Random forest based classification of alcohol dependence patients and healthy controls using resting state MRI

Why experimental variation in neuroimaging should be embraced

In a perfect world, scientists would develop analyses that are guaranteed to reveal the ground truth of a research question. In reality, there are countless viable workflows that produce distinct, often conflicting, results. Although reproducibility places a necessary bound on the validity of results, it is not sufficient for claiming underlying validity, eventual utility, or generalizability. In this work we focus on how embracing variability in data analysis can improve the generalizability of results. We contextualize how design decisions in brain imaging can be made to capture variation, highlight examples, and discuss how variability capture may improve the quality of results.

Atypical effective connectivity from the frontal cortex to striatum in alcohol use disorder

Alcohol use disorder (AUD) is a profound psychiatric condition marked by disrupted connectivity among distributed brain regions, indicating impaired functional integration. Previous connectome studies utilizing functional magnetic resonance imaging (fMRI) have predominantly focused on undirected functional connectivity, while the specific alterations in directed effective connectivity (EC) associated with AUD remain unclear. To address this issue, this study utilized multivariate pattern analysis (MVPA) and spectral dynamic causal modeling (DCM). We recruited 32 abstinent men with AUD and 30 healthy controls (HCs) men, and collected their resting-state fMRI data. A regional homogeneity (ReHo)-based MVPA method was employed to classify AUD and HC groups, as well as predict the severity of addiction in AUD individuals. The most informative brain regions identified by the MVPA were further investigated using spectral DCM. Our results indicated that the ReHo-based support vector classification (SVC) exhibits the highest accuracy in distinguishing individuals with AUD from HCs (classification accuracy: 98.57%). Additionally, our results demonstrated that ReHo-based support vector regression (SVR) could be utilized to predict the addiction severity (alcohol use disorders identification test, AUDIT, R2 = 0.38; Michigan alcoholism screening test, MAST, R2 = 0.29) of patients with AUD. The most informative brain regions for the prediction include left pre-SMA, right dACC, right LOFC, right putamen, and right NACC. These findings were validated in an independent data set (35 patients with AUD and 36 HCs, Classification accuracy: 91.67%; AUDIT, R2 = 0.17; MAST, R2 = 0.20). The results of spectral DCM analysis indicated that individuals with AUD exhibited decreased EC from the left pre-SMA to the right putamen, from the right dACC to the right putamen, and from the right LOFC to the right NACC compared to HCs. Moreover, the EC strength from the right NACC to left pre-SMA and from the right dACC to right putamen mediated the relationship between addiction severity (MAST scores) and behavioral measures (impulsive and compulsive scores). These findings provide crucial evidence for the underlying mechanism of impaired self-control, risk assessment, and impulsive and compulsive alcohol consumption in individuals with AUD, providing novel causal insights into both diagnosis and treatment.

Classifying Unconscious, Psychedelic, and Neuropsychiatric Brain States with Functional Connectivity, Graph Theory, and Cortical Gradient Analysis

Accurate and generalizable classification of brain states is essential for understanding their neural underpinnings and improving clinical diagnostics. Traditionally, functional connectivity patterns and graph-theoretic metrics have been utilized. However, cortical gradient features, which reflect global brain organization, offer a complementary approach. We hypothesized that a machine learning model integrating these three feature sets would effectively discriminate between baseline and atypical brain states across a wide spectrum of conditions, even though the underlying neural mechanisms vary. To test this, we extracted features from brain states associated with three meta-conditions including unconsciousness (NREM2 sleep, propofol deep sedation, and propofol general anesthesia), psychedelic states induced by hallucinogens (subanesthetic ketamine, lysergic acid diethylamide, and nitrous oxide), and neuropsychiatric disorders (attention-deficit hyperactivity disorder, bipolar disorder, and schizophrenia). We used support vector machine with nested cross-validation to construct our models. The soft voting ensemble model marked the average balanced accuracy (average of specificity and sensitivity) of 79% (62-98% across all conditions), outperforming individual base models (70-76%). Notably, our models exhibited varying degrees of transferability across different datasets, with performance being dependent on the specific brain states and feature sets used. Feature importance analysis across meta-conditions suggests that the underlying neural mechanisms vary significantly, necessitating tailored approaches for accurate classification of specific brain states. This finding underscores the value of our feature-integrated ensemble models, which leverage the strengths of multiple feature types to achieve robust performance across a broader range of brain states. While our approach offers valuable insights into the neural signatures of different brain states, future work is needed to develop and validate even more generalizable models that can accurately classify brain states across a wider array of conditions.

