Faculty Bibliography

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Objective/UNASSIGNED:Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods/UNASSIGNED:This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results/UNASSIGNED:The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73-0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions/UNASSIGNED:Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies.

Grid cells or grid-like responses have been reported in the rodent, bat and human brains during various spatial and non-spatial tasks. However, the functions of grid-like representations beyond the classical hippocampal formation remain elusive. Based on accumulating evidence from recent rodent recordings and human fMRI data, we make speculative accounts regarding the mechanisms and functional significance of the sensory cortical grid cells and further make theory-driven predictions. We argue and reason the rationale why grid responses may be universal in the brain for a wide range of perceptual and cognitive tasks that involve locomotion and mental navigation. Computational modeling may provide an alternative and complementary means to investigate the grid code or grid-like map. We hope that the new discussion will lead to experimentally testable hypotheses and drive future experimental data collection.

The prefrontal cortex (PFC) regulates a wide range of sensory experiences. Chronic pain is known to impair normal neural response, leading to enhanced aversion. However, it remains unknown how nociceptive responses in the cortex are processed at the population level and whether such processes are disrupted by chronic pain. Using in vivo endoscopic calcium imaging, we identify increased population activity in response to noxious stimuli and stable patterns of functional connectivity among neurons in the prelimbic (PL) PFC from freely behaving rats. Inflammatory pain disrupts functional connectivity of PFC neurons and reduces the overall nociceptive response. Interestingly, ketamine, a well-known neuromodulator, restores the functional connectivity among PL-PFC neurons in the inflammatory pain model to produce anti-aversive effects. These results suggest a dynamic resource allocation mechanism in the prefrontal representations of pain and indicate that population activity in the PFC critically regulates pain and serves as an important therapeutic target.

Recurrent neural networks (RNNs) have been widely used to model sequential neural dynamics ("neural sequences") of cortical circuits in cognitive and motor tasks. Efforts to incorporate biological constraints and Dale's principle will help elucidate the neural representations and mechanisms of underlying circuits. We trained an excitatory-inhibitory RNN to learn neural sequences in a supervised manner and studied the representations and dynamic attractors of the trained network. The trained RNN was robust to trigger the sequence in response to various input signals and interpolated a time-warped input for sequence representation. Interestingly, a learned sequence can repeat periodically when the RNN evolved beyond the duration of a single sequence. The eigenspectrum of the learned recurrent connectivity matrix with growing or damping modes, together with the RNN's nonlinearity, were adequate to generate a limit cycle attractor. We further examined the stability of dynamic attractors while training the RNN to learn two sequences. Together, our results provide a general framework for understanding neural sequence representation in the excitatory-inhibitory RNN.

The prefrontal cortex (PFC) plays a prominent role in performing flexible cognitive functions and working memory, yet the underlying computational principle remains poorly understood. Here, we trained a rate-based recurrent neural network (RNN) to explore how the context rules are encoded, maintained across seconds-long mnemonic delay, and subsequently used in a context-dependent decision-making task. The trained networks replicated key experimentally observed features in the PFC of rodent and monkey experiments, such as mixed selectivity, neuronal sequential activity, and rotation dynamics. To uncover the high-dimensional neural dynamical system, we further proposed a geometric framework to quantify and visualize population coding and sensory integration in a temporally defined manner. We employed dynamic epoch-wise principal component analysis (PCA) to define multiple task-specific subspaces and task-related axes, and computed the angles between task-related axes and these subspaces. In low-dimensional neural representations, the trained RNN first encoded the context cues in a cue-specific subspace, and then maintained the cue information with a stable low-activity state persisting during the delay epoch, and further formed line attractors for sensor integration through low-dimensional neural trajectories to guide decision-making. We demonstrated via intensive computer simulations that the geometric manifolds encoding the context information were robust to varying degrees of weight perturbation in both space and time. Overall, our analysis framework provides clear geometric interpretations and quantification of information coding, maintenance, and integration, yielding new insight into the computational mechanisms of context-dependent computation.

Propagation of activity in spatially structured neuronal networks has been observed in awake, anesthetized, and sleeping brains. How these wave patterns emerge and organize across brain structures, and how network connectivity affects spatiotemporal neural activity remains unclear. Here, we develop a computational model of a two-dimensional thalamocortical network, which gives rise to emergent traveling waves similar to those observed experimentally. We illustrate how spontaneous and evoked oscillatory activity in space and time emerge using a closed-loop thalamocortical architecture, sustaining smooth waves in the cortex and staggered waves in the thalamus. We further show that intracortical and thalamocortical network connectivity, cortical excitation/inhibition balance, and thalamocortical or corticothalamic delay can independently or jointly change the spatiotemporal patterns (radial, planar and rotating waves) and characteristics (speed, direction, and frequency) of cortical and thalamic traveling waves. Computer simulations predict that increased thalamic inhibition induces slower cortical frequencies and that enhanced cortical excitation increases traveling wave speed and frequency. Overall, our results provide insight into the genesis and sustainability of thalamocortical spatiotemporal patterns, showing how simple synaptic alterations cause varied spontaneous and evoked wave patterns. Our model and simulations highlight the need for spatially spread neural recordings to uncover critical circuit mechanisms for brain functions.

Exploring the neural circuits of the extinction of conditioned fear is critical to advance our understanding of fear- and anxiety-related disorders. The field has focused on examining the role of various regions of the medial prefrontal cortex, insular cortex, hippocampus, and amygdala in conditioned fear and its extinction. The contribution of this 'fear network' to the conscious awareness of fear has recently been questioned. And as such, there is a need to examine higher/multiple cortical systems that might contribute to the conscious feeling of fear and anxiety. Herein, we studied functional connectivity patterns across the entire brain to examine the contribution of multiple networks to the acquisition of fear extinction learning and its retrieval. We conducted trial-by-trial analyses on data from 137 healthy participants who underwent a two-day fear conditioning and extinction paradigm in a functional magnetic resonance imaging (fMRI) scanner. We found that functional connectivity across a broad range of brain regions, many of which are part of the default mode, frontoparietal, and ventral attention networks, increased from early to late extinction learning only to a conditioned cue. The increased connectivity during extinction learning predicted the magnitude of extinction memory tested 24 hours later. Together, these findings provide evidence supporting recent studies implicating distributed brain regions in learning, consolidation and expression of fear extinction memory in the human brain.

Emerging technologies to acquire data at increasingly greater scales promise to transform discovery in systems neuroscience. However, current exponential growth in the scale of data acquisition is a double-edged sword. Scaling up data acquisition can speed up the cycle of discovery but can also misinterpret the results or possibly slow down the cycle because of challenges presented by the curse of high-dimensional data. Active, adaptive, closed-loop experimental paradigms use hardware and algorithms optimized to enable time-critical computation to provide feedback that interprets the observations and tests hypotheses to actively update the stimulus or stimulation parameters. In this perspective, we review important concepts of active and adaptive experiments and discuss how selectively constraining the dimensionality and optimizing strategies at different stages of discovery loop can help mitigate the curse of high-dimensional data. Active and adaptive closed-loop experimental paradigms can speed up discovery despite an exponentially increasing data scale, offering a road map to timely and iterative hypothesis revision and discovery in an era of exponential growth in neuroscience.