conceive of autonomy and privacy. Similarly, successful applications of CP may have transformative effects on how we categorise and classify mental disorders and mental health. Since many mental disorders go along with disturbed conscious experiences, it is desirable that successful applications of CP improve our understanding of disorders involving disruptions in conscious experience. Here, we discuss prospects and pitfalls of transformative effects that CP may have on our understanding of mental disorders. In particular, we examine the concern that even successful applications of CP may fail to take all aspects of disordered conscious experiences into account.

An introduction to thermodynamic integration and application to dynamic causal models

In generative modeling of neuroimaging data, such as dynamic causal modeling (DCM), one typically considers several alternative models, either to determine the most plausible explanation for observed data (Bayesian model selection) or to account for model uncertainty (Bayesian model averaging). Both procedures rest on estimates of the model evidence, a principled trade-off between model accuracy and complexity. In the context of DCM, the log evidence is usually approximated using variational Bayes. Although this approach is highly efficient, it makes distributional assumptions and is vulnerable to local extrema. This paper introduces the use of thermodynamic integration (TI) for Bayesian model selection and averaging in the context of DCM. TI is based on Markov chain Monte Carlo sampling which is asymptotically exact but orders of magnitude slower than variational Bayes. In this paper, we explain the theoretical foundations of TI, covering key concepts such as the free energy and its origins in statistical physics. Our aim is to convey an in-depth understanding of the method starting from its historical origin in statistical physics. In addition, we demonstrate the practical application of TI via a series of examples which serve to guide the user in applying this method. Furthermore, these examples demonstrate that, given an efficient implementation and hardware capable of parallel processing, the challenge of high computational demand can be overcome successfully. The TI implementation presented in this paper is freely available as part of the open source software TAPAS.

Computational Modeling of Electroencephalography and Functional Magnetic Resonance Imaging Paradigms Indicates a Consistent Loss of Pyramidal Cell Synaptic Gain in Schizophrenia

BACKGROUND

Diminished synaptic gain-the sensitivity of postsynaptic responses to neural inputs-may be a fundamental synaptic pathology in schizophrenia. Evidence for this is indirect, however. Furthermore, it is unclear whether pyramidal cells or interneurons (or both) are affected, or how these deficits relate to symptoms.

METHODS

People with schizophrenia diagnoses (PScz) (n = 108), their relatives (n = 57), and control subjects (n = 107) underwent 3 electroencephalography (EEG) paradigms-resting, mismatch negativity, and 40-Hz auditory steady-state response-and resting functional magnetic resonance imaging. Dynamic causal modeling was used to quantify synaptic connectivity in cortical microcircuits.

RESULTS

Classic group differences in EEG features between PScz and control subjects were replicated, including increased theta and other spectral changes (resting EEG), reduced mismatch negativity, and reduced 40-Hz power. Across all 4 paradigms, characteristic PScz data features were all best explained by models with greater self-inhibition (decreased synaptic gain) in pyramidal cells. Furthermore, disinhibition in auditory areas predicted abnormal auditory perception (and positive symptoms) in PScz in 3 paradigms.

CONCLUSIONS

First, characteristic EEG changes in PScz in 3 classic paradigms are all attributable to the same underlying parameter change: greater self-inhibition in pyramidal cells. Second, psychotic symptoms in PScz relate to disinhibition in neural circuits. These findings are more commensurate with the hypothesis that in PScz, a primary loss of synaptic gain on pyramidal cells is then compensated by interneuron downregulation (rather than the converse). They further suggest that psychotic symptoms relate to this secondary downregulation.

Neuronal and Astrocytic Regulations in Schizophrenia: A Computational Modelling Study