Widespread, depth-dependent cortical microstructure alterations in pediatric focal epilepsy

OBJECTIVE

Tissue abnormalities in focal epilepsy may extend beyond the presumed focus. The underlying pathophysiology of these broader changes is unclear, and it is not known whether they result from ongoing disease processes or treatment-related side effects, or whether they emerge earlier. Few studies have focused on the period of onset for most focal epilepsies, childhood. Fewer still have utilized quantitative magnetic resonance imaging (MRI), which may provide a more sensitive and interpretable measure of tissue microstructural change. Here, we aimed to determine common spatial modes of changes in cortical architecture in children with heterogeneous drug-resistant focal epilepsy and, secondarily, whether changes were related to disease severity.

METHODS

To assess cortical microstructure, quantitative T1 and T2 relaxometry (qT1 and qT2) was measured in 43 children with drug-resistant focal epilepsy (age range = 4-18 years) and 46 typically developing children (age range = 2-18 years). We assessed depth-dependent qT1 and qT2 values across the neocortex, as well as their gradient of change across cortical depths. We also determined whether global changes seen in group analyses were driven by focal pathologies in individual patients. Finally, as a proof-of-concept, we trained a classifier using qT1 and qT2 gradient maps from patients with radiologically defined abnormalities (MRI positive) and healthy controls, and tested whether this could classify patients without reported radiological abnormalities (MRI negative).

RESULTS

We uncovered depth-dependent qT1 and qT2 increases in widespread cortical areas in patients, likely representing microstructural alterations in myelin or gliosis. Changes did not correlate with disease severity measures, suggesting they may represent antecedent neurobiological alterations. Using a classifier trained with MRI-positive patients and controls, sensitivity was 71.4% at 89.4% specificity on held-out MRI-negative patients.

SIGNIFICANCE

These findings suggest the presence of a potential imaging endophenotype of focal epilepsy, detectable irrespective of radiologically identified abnormalities.

Machine Learning of Functional Connectivity to Biotype Alcohol and Nicotine Use Disorders

BACKGROUND

Magnetic resonance imaging provides noninvasive tools to investigate alcohol use disorder (AUD) and nicotine use disorder (NUD) and neural phenotypes for genetic studies. A data-driven transdiagnostic approach could provide a new perspective on the neurobiology of AUD and NUD.

METHODS

Using samples of individuals with AUD (n = 140), individuals with NUD (n = 249), and healthy control participants (n = 461) from the UK Biobank, we integrated clinical, neuroimaging, and genetic markers to identify biotypes of AUD and NUD. We partitioned participants with AUD and NUD based on resting-state functional connectivity (FC) features associated with clinical metrics. A multitask artificial neural network was trained to evaluate the cluster-defined biotypes and jointly infer AUD and NUD diagnoses.

RESULTS

Three biotypes-primary NUD, mixed NUD/AUD with depression and anxiety, and mixed AUD/NUD-were identified. Multitask classifiers incorporating biotype knowledge achieved higher area under the curve (AUD: 0.76, NUD: 0.74) than single-task classifiers without biotype differentiation (AUD: 0.61, NUD: 0.64). Cerebellar FC features were important in distinguishing the 3 biotypes. The biotype of mixed NUD/AUD with depression and anxiety demonstrated the largest number of FC features (n = 5), all related to the visual cortex, that significantly differed from healthy control participants and were validated in a replication sample (p < .05). A polymorphism in TNRC6A was associated with the mixed AUD/NUD biotype in both the discovery (p = 7.3 × 10-5) and replication (p = 4.2 × 10-2) sets.

CONCLUSIONS

Biotyping and multitask learning using FC features can characterize the clinical and genetic profiles of AUD and NUD and help identify cerebellar and visual circuit markers to differentiate the AUD/NUD group from the healthy control group. These markers support a new growing body of literature.

