The accurate identification of an attention deficit hyperactivity disorder (ADHD) subject has remained a challenge for both neuroscience research and clinical diagnosis. Unfortunately, the traditional methods concerning the classification model and feature extraction usually depend on the single-channel model and static measurements (i.e., functional connectivity, FC) in the small, homogenous single-site dataset, which is limited and may cause the loss of intrinsic information in functional MRI (fMRI). In this study, we proposed a new two-stage network structure by combing a separated channel convolutional neural network (SC-CNN) with an attention-based network (SC-CNN-attention) to discriminate ADHD and healthy controls on a large-scale multi-site database (5 sites and n = 1019). To utilize both intrinsic temporal feature and the interactions of temporal dependent in whole-brain resting-state fMRI, in the first stage of our proposed network structure, a SC- CNN is used to learn the temporal feature of each brain region, and an attention network in the second stage is adopted to capture temporal dependent features among regions and extract fusion features. Using a “leave-one-site-out” cross-validation framework, our proposed method obtained a mean classification accuracy of 68.6% on five different sites, which is higher than those reported in previous studies. The classification results demonstrate that our proposed network is robust to data variants and is also replicated across sites. The combination of the SC-CNN with the attention network is powerful to capture the intrinsic fMRI information to discriminate ADHD across multi-site resting-state fMRI data.

The objective of the current study is to determine robust transdiagnostic brain structural markers for compulsivity by capitalizing on the increasing number of case-control studies examining gray matter volume (GMV) alterations in substance use disorders (SUD) and obsessive-compulsive disorder (OCD). Voxel-based meta-analysis within the individual disorders and conjunction analysis were employed to reveal common GMV alterations between SUDs and OCD. Meta-analytic coordinates and signed brain volumetric maps determining directed (reduced/increased) GMV alterations between the disorder groups and controls served as the primary outcome. The separate meta-analysis demonstrated that SUD and OCD patients exhibited widespread GMV reductions in frontocortical regions including prefrontal, cingulate, and insular. Conjunction analysis revealed that the left inferior frontal gyrus (IFG) consistently exhibited decreased GMV across all disorders. Functional characterization suggests that the IFG represents a core hub in the cognitive control network and exhibits bidirectional (Granger) causal interactions with the striatum. Only OCD showed increased GMV in the dorsal striatum with higher changes being associated with more severe OCD symptomatology. Together the findings demonstrate robustly decreased GMV across the disorders in the left IFG, suggesting a transdiagnostic brain structural marker. The functional characterization as a key hub in the cognitive control network and casual interactions with the striatum suggest that deficits in inhibitory control mechanisms may promote compulsivity and loss of control that characterize both disorders.

Reinforcement learning was developed mainly for discrete-time Markov decision processes. This paper establishes a novel learning approach based on temporal-difference and nonparametric smoothing to solve reinforcement learning problems in a continuous-time setting with noisy data, where the true model to learn is governed by an ordinary differential equation, and data samples are generated from a stochastic differential equation that is considered as a noisy version of the ordinary differential equation. Continuous-time temporal-difference learning developed for deterministic models is unstable and in fact diverges when applied to data generated from stochastic models. Furthermore, because there are measurement errors or noises in the observed data, a new reinforcement learning framework is needed to handle the learning problems with noisy data. We show that the proposed learning approach has a robust performance for learning deterministic functions based on noisy data generated from stochastic models governed by stochastic differential equations. An asymptotic theory is established for the proposed approach, and a numerical study is carried out to solve a pendulum reinforcement learning problem and check the finite sample performance of the proposed method.

No abstract

Aim: To determine robust transdiagnostic brain structural markers for compulsivity by capitalizing on the increasing number of case-control studies examining gray matter alterations in substance use disorders (SUD) and obsessive-compulsive disorder (OCD). Design: Pre-registered voxel-based meta-analysis of grey matter volume (GMV) changes through seed-based d Mapping (SDM), follow-up functional, and network-level characterization of the identified transdiagnostic regions by means of co-activation and Granger Causality (GCA) analysis. Participants: Literature search resulted in 31 original VBM studies comparing SUD (n=1191, mean-age=40.03, SD=10.87) and 30 original studies comparing OCD (n=1293, mean-age=29.18, SD=10.34) patients with healthy controls (SUD: n=1585, mean-age=42.63, SD=14.27, OCD: n=1374, mean-age=28.97, SD=9.96). Measurements: Voxel-based meta-analysis within the individual disorders as well as conjunction analysis were employed to reveal common GMV alterations between SUDs and OCD. Meta-analytic coordinates and signed brain volumetric maps determining directed (reduced or increased) brain volumetric alterations between the disorder groups and controls served as the primary outcome. Meta-analytic results employed statistical significance thresholding (FWE<0.05). Findings: Separate meta-analysis demonstrated that SUD (cocaine, alcohol, and nicotine) as well as OCD patients exhibited widespread GMV reductions in frontocortical regions including prefrontal, cingulate, and insular regions. Conjunction analysis revealed that the left inferior frontal gyrus (IFG) consistently exhibited decreased GMV across all disorders. Functional characterization suggests that the IFG represents a core hub in the cognitive control network and exhibits bidirectional (Granger) causal interactions with the striatum. Only OCD showed increased GMV in the dorsal striatum with higher changes being associated with more severe OCD symptomatology. Conclusions: Findings demonstrate robustly decreased GMV across the disorders in the left IFG, suggesting a transdiagnostic brain structural marker. The functional characterization as a key hub in the cognitive control network and casual interactions with the striatum suggest that deficits in inhibitory control mechanisms may promote compulsivity and loss of control that characterize both disorders.