According to the tripartite synapse model, astrocytes have a modulatory effect on neuronal signal transmission. More recently, astrocyte malfunction has been associated with psychiatric diseases such as schizophrenia. Several hypotheses have been proposed on the pathological mechanisms of astrocytes in schizophrenia. For example, post-mortem examinations have revealed a reduced astrocytic density in patients with schizophrenia. Another hypothesis suggests that disease symptoms are linked to an abnormality of glutamate transmission, which is also regulated by astrocytes (glutamate hypothesis of schizophrenia). Electrophysiological findings indicate a dispute over whether the disorder causes an increase or a decrease in neuronal and astrocytic activity. Moreover, there is no consensus as to which molecular pathways and network mechanisms are altered in schizophrenia. Computational models can aid the process in finding the underlying pathological malfunctions. The effect of astrocytes on the activity of neuron-astrocyte networks has been analysed with computational models. These can reproduce experimentally observed phenomena, such as astrocytic modulation of spike and burst signalling in neuron-astrocyte networks. Using an established computational neuron-astrocyte network model, we simulate experimental data of healthy and pathological networks by using different neuronal and astrocytic parameter configurations. In our simulations, the reduction of neuronal or astrocytic cell densities yields decreased glutamate levels and a statistically significant reduction in the network activity. Amplifications of the astrocytic ATP release toward postsynaptic terminals also reduced the network activity and resulted in temporarily increased glutamate levels. In contrast, reducing either the glutamate release or re-uptake in astrocytes resulted in higher network activities. Similarly, an increase in synaptic weights of excitatory or inhibitory neurons raises the excitability of individual cells and elevates the activation level of the network. To conclude, our simulations suggest that the impairment of both neurons and astrocytes disturbs the neuronal network activity in schizophrenia.

Predicting subclinical psychotic-like experiences on a continuum using machine learning

Previous studies applying machine learning methods to psychosis have primarily been concerned with the binary classification of chronic schizophrenia patients and healthy controls. The aim of this study was to use electroencephalographic (EEG) data and pattern recognition to predict subclinical psychotic-like experiences on a continuum between these two extremes in otherwise healthy people. We applied two different approaches to an auditory oddball regularity learning task obtained from N = 73 participants: A feature extraction and selection routine incorporating behavioural measures, event-related potential components and effective connectivity parameters; Regularisation of spatiotemporal maps of event-related potentials. Using the latter approach, optimal performance was achieved using the response to frequent, predictable sounds. Features within the P50 and P200 time windows had the greatest contribution toward lower Prodromal Questionnaire (PQ) scores and the N100 time window contributed most to higher PQ scores. As a proof-of-concept, these findings demonstrate that EEG data alone are predictive of individual psychotic-like experiences in healthy people. Our findings are in keeping with the mounting evidence for altered sensory responses in schizophrenia, as well as the notion that psychosis may exist on a continuum expanding into the non-clinical population.

TAPAS: An Open-Source Software Package for Translational Neuromodeling and Computational Psychiatry

Psychiatry faces fundamental challenges with regard to mechanistically guided differential diagnosis, as well as prediction of clinical trajectories and treatment response of individual patients. This has motivated the genesis of two closely intertwined fields: (i) Translational Neuromodeling (TN), which develops "computational assays" for inferring patient-specific disease processes from neuroimaging, electrophysiological, and behavioral data; and (ii) Computational Psychiatry (CP), with the goal of incorporating computational assays into clinical decision making in everyday practice. In order to serve as objective and reliable tools for clinical routine, computational assays require end-to-end pipelines from raw data (input) to clinically useful information (output). While these are yet to be established in clinical practice, individual components of this general end-to-end pipeline are being developed and made openly available for community use. In this paper, we present the Translational Algorithms for Psychiatry-Advancing Science (TAPAS) software package, an open-source collection of building blocks for computational assays in psychiatry. Collectively, the tools in TAPAS presently cover several important aspects of the desired end-to-end pipeline, including: (i) tailored experimental designs and optimization of measurement strategy prior to data acquisition, (ii) quality control during data acquisition, and (iii) artifact correction, statistical inference, and clinical application after data acquisition. Here, we review the different tools within TAPAS and illustrate how these may help provide a deeper understanding of neural and cognitive mechanisms of disease, with the ultimate goal of establishing automatized pipelines for predictions about individual patients. We hope that the openly available tools in TAPAS will contribute to the further development of TN/CP and facilitate the translation of advances in computational neuroscience into clinically relevant computational assays.