Aberrant functional brain network organization is associated with relapse during 1-year follow-up in alcohol-dependent patients

Alcohol dependence (AD) is a debilitating disease associated with high relapse rates even after long periods of abstinence. Thus, elucidating neurobiological substrates of relapse risk is fundamental for the development of novel targeted interventions that could promote long-lasting abstinence. In the present study, we analysed resting-state functional magnetic resonance imaging (rsfMRI) data from a sample of recently detoxified patients with AD (n = 93) who were followed up for 12 months after rsfMRI assessment. Specifically, we employed graph theoretic analyses to compare functional brain network topology and functional connectivity between future relapsers (REL, n = 59), future abstainers (ABS, n = 28) and age- and gender-matched controls (CON, n = 83). Our results suggest increased whole-brain network segregation, decreased global network integration and overall blunted connectivity strength in REL compared with CON. Conversely, we found evidence for a comparable network architecture in ABS relative to CON. At the nodal level, REL exhibited decreased integration and decoupling between multiple brain systems compared with CON, encompassing regions associated with higher-order executive functions, sensory and reward processing. Among patients with AD, increased coupling between nodes implicated in reward valuation and salience attribution constitutes a particular risk factor for future relapse. Importantly, aberrant network organization in REL was consistently associated with shorter abstinence duration during follow-up, portending to a putative neural signature of relapse risk in AD. Future research should further evaluate the potential diagnostic value of the identified changes in network topology and functional connectivity for relapse prediction at the individual subject level.

oFVSD: a Python package of optimized forward variable selection decoder for high-dimensional neuroimaging data

The complexity and high dimensionality of neuroimaging data pose problems for decoding information with machine learning (ML) models because the number of features is often much larger than the number of observations. Feature selection is one of the crucial steps for determining meaningful target features in decoding; however, optimizing the feature selection from such high-dimensional neuroimaging data has been challenging using conventional ML models. Here, we introduce an efficient and high-performance decoding package incorporating a forward variable selection (FVS) algorithm and hyper-parameter optimization that automatically identifies the best feature pairs for both classification and regression models, where a total of 18 ML models are implemented by default. First, the FVS algorithm evaluates the goodness-of-fit across different models using the k-fold cross-validation step that identifies the best subset of features based on a predefined criterion for each model. Next, the hyperparameters of each ML model are optimized at each forward iteration. Final outputs highlight an optimized number of selected features (brain regions of interest) for each model with its accuracy. Furthermore, the toolbox can be executed in a parallel environment for efficient computation on a typical personal computer. With the optimized forward variable selection decoder (oFVSD) pipeline, we verified the effectiveness of decoding sex classification and age range regression on 1,113 structural magnetic resonance imaging (MRI) datasets. Compared to ML models without the FVS algorithm and with the Boruta algorithm as a variable selection counterpart, we demonstrate that the oFVSD significantly outperformed across all of the ML models over the counterpart models without FVS (approximately 0.20 increase in correlation coefficient, r, with regression models and 8% increase in classification models on average) and with Boruta variable selection algorithm (approximately 0.07 improvement in regression and 4% in classification models). Furthermore, we confirmed the use of parallel computation considerably reduced the computational burden for the high-dimensional MRI data. Altogether, the oFVSD toolbox efficiently and effectively improves the performance of both classification and regression ML models, providing a use case example on MRI datasets. With its flexibility, oFVSD has the potential for many other modalities in neuroimaging. This open-source and freely available Python package makes it a valuable toolbox for research communities seeking improved decoding accuracy.

The Moderating Role of Sex in the Relation between Cue-Induced Craving and Resting-State Functional Connectivity in the Salience Network of Non-Clinically Diagnosed Drinkers

INTRODUCTION

Previous research indicates a relation between craving and increased connectivity in the resting-state salience network. However, the link between cue-induced craving and connectivity in the salience network remains unclear. Further investigation is needed to understand the effect of sex on the relationship between cue-induced craving and the salience network. We investigated the role of sex in the association between the resting-state functional connectivity (RSFC) salience network and subjective cue-induced craving.

METHODS

Twenty-six males (mean age = 25.3) and 23 females (mean age = 26.0), with a score of 12 or higher on the alcohol use disorder identification test, were included in the current study. No significant difference in age was observed between males and females. Participants underwent a resting-state MRI scan for 6 min. Following the MRI scan, participants completed an alcohol cue-exposure task for 5.5 min to assess cue-induced craving using the desire to drink alcohol questionnaire. We applied independent component analysis methods to determine functional connectivity within the salience network. Subsequently, we investigated how cue-induced craving is related to the salience network's RSFC and if this relationship is moderated by sex.

