Association between abnormal brain functional connectivity in children and psychopathology: A study based on graph theory and machine learning

Delineating disorder-general and disorder-specific dimensions of psychopathology from functional brain networks in a developmental clinical sample

The interplay between functional brain network maturation and psychopathology during development remains elusive. To establish the structure of psychopathology and its neurobiological mechanisms, mapping of both shared and unique functional connectivity patterns across developmental clinical populations is needed. We investigated shared associations between resting-state functional connectivity and psychopathology in children and adolescents aged 5-21 (n = 1689). Specifically, we used partial least squares (PLS) to identify latent variables (LV) between connectivity and both symptom scores and diagnostic information. We also investigated associations between connectivity and each diagnosis specifically, controlling for other diagnosis categories. PLS identified five significant LVs between connectivity and symptoms, mapping onto the psychopathology hierarchy. The first LV resembled a general psychopathology factor, followed by dimensions of internalising- externalising, neurodevelopment, somatic complaints, and thought problems. Another PLS with diagnostic data revealed one significant LV, resembling a cross-diagnostic case-control pattern. The diagnosis-specific PLS identified a unique connectivity pattern for autism spectrum disorder (ASD). All LVs were associated with distinct patterns of functional connectivity. These dimensions largely replicated in an independent sample (n = 420) from the same dataset, as well as to an independent cohort (n = 3504). This suggests that covariance in developmental functional brain networks supports transdiagnostic dimensions of psychopathology.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Estimating Gender and Age from Brain Structural MRI of Children and Adolescents: A 3D Convolutional Neural Network Multitask Learning Model

Despite recent advances, assessing biological measurements for neuropsychiatric disorders is still a challenge, where confounding variables such as gender and age (as a proxy for neurodevelopment) play an important role. This study explores brain structural magnetic resonance imaging (sMRI) from two public data sets (ABIDE-II and ADHD-200) with healthy control (HC, N = 894), autism spectrum disorder (ASD, N = 251), and attention deficit hyperactivity disorder (ADHD, N = 357) individuals. We used gray and white matter preprocessed via voxel-based morphometry (VBM) to train a 3D convolutional neural network with a multitask learning strategy to estimate gender, age, and mental health status from structural brain differences. Gradient-based methods were employed to generate attention maps, providing clinically relevant identification of most representative brain regions for models' decision-making. This approach resulted in satisfactory predictions for gender and age. ADHD-200-trained models, evaluated in 10-fold cross-validation procedures on test set, obtained a mean absolute error (MAE) of 1.43 years (±0.22 SD) for age prediction and an area under the curve (AUC) of 0.85 (±0.04 SD) for gender classification. In out-of-sample validation, the best-performing ADHD-200 models satisfactorily predicted age (MAE = 1.57 years) and gender (AUC = 0.89) in the ABIDE-II data set. The models' accuracy was in line with the current state-of-the-art machine learning applications in neuroimaging. Key regions for models' accuracy were presented as a meaningful graphical output. New implementations, such as the use of VBM along with a 3D convolutional neural network multitask learning model and a brain imaging graphical output, reinforce the relevance of the proposed workflow.

Psychiatric neuroimaging research in Brazil: historical overview, current challenges, and future opportunities

The last four decades have witnessed tremendous growth in research studies applying neuroimaging methods to evaluate pathophysiological and treatment aspects of psychiatric disorders around the world. This article provides a brief history of psychiatric neuroimaging research in Brazil, including quantitative information about the growth of this field in the country over the past 20 years. Also described are the various methodologies used, the wealth of scientific questions investigated, and the strength of international collaborations established. Finally, examples of the many methodological advances that have emerged in the field of in vivo neuroimaging are provided, with discussion of the challenges faced by psychiatric research groups in Brazil, a country of limited resources, to continue incorporating such innovations to generate novel scientific data of local and global relevance.