Model-based prediction of muscarinic receptor function from auditory mismatch negativity responses

Drugs affecting neuromodulation, for example by dopamine or acetylcholine, take centre stage among therapeutic strategies in psychiatry. These neuromodulators can change both neuronal gain and synaptic plasticity and therefore affect electrophysiological measures. An important goal for clinical diagnostics is to exploit this effect in the reverse direction, i.e., to infer the status of specific neuromodulatory systems from electrophysiological measures. In this study, we provide proof-of-concept that the functional status of cholinergic (specifically muscarinic) receptors can be inferred from electrophysiological data using generative (dynamic causal) models. To this end, we used epidural EEG recordings over two auditory cortical regions during a mismatch negativity (MMN) paradigm in rats. All animals were treated, across sessions, with muscarinic receptor agonists and antagonists at different doses. Together with a placebo condition, this resulted in five levels of muscarinic receptor status. Using a dynamic causal model - embodying a small network of coupled cortical microcircuits - we estimated synaptic parameters and their change across pharmacological conditions. The ensuing parameter estimates associated with (the neuromodulation of) synaptic efficacy showed both graded muscarinic effects and predictive validity between agonistic and antagonistic pharmacological conditions. This finding illustrates the potential utility of generative models of electrophysiological data as computational assays of muscarinic function. In application to EEG data of patients from heterogeneous spectrum diseases, e.g. schizophrenia, such models might help identify subgroups of patients that respond differentially to cholinergic treatments. SIGNIFICANCE STATEMENT: In psychiatry, the vast majority of pharmacological treatments affect actions of neuromodulatory transmitters, e.g. dopamine or acetylcholine. As treatment is largely trial-and-error based, one of the goals for computational psychiatry is to construct mathematical models that can serve as "computational assays" and infer the status of specific neuromodulatory systems in individual patients. This translational neuromodeling strategy has great promise for electrophysiological data in particular but requires careful validation. The present study demonstrates that the functional status of cholinergic (muscarinic) receptors can be inferred from electrophysiological data using dynamic causal models of neural circuits. While accuracy needs to be enhanced and our results must be replicated in larger samples, our current results provide proof-of-concept for computational assays of muscarinic function using EEG.

Computational approaches and machine learning for individual-level treatment predictions

RATIONALE

The impact of neuroscience-based approaches for psychiatry on pragmatic clinical decision-making has been limited. Although neuroscience has provided insights into basic mechanisms of neural function, these insights have not improved the ability to generate better assessments, prognoses, diagnoses, or treatment of psychiatric conditions.

OBJECTIVES

To integrate the emerging findings in machine learning and computational psychiatry to address the question: what measures that are not derived from the patient's self-assessment or the assessment by a trained professional can be used to make more precise predictions about the individual's current state, the individual's future disease trajectory, or the probability to respond to a particular intervention?

RESULTS

Currently, the ability to use individual differences to predict differential outcomes is very modest possibly related to the fact that the effect sizes of interventions are small. There is emerging evidence of genetic and neuroimaging-based heterogeneity of psychiatric disorders, which contributes to imprecise predictions. Although the use of machine learning tools to generate clinically actionable predictions is still in its infancy, these approaches may identify subgroups enabling more precise predictions. In addition, computational psychiatry might provide explanatory disease models based on faulty updating of internal values or beliefs.

CONCLUSIONS

There is a need for larger studies, clinical trials using machine learning, or computational psychiatry model parameters predictions as actionable outcomes, comparing alternative explanatory computational models, and using translational approaches that apply similar paradigms and models in humans and animals.

Psychiatric Neural Networks and Precision Therapeutics by Machine Learning

Learning and environmental adaptation increase the likelihood of survival and improve the quality of life. However, it is often difficult to judge optimal behaviors in real life due to highly complex social dynamics and environment. Consequentially, many different brain regions and neuronal circuits are involved in decision-making. Many neurobiological studies on decision-making show that behaviors are chosen through coordination among multiple neural network systems, each implementing a distinct set of computational algorithms. Although these processes are commonly abnormal in neurological and psychiatric disorders, the underlying causes remain incompletely elucidated. Machine learning approaches with multidimensional data sets have the potential to not only pathologically redefine mental illnesses but also better improve therapeutic outcomes than DSM/ICD diagnoses. Furthermore, measurable endophenotypes could allow for early disease detection, prognosis, and optimal treatment regime for individuals. In this review, decision-making in real life and psychiatric disorders and the applications of machine learning in brain imaging studies on psychiatric disorders are summarized, and considerations for the future clinical translation are outlined. This review also aims to introduce clinicians, scientists, and engineers to the opportunities and challenges in bringing artificial intelligence into psychiatric practice.