RESULTS

The association between the salience network and cue-induced craving was not statistically significant nor did we find a moderating effect for sex.

CONCLUSION

The null findings in the study may be explained by a lack of power. Alternatively, alcohol use sex disparities may be more prevalent in the recreational/impulsive stage, whereas participants in our study were in the later stage of addiction.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Diabetes Detection Models in Mexican Patients by Combining Machine Learning Algorithms and Feature Selection Techniques for Clinical and Paraclinical Attributes: A Comparative Evaluation

The development of medical diagnostic models to support healthcare professionals has witnessed remarkable growth in recent years. Among the prevalent health conditions affecting the global population, diabetes stands out as a significant concern. In the domain of diabetes diagnosis, machine learning algorithms have been widely explored for generating disease detection models, leveraging diverse datasets primarily derived from clinical studies. The performance of these models heavily relies on the selection of the classifier algorithm and the quality of the dataset. Therefore, optimizing the input data by selecting relevant features becomes essential for accurate classification. This research presents a comprehensive investigation into diabetes detection models by integrating two feature selection techniques: the Akaike information criterion and genetic algorithms. These techniques are combined with six prominent classifier algorithms, including support vector machine, random forest, k-nearest neighbor, gradient boosting, extra trees, and naive Bayes. By leveraging clinical and paraclinical features, the generated models are evaluated and compared to existing approaches. The results demonstrate superior performance, surpassing accuracies of 94%. Furthermore, the use of feature selection techniques allows for working with a reduced dataset. The significance of feature selection is underscored in this study, showcasing its pivotal role in enhancing the performance of diabetes detection models. By judiciously selecting relevant features, this approach contributes to the advancement of medical diagnostic capabilities and empowers healthcare professionals in making informed decisions regarding diabetes diagnosis and treatment.

MRI texture-based radiomics analysis for the identification of altered functional networks in alcoholic patients and animal models

Alcohol use disorder (AUD) is a complex condition representing a leading risk factor for death, disease and disability. Its high prevalence and severe health consequences make necessary a better understanding of the brain network alterations to improve diagnosis and treatment. The purpose of this study was to evaluate the potential of resting-state fMRI 3D texture features as a novel source of biomarkers to identify AUD brain network alterations following a radiomics approach. A longitudinal study was conducted in Marchigian Sardinian alcohol-preferring msP rats (N = 36) who underwent resting-state functional and structural MRI before and after 30 days of alcohol or water consumption. A cross-sectional human study was also conducted among 33 healthy controls and 35 AUD patients. The preprocessed functional data corresponding to control and alcohol conditions were used to perform a probabilistic independent component analysis, identifying seven independent components as resting-state networks. Forty-three radiomic features extracted from each network were compared using a Wilcoxon signed-rank test with Holm correction to identify the network most affected by alcohol consumption. Features extracted from this network were then used in the machine learning process, evaluating two feature selection methods and six predictive models within a nested cross-validation structure. The classification was evaluated by computing the area under the ROC curve. Images were quantized using different numbers of gray-levels to test their influence on the results. The influence of ageing, data preprocessing, and brain iron accumulation were also analyzed. The methodology was validated using structural scans. The striatal network in alcohol-exposed msP rats presented the most significant number of altered features. The radiomics approach supported this result achieving good classification performance in animals (AUC = 0.915 ± 0.100, with 12 features) and humans (AUC = 0.724 ± 0.117, with 9 features) using a random forest model. Using the structural scans, high accuracy was achieved with a multilayer perceptron in both species (animals: AUC > 0.95 with 2 features, humans: AUC > 0.82 with 18 features). The best results were obtained using a feature selection method based on the p-value. The proposed radiomics approach is able to identify AUD patients and alcohol-exposed rats with good accuracy, employing a subset of 3D features extracted from fMRI. Furthermore, it can help identify relevant networks in drug addiction.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Machine learning with neuroimaging biomarkers: Application in the diagnosis and prediction of drug addiction

Drug abuse is a serious problem worldwide. Owing to intermittent intake of certain substances and the early inconspicuous clinical symptoms, this brings huge challenges for timely diagnosing addiction status and preventing substance use disorders (SUDs). As a non-invasive technique, neuroimaging can capture neurobiological signatures of abnormality in multiple brain regions caused by drug consumption in each clinical stage, like parenchymal morphology alteration as well as aberrant functional activity and connectivity of cerebral areas, making it realizable to diagnosis, prediction and even preemptive therapy of addiction. Machine learning (ML) algorithms primarily used for classification have been extensively applied in analysing medical imaging datasets. Significant neurobiological characteristics employed and revealed by classifiers were used to diagnose addictive states and predict initiation and vulnerability to drug usage, treatment abstinence, relapse and resilience of addicts and the risk of SUD. In this review, we summarize application of ML methods in neuroimaging focusing on addicts' diagnosis of clinical status and risk prediction and elucidate the discriminative neurobiological features from brain electrophysiological, morphological and functional perspectives that contribute most to the classifier, finally highlighting the auxiliary role of ML in addiction treatment.