Birth weight is associated with adolescent brain development: A multimodal imaging study in monozygotic twins

Previous research has shown that the prenatal environment, commonly indexed by birth weight (BW), is a predictor of morphological brain development. We previously showed in monozygotic (MZ) twins associations between BW and brain morphology that were independent of genetics. In the present study, we employed a longitudinal MZ twin design to investigate whether variations in prenatal environment (as indexed by discordance in BW) are associated with resting‐state functional connectivity (rs‐FC) and with structural connectivity. We focused on the limbic and default mode networks (DMNs), which are key regions for emotion regulation and internally generated thoughts, respectively. One hundred and six healthy adolescent MZ twins (53 pairs; 42% male pairs) followed longitudinally from birth underwent a magnetic resonance imaging session at age 15. Graph theoretical analysis was applied to rs‐FC measures. TrackVis was used to determine track count as an indicator of structural connectivity strength. Lower BW twins had less efficient limbic network connectivity as compared to their higher BW co‐twin, driven by differences in the efficiency of the right hippocampus and right amygdala. Lower BW male twins had fewer tracks connecting the right hippocampus and right amygdala as compared to their higher BW male co‐twin. There were no associations between BW and the DMN. These findings highlight the possible role of unique prenatal environmental influences in the later development of efficient spontaneous limbic network connections within healthy individuals, irrespective of DNA sequence or shared environment.

Machine learning in mental health: a scoping review of methods and applications

BACKGROUND

This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice.

METHODS

We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review.

RESULTS

Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health, and; (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering.

CONCLUSIONS

Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.

Applying Machine Learning Techniques to Identify Undiagnosed Patients with Exocrine Pancreatic Insufficiency

BACKGROUND

Exocrine pancreatic insufficiency (EPI) is a serious condition characterized by a lack of functional exocrine pancreatic enzymes and the resultant inability to properly digest nutrients. EPI can be caused by a variety of disorders, including chronic pancreatitis, pancreatic cancer, and celiac disease. EPI remains underdiagnosed because of the nonspecific nature of clinical symptoms, lack of an ideal diagnostic test, and the inability to easily identify affected patients using administrative claims data.

OBJECTIVES

To develop a machine learning model that identifies patients in a commercial medical claims database who likely have EPI but are undiagnosed.

METHODS

A machine learning algorithm was developed in Scikit-learn, a Python module. The study population, selected from the 2014 Truven MarketScan® Commercial Claims Database, consisted of patients with EPI-prone conditions. Patients were labeled with 290 condition category flags and split into actual positive EPI cases, actual negative EPI cases, and unlabeled cases. The study population was then randomly divided into a training subset and a testing subset. The training subset was used to determine the performance metrics of 27 models and to select the highest performing model, and the testing subset was used to evaluate performance of the best machine learning model.

RESULTS

The study population consisted of 2088 actual positive EPI cases, 1077 actual negative EPI cases, and 437 530 unlabeled cases. In the best performing model, the precision, recall, and accuracy were 0.91, 0.80, and 0.86, respectively. The best-performing model estimated that the number of patients likely to have EPI was about 12 times the number of patients directly identified as EPI-positive through a claims analysis in the study population. The most important features in assigning EPI probability were the presence or absence of diagnosis codes related to pancreatic and digestive conditions.

CONCLUSIONS

Machine learning techniques demonstrated high predictive power in identifying patients with EPI and could facilitate an enhanced understanding of its etiology and help to identify patients for possible diagnosis and treatment.

Sensor Level Functional Connectivity Topography Comparison Between Different References Based EEG and MEG

Sensor-level functional connectivity topography (sFCT) contributes significantly to our understanding of brain networks. sFCT can be constructed using either electroencephalography (EEG) or magnetoencephalography (MEG). Here, we compared sFCT within the EEG modality and between EEG and MEG modalities. We first used simulations to look at how different EEG references-including the Reference Electrode Standardization Technique (REST), average reference (AR), linked mastoids (LM), and left mastoid references (LR)-affect EEG-based sFCT. The results showed that REST decreased the reference effects on scalp EEG recordings, making REST-based sFCT closer to the ground truth (sFCT based on ideal recordings). For the inter-modality simulation comparisons, we compared each type of EEG-sFCT with MEG-sFCT using three metrics to quantize the differences: Relative Error (RE), Overlap Rate (OR), and Hamming Distance (HD). When two sFCTs are similar, RE and HD are low, while OR is high. Results showed that among all reference schemes, EEG-and MEG-sFCT were most similar when the EEG was REST-based and the EEG and MEG were recorded simultaneously. Next, we analyzed simultaneously recorded MEG and EEG data from publicly available face-recognition experiments using a similar procedure as in the simulations. The results showed (1) if MEG-sFCT is the standard, REST-and LM-based sFCT provided results closer to this standard in the terms of HD; (2) REST-based sFCT and MEG-sFCT had the highest similarity in terms of RE; (3) REST-based sFCT had the most overlapping edges with MEG-sFCT in terms of OR. This study thus provides new insights into the effect of different reference schemes on sFCT and the similarity between MEG and EEG in terms of sFCT.