Markov chain Monte Carlo methods for hierarchical clustering of dynamic causal models

In this article, we address technical difficulties that arise when applying Markov chain Monte Carlo (MCMC) to hierarchical models designed to perform clustering in the space of latent parameters of subject‐wise generative models. Specifically, we focus on the case where the subject‐wise generative model is a dynamic causal model (DCM) for functional magnetic resonance imaging (fMRI) and clusters are defined in terms of effective brain connectivity. While an attractive approach for detecting mechanistically interpretable subgroups in heterogeneous populations, inverting such a hierarchical model represents a particularly challenging case, since DCM is often characterized by high posterior correlations between its parameters. In this context, standard MCMC schemes exhibit poor performance and extremely slow convergence. In this article, we investigate the properties of hierarchical clustering which lead to the observed failure of standard MCMC schemes and propose a solution designed to improve convergence but preserve computational complexity. Specifically, we introduce a class of proposal distributions which aims to capture the interdependencies between the parameters of the clustering and subject‐wise generative models and helps to reduce random walk behaviour of the MCMC scheme. Critically, these proposal distributions only introduce a single hyperparameter that needs to be tuned to achieve good performance. For validation, we apply our proposed solution to synthetic and real‐world datasets and also compare it, in terms of computational complexity and performance, to Hamiltonian Monte Carlo (HMC), a state‐of‐the‐art Monte Carlo technique. Our results indicate that, for the specific application domain considered here, our proposed solution shows good convergence performance and superior runtime compared to HMC.

[Diagnostics and Therapy 24/7? Artificial Intelligence as a Challenge and Opportunity in Psychiatry and Psychotherapy]

OBJECTIVE

The aim of the article is to enable a fundamental understanding of the potentials and requirements of Artificial Intelligence (AI) for psychiatrists in the present and for the development of future working environments. Psychiatrists will need to understand the function of AI-systems and personalized AI-assistants in therapy systems and as part of their patients' daily life.

METHOD

The article provides an overview of basic categories and fields of application of AI and machine learning in the diagnosis, prevention and therapy of mental disorders.

RESULTS

AI-applications will shape the prevention, diagnosis and treatment as well as the basic etiological understanding of mental disorders. Notably, the treatment of mental disorders is significantly influenced by commercial product development and assistance systems outside the medical system, as the corresponding developments can exploit large data pools with significantly lower restrictions.

CONCLUSION

Psychiatrists should now seize the opportunity to actively shape the implementation of AI-systems as otherwise key competences could be transferred to a primary field outside the medical system to the detriment of the patient and the therapist.

Advances in the computational understanding of mental illness

Computational psychiatry is a rapidly growing field attempting to translate advances in computational neuroscience and machine learning into improved outcomes for patients suffering from mental illness. It encompasses both data-driven and theory-driven efforts. Here, recent advances in theory-driven work are reviewed. We argue that the brain is a computational organ. As such, an understanding of the illnesses arising from it will require a computational framework. The review divides work up into three theoretical approaches that have deep mathematical connections: dynamical systems, Bayesian inference and reinforcement learning. We discuss both general and specific challenges for the field, and suggest ways forward.

Structural and functional imaging markers for susceptibility to psychosis

The introduction of clinical criteria for the operationalization of psychosis high risk provided a basis for early detection and treatment of vulnerable individuals. However, about two-thirds of people meeting clinical high-risk (CHR) criteria will never develop a psychotic disorder. In the effort to increase prognostic precision, structural and functional neuroimaging have received growing attention as a potentially useful resource in the prediction of psychotic transition in CHR patients. The present review summarizes current research on neuroimaging biomarkers in the CHR state, with a particular focus on their prognostic utility and limitations. Large, multimodal/multicenter studies are warranted to address issues important for clinical applicability such as generalizability and replicability, standardization of clinical definitions and neuroimaging methods, and consideration of contextual factors (e.g., age, comorbidity).