Class balancing framework for credit card fraud detection based on clustering and similarity-based selection (SBS)

Credit card fraud is a growing problem nowadays and it has escalated during COVID-19 due to the authorities in many countries requiring people to use cashless transactions. Every year, billions of Euros are lost due to credit card fraud transactions, therefore, fraud detection systems are essential for financial institutions. As the classes' distribution is not equally represented in the credit card dataset, the machine learning trains the model according to the majority class which leads to inaccurate fraud predictions. For that, in this research, we mainly focus on processing unbalanced data by using an under-sampling technique to get more accurate and better results with different machine learning algorithms. We propose a framework that is based on clustering the dataset using fuzzy C-means and selecting similar fraud and normal instances that have the same features, which guarantees the integrity between the data features.

Alcohol use disorder-associated structural and functional characteristics of the insula

Based on our current understanding of insular regions, effects of chronic alcohol use on the insula may affect the integration of sensory-motor, socio-emotional, and cognitive function. There is no comprehensive understanding about these differences in individuals with alcohol use disorder that accounts for both structural and functional differences related to chronic alcohol use. The purpose of this study was to investigate these variations in both the anterior and posterior insula in persons with alcohol use disorder. We investigated insula gray matter volume, morphometry, white matter structural connectivity, and resting state functional connectivity in 75 participants with alcohol use disorder (females = 27) and 75 age-matched healthy control participants (females = 39). Results indicated structural differences mostly in the anterior regions, while functional connectivity differences were observed in both the anterior and posterior insula in those with alcohol use disorder. Differing connectivity was observed with frontal, parietal, occipital, cingulate, cerebellar, and temporal brain regions. While these results align with prior studies showing differences primarily in anterior insular regions, they also contribute to the existing literature suggesting differences in anterior insular connectivity with brain regions shown to be engaged during higher cognitive and emotional tasks.

Alcohol dependence inpatients classification with GLM and hierarchical clustering integration using fMRI data of alcohol multiple scenario cues

Alterations in brain reactions to alcohol-related cues are a neurobiological characteristic of alcohol dependence (AD) and a prospective target for achieving substantial treatment effects. However, a robust prediction of the differences in inpatients' brain responses to alcohol cues during the treatment process is still required. This study offers a data-driven approach for classifying AD inpatients undertaking alcohol treatment protocols based on their brain responses to alcohol imagery with and without drinking actions. The brain activity of thirty inpatients with AD undergoing treatment was scanned using functional magnetic resonance imaging (fMRI) while seeing alcohol and matched non-alcohol images. The mean values of brain regions of interest (ROI) for alcohol-related brain responses were obtained using general linear modeling (GLM) and subjected to hierarchical clustering analysis. The proposed classification technique identified two distinct subgroups of inpatients. For the two types of cues, subgroup one exhibited significant activation in a wide range of brain regions, while subgroup two showed mainly decreased activation. The proposed technique may aid in detecting the vulnerability of the classified inpatient subgroups, which can suggest allocating the inpatients in the classified subgroups to more effective therapies and developing prognostic future relapse markers in AD.

Neural mechanisms underlying empathy during alcohol abstinence: evidence from connectome-based predictive modeling

Empathy impairments have been linked to alcohol dependence even during abstinent periods. Nonetheless, the neural underpinnings of abstinence-induced empathy deficits remain unclear. In this study, we employed connectome-based predictive modeling (CPM) by using whole brain resting-state functional connectivity (rs-FC) to predict empathy capability of abstinent alcoholics (n = 47) versus healthy controls (n = 59). In addition, the generalizability of the predictive model (i.e., one group treated as a training dataset and another one treated as a test dataset) was performed to determine whether healthy controls and abstinent alcoholics share common neural fingerprints of empathy. Our results showed that abstinent alcoholics relative to healthy controls had decreased empathy capacity. Although no predictive models were observed in the abstinence group, we found that individual empathy scores in the healthy group can be reliably predicted by functional connectivity from the default mode network (DMN) to the sensorimotor network (SMN), occipital network, and cingulo-opercular network (CON). Moreover, the identified connectivity fingerprints of healthy controls could be generalized to predict empathy in the abstinence group. These findings indicate that neural circuits accounting for empathy may be disrupted by alcohol use and the impaired degree varies greatly among abstinent individuals. The large inter-individual variation may impede identification of the predictive model of empathy in alcohol abstainers.

Identifying Alcohol Use Disorder With Resting State Functional Magnetic Resonance Imaging Data: A Comparison Among Machine Learning Classifiers

Alcohol use disorder (AUD) is a burden to society creating social and health problems. Detection of AUD and its effects on the brain are difficult to assess. This problem is enhanced by the comorbid use of other substances such as nicotine that has been present in previous studies. Recent machine learning algorithms have raised the attention of researchers as a useful tool in studying and detecting AUD. This work uses AUD and controls samples free of any other substance use to assess the performance of a set of commonly used machine learning classifiers detecting AUD from resting state functional network connectivity (rsFNC) derived from independent component analysis. The cohort used included 51 alcohol dependent subjects and 51 control subjects. Despite alcohol, none of the 102 subjects reported use of nicotine, cannabis or any other dependence or habit formation substance. Classification features consisted of whole brain rsFNC estimates undergoing a feature selection process using a random forest approach. Features were then fed to 10 different machine learning classifiers to be evaluated based on their classification performance. A neural network classifier showed the highest performance with an area under the curve (AUC) of 0.79. Other good performers with similar AUC scores were logistic regression, nearest neighbor, and support vector machine classifiers. The worst results were obtained with Gaussian process and quadratic discriminant analysis. The feature selection outcome pointed to functional connections between visual, sensorimotor, executive control, reward, and salience networks as the most relevant for classification. We conclude that AUD can be identified using machine learning classifiers in the absence of nicotine comorbidity.

Identifying alcohol misuse biotypes from neural connectivity markers and concurrent genetic associations

Alcohol use behaviors are highly heterogeneous, posing significant challenges to etiologic research of alcohol use disorder (AUD). Magnetic resonance imaging (MRI) provides intermediate endophenotypes in characterizing problem alcohol use and assessing the genetic architecture of addictive behavior. We used connectivity features derived from resting state functional MRI to subtype alcohol misuse (AM) behavior. With a machine learning pipeline of feature selection, dimension reduction, clustering, and classification we identified three AM biotypes-mild, comorbid, and moderate AM biotypes (MIA, COA, and MOA)-from a Human Connectome Project (HCP) discovery sample (194 drinkers). The three groups and controls (397 non-drinkers) demonstrated significant differences in alcohol use frequency during the heaviest 12-month drinking period (MOA > MIA; COA > non-drinkers) and were distinguished by connectivity features involving the frontal, parietal, subcortical and default mode networks. Further, COA relative to MIA, MOA and controls endorsed significantly higher scores in antisocial personality. A genetic association study identified that an alcohol use and antisocial behavior related variant rs16930842 from LINC01414 was significantly associated with COA. Using a replication HCP sample (28 drinkers and 46 non-drinkers), we found that subtyping helped in classifying AM from controls (area under the curve or AUC = 0.70, P < 0.005) in comparison to classifiers without subtyping (AUC = 0.60, not significant) and successfully reproduced the genetic association. Together, the results suggest functional connectivities as important features in classifying AM subgroups and the utility of reducing the heterogeneity in connectivity features among AM subgroups in advancing the research of etiological neural markers of AUD.