A Two Consequent Multi-layers Deep Discriminative Approach for Classifying fMRI Images

Functional Magnetic Resonance Imaging (fMRI), for many decades acts as a potential aiding method for diagnosing medical problems. Several successful machine learning algorithms have been proposed in literature to extract valuable knowledge from fMRI. One of these algorithms is the convolutional neural network (CNN) that competent with high capabilities for learning optimal abstractions of fMRI. This is because the CNN learns features similarly to human brain where it preserves local structure and avoids distortion of the global feature space. Focusing on the achievements of using the CNN for the fMRI, and accordingly, the Deep Convolutional Auto-Encoder (DCAE) benefits from the data-driven approach with CNN’s optimal features to strengthen the fMRI classification. In this paper, a new two consequent multi-layers DCAE deep discriminative approach for classifying fMRI Images is proposed. The first DCAE is unsupervised sub-model that is composed of four CNN. It focuses on learning weights to utilize discriminative characteristics of the extracted features for robust reconstruction of fMRI with lower dimensional considering tiny details and refining by its deep multiple layers. Then the second DCAE is a supervised sub-model that focuses on training labels to reach an outperformed results. The proposed approach proved its effectiveness and improved literately reported results on a large brain disorder fMRI dataset.

Modelling subject variability in the spatial and temporal characteristics of functional modes

Recent work has highlighted the scale and ubiquity of subject variability in observations from functional MRI data (fMRI). Furthermore, it is highly likely that errors in the estimation of either the spatial presentation of, or the coupling between, functional regions can confound cross-subject analyses, making accurate and unbiased representations of functional data essential for interpreting any downstream analyses. Here, we extend the framework of probabilistic functional modes (PFMs) (Harrison et al., 2015) to capture cross-subject variability not only in the mode spatial maps, but also in the functional coupling between modes and in mode amplitudes. A new implementation of the inference now also allows for the analysis of modern, large-scale data sets, and the combined inference and analysis package, PROFUMO, is available from git.fmrib.ox.ac.uk/samh/profumo. A new implementation of the inference now also allows for the analysis of modern, large-scale data sets. Using simulated data, resting-state data from 1000 subjects collected as part of the Human Connectome Project (Van Essen et al., 2013), and an analysis of 14 subjects in a variety of continuous task-states (Kieliba et al., 2019), we demonstrate how PFMs are able to capture, within a single model, a rich description of how the spatio-temporal structure of resting-state fMRI activity varies across subjects. We also compare the new PFM model to the well established independent component analysis with dual regression (ICA-DR) pipeline. This reveals that, under PFM assumptions, much more of the (behaviorally relevant) cross-subject variability in fMRI activity should be attributed to the variability in spatial maps, and that, after accounting for this, functional coupling between modes primarily reflects current cognitive state. This has fundamental implications for the interpretation of cross-sectional studies of functional connectivity that do not capture cross-subject variability to the same extent as PFMs.

Personalizing neuromodulation

In the era of "big data", we are gaining rich person-specific information about neuroanatomy, neural function, and cognitive functions. However, the optimal ways to create precise approaches to optimize individuals' mental functions in health and disease are unclear. Multimodal analysis and modeling approaches can guide neuromodulation by combining anatomical networks, functional signal analysis, and cognitive neuroscience paradigms in single subjects. Our progress could be improved by progressing from statistical fits to mechanistic models. Using transcranial magnetic stimulation as an example, we discuss how integrating methods with a focus on mechanisms could improve our predictions TMS effects within individuals, refine our models of health and disease, and improve our treatments.

Analysis of MRI Data in Diagnostic Neuroradiology

Magnetic resonance imaging (MRI) is a noninvasive imaging tool for neuroradiological diagnosis. Numerous concepts of automated MRI analysis and the use of machine learning have been proposed to assist diagnosis and prognosis. While these academic innovations have proven effective in principle within controlled environments, their application to clinical practice has faced unmet requirements, such as the ability to perform reliably across a heterogeneous population, to work robustly in the presence of comorbidities, and to be invariant to scanner hardware and image quality. The lack of realistic confidence bounds and the inability to handle missing data have also reduced the application of most of these methods outside of academic studies. Mastering the complex challenges in the diagnostic process may help researchers discover novel biological constructs in multimodal data and improve stratification for clinical trials, paving the way for precision medicine. This review presents the state of the art of computerized brain MRI analysis for diagnostic purposes. We critically evaluate the current clinical usefulness of the methods and highlight challenges and future perspectives of the field.

Identifying commonality and specificity across psychosis sub-groups via classification based on features from dynamic connectivity analysis

It is difficult to distinguish schizophrenia (SZ), schizoaffective disorder (SAD), and bipolar disorder with psychosis (BPP) as their clinical diagnoses rely on symptoms that overlap. In this paper, we investigate if there is biological evidence to support the symptom-based clinical categories by looking across the three disorders using dynamic connectivity measures, and provide meaningful characteristics on which brain functional connectivity measures are commonly or uniquely impaired. Large-sample functional magnetic resonance image (fMRI) datasets from 623 subjects including 238 healthy controls (HCs), 113 SZ patients, 132 SAD patients, and 140 BPP patients were analyzed. First, we computed whole-brain dynamic functional connectivity (DFC) using a sliding-window technique, and then extracted the individual connectivity states by applying our previously proposed decomposition-based DFC analysis method. Next, with the features from the dominant connectivity state, we assessed the clinical categories by performing both four-group (SZ, SAD, BPP and healthy control groups) and pair-wise classification using a support vector machine within cross-validation. Furthermore, we comprehensively summarized the shared and unique connectivity alterations among the disorders. In terms of the classification performance, our method achieved 69% in the four-group classification and >80% in the between-group classifications for the mean overall accuracy; and yielded 66% in the four-group classification and >80% in the between-group classifications for the mean balanced accuracy. Through summarizing the features that were automatically selected in the classifications, we found that among the three symptom-related disorders, their disorder-common impairments primarily included the decreased connectivity strength between thalamus and cerebellum and the increased strength between postcentral gyrus and thalamus. The disorder-unique changes included more various brain regions, mainly in the temporal and frontal gyrus. Our work demonstrates that dynamic functional connectivity provides biological evidence that both common and unique impairments exist in psychosis sub-groups.

Analysing brain networks in population neuroscience: a case for the Bayesian philosophy

Network connectivity fingerprints are among today's best choices to obtain a faithful sampling of an individual's brain and cognition. Widely available MRI scanners can provide rich information tapping into network recruitment and reconfiguration that now scales to hundreds and thousands of humans. Here, we contemplate the advantages of analysing such connectome profiles using Bayesian strategies. These analysis techniques afford full probability estimates of the studied network coupling phenomena, provide analytical machinery to separate epistemological uncertainty and biological variability in a coherent manner, usher us towards avenues to go beyond binary statements on existence versus non-existence of an effect, and afford credibility estimates around all model parameters at play which thus enable single-subject predictions with rigorous uncertainty intervals. We illustrate the brittle boundary between healthy and diseased brain circuits by autism spectrum disorder as a recurring theme where, we argue, network-based approaches in neuroscience will require careful probabilistic answers. This article is part of the theme issue 'Unifying the essential concepts of biological networks: biological insights and philosophical foundations'.

Predicting individual clinical trajectories of depression with generative embedding

•

Patients with major depressive disorder (MDD) show variable clinical trajectories.

•

Generative embedding (GE) is used to predict clinical trajectories in MDD patients.

•

GE classifies patients with chronic depression vs. fast remission with 79% accuracy.

•

GE provides mechanistic interpretability and outperforms conventional measures.

•

Proof-of-concept that illustrates the potential of GE for clinical prediction.

Patients with major depressive disorder (MDD) show heterogeneous treatment response and highly variable clinical trajectories: while some patients experience swift recovery, others show relapsing-remitting or chronic courses. Predicting individual clinical trajectories at an early stage is a key challenge for psychiatry and might facilitate individually tailored interventions. So far, however, reliable predictors at the single-patient level are absent. Here, we evaluated the utility of a machine learning strategy – generative embedding (GE) – which combines interpretable generative models with discriminative classifiers. Specifically, we used functional magnetic resonance imaging (fMRI) data of emotional face perception in 85 MDD patients from the NEtherlands Study of Depression and Anxiety (NESDA) who had been followed up over two years and classified into three subgroups with distinct clinical trajectories. Combining a generative model of effective (directed) connectivity with support vector machines (SVMs), we could predict whether a given patient would experience chronic depression vs. fast remission with a balanced accuracy of 79%. Gradual improvement vs. fast remission could still be predicted above-chance, but less convincingly, with a balanced accuracy of 61%. Generative embedding outperformed classification based on conventional (descriptive) features, such as functional connectivity or local activation estimates, which were obtained from the same data and did not allow for above-chance classification accuracy. Furthermore, predictive performance of GE could be assigned to a specific network property: the trial-by-trial modulation of connections by emotional content. Given the limited sample size of our study, the present results are preliminary but may serve as proof-of-concept, illustrating the potential of GE for obtaining clinical predictions that are interpretable in terms of network mechanisms. Our findings suggest that abnormal dynamic changes of connections involved in emotional face processing might be associated with higher risk of developing a less favorable clinical course.

Computational Dissociation of Dopaminergic and Cholinergic Effects on Action Selection and Inhibitory Control

BACKGROUND

Patients with schizophrenia make more errors than healthy subjects in the antisaccade task. In this paradigm, participants are required to inhibit a reflexive saccade to a target and to select the correct action (a saccade in the opposite direction). While the precise origin of this deficit is not clear, it has been connected to aberrant dopaminergic and cholinergic neuromodulation.

METHODS

To study the impact of dopamine and acetylcholine on inhibitory control and action selection, we administered two selective drugs (levodopa 200 mg/galantamine 8 mg) to healthy volunteers (N = 100) performing the antisaccade task. The computational model SERIA (stochastic early reaction, inhibition, and late action) was employed to separate the contribution of inhibitory control and action selection to empirical reaction times and error rates.

RESULTS

Modeling suggested that levodopa improved action selection (at the cost of increased reaction times) but did not have a significant effect on inhibitory control. By contrast, according to our model, galantamine affected inhibitory control in a dose-dependent fashion, reducing inhibition failures at low doses and increasing them at higher levels. These effects were sufficiently specific that the computational analysis allowed for identifying the drug administered to an individual with 70% accuracy.

CONCLUSIONS

Our results do not support the hypothesis that elevated tonic dopamine strongly impairs inhibitory control. Rather, levodopa improved the ability to select correct actions. However, inhibitory control was modulated by cholinergic drugs. This approach may provide a starting point for future computational assays that differentiate neuromodulatory abnormalities in heterogeneous diseases like schizophrenia.

Deep neural networks in psychiatry

Machine and deep learning methods, today's core of artificial intelligence, have been applied with increasing success and impact in many commercial and research settings. They are powerful tools for large scale data analysis, prediction and classification, especially in very data-rich environments ("big data"), and have started to find their way into medical applications. Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their relation to statistics, and the core principles behind them. We will then discuss and review directions along which (deep) neural networks can be, or already have been, applied in the context of psychiatry, and will try to delineate their future potential in this area. We will also comment on an emerging area that so far has been much less well explored: by embedding semantically interpretable computational models of brain dynamics or behavior into a statistical machine learning context, insights into dysfunction beyond mere prediction and classification may be gained. Especially this marriage of computational models with statistical inference may offer insights into neural and behavioral mechanisms that could open completely novel avenues for psychiatric treatment.

Considerations of power and sample size in rehabilitation research

With the current emphasis on power and reproducibility, pressures are rising to increase sample sizes in rehabilitation research in order to reflect more accurate effect estimation and generalizable results. The conventional way of increasing power by enrolling more participants is less feasible in some fields of research. In particular, rehabilitation research faces considerable challenges in achieving this goal. We describe the specific challenges to increasing power by recruiting large sample sizes and obtaining large effects in rehabilitation research. Specifically, we discuss how variability within clinical populations, lack of common standards for selecting appropriate control groups; potentially reduced reliability of measurements of brain function in individuals recovering from a brain injury; biases involved in a priori effect size estimation, and higher budgetary and staffing requirements can influence considerations of sample and effect size in rehabilitation. We also describe solutions to these challenges, such as increased sampling per participant, improving experimental control, appropriate analyses, transparent result reporting and using innovative ways of harnessing the inherent variability of clinical populations. These solutions can improve statistical power and produce reliable and valid results even in the face of limited availability of large samples.

The Future of Brain Imaging in Parkinson's Disease

Parkinson’s disease (PD) is a progressive neurodegenerative disorder that is associated with distinct abnormalities in brain function and structure. Here we discuss how future developments in functional, structural and nuclear brain imaging may help us to better understand, diagnose, and potentially even treat PD. These new horizons may be reached by developing tracers that specifically bind to alpha synuclein, by looking into different places in the body (such as the gut) or in smaller cerebral nuclei (with improved spatial resolution), and by developing new approaches for quantifying and interpreting altered dynamics in large-scale brain networks.