Brain Network Allostasis after Chronic Alcohol Drinking Is Characterized by Functional Dedifferentiation and Narrowing

Alcohol use disorder (AUD) causes complex alterations in the brain that are poorly understood. The heterogeneity of drinking patterns and the high incidence of comorbid factors compromise mechanistic investigations in AUD patients. Here we used male Marchigian Sardinian alcohol-preferring (msP) rats, a well established animal model of chronic alcohol drinking, and a combination of longitudinal resting-state fMRI and manganese-enhanced MRI to provide objective measurements of brain connectivity and activity, respectively. We found that 1 month of chronic alcohol drinking changed the correlation between resting-state networks. The change was not homogeneous, resulting in the reorganization of pairwise interactions and a shift in the equilibrium of functional connections. We identified two fundamentally different forms of network reorganization. First is functional dedifferentiation, which is defined as a regional increase in neuronal activity and overall correlation, with a concomitant decrease in preferential connectivity between specific networks. Through this mechanism, occipital cortical areas lost their specific interaction with sensory-insular cortex, striatal, and sensorimotor networks. Second is functional narrowing, which is defined as an increase in neuronal activity and preferential connectivity between specific brain networks. Functional narrowing strengthened the interaction between striatal and prefrontocortical networks, involving the anterior insular, cingulate, orbitofrontal, prelimbic, and infralimbic cortices. Importantly, these two types of alterations persisted after alcohol discontinuation, suggesting that dedifferentiation and functional narrowing rendered persistent network states. Our results support the idea that chronic alcohol drinking, albeit at moderate intoxicating levels, induces an allostatic change in the brain functional connectivity that propagates into early abstinence.SIGNIFICANCE STATEMENT Excessive consumption of alcohol is positioned among the top five risk factors for disease and disability. Despite this priority, the transformations that the nervous system undergoes from an alcohol-naive state to a pathologic alcohol drinking are not well understood. In our study, we use an animal model with proven translational validity to study this transformation longitudinally. The results show that shortly after chronic alcohol consumption there is an increase in redundant activity shared by brain structures, and the specific communication shrinks to a set of pathways. This functional dedifferentiation and narrowing are not reversed immediately after alcohol withdrawal but persist during early abstinence. We causally link chronic alcohol drinking with an early and abstinence-persistent retuning of the functional equilibrium of the brain.

Multimodal neuroimaging of metabotropic glutamate 5 receptors and functional connectivity in alcohol use disorder

BACKGROUND

People recovering from alcohol use disorder (AUD) show altered resting brain connectivity. The metabotropic glutamate 5 (mGlu5) receptor is an important regulator of synaptic plasticity potentially linked with synchronized brain activity and a target of interest in treating AUD. The goal of this work was to assess potential relationships of brain connectivity at rest with mGlu5 receptor availability in people with AUD at two time points early in abstinence.

METHODS

Forty-eight image data sets were acquired with a multimodal neuroimaging battery that included resting-state functional magnetic resonance imaging (fMRI) and mGlu5 receptor positron emission tomography (PET) with the radiotracer [¹⁸ F]FPEB. Participants with AUD (n = 14) were scanned twice, at approximately 1 and 4 weeks after beginning supervised abstinence. [¹⁸ F]FPEB PET results were published previously. Primary comparisons of fMRI outcomes were performed between the AUD group and healthy controls (HCs; n = 23) and assessed changes over time within the AUD group. Relationships between resting-state connectivity measures and mGlu5 receptor availability were explored within groups.

RESULTS

Compared to HCs, global functional connectivity of the orbitofrontal cortex was higher in the AUD group at 4 weeks of abstinence (p = 0.003), while network-level functional connectivity within the default mode network (DMN) was lower (p < 0.04). Exploratory multimodal analyses showed that mGlu5 receptor availability was correlated with global connectivity across all brain regions (HCs, r = 0.41; AUD group at 1 week of abstinence, r = 0.50 and at 4 weeks, r = 0.46; all p < 0.0001). Furthermore, a component of cortical and striatal mGlu5 availability was correlated with connectivity between the DMN and salience networks in HCs (r = 0.60, p = 0.003) but not in the AUD group (p > 0.3).

CONCLUSIONS

These preliminary findings of altered global and network connectivity during the first month of abstinence from drinking may reflect the loss of efficient network function, while exploratory relationships with mGlu5 receptor availability suggest a potential glutamatergic relationship with network coherence.

Differentiating Individuals with and without Alcohol Use Disorder Using Resting-State fMRI Functional Connectivity of Reward Network, Neuropsychological Performance, and Impulsivity Measures

Individuals with alcohol use disorder (AUD) may manifest an array of neural and behavioral abnormalities, including altered brain networks, impaired neurocognitive functioning, and heightened impulsivity. Using multidomain measures, the current study aimed to identify specific features that can differentiate individuals with AUD from healthy controls (CTL), utilizing a random forests (RF) classification model. Features included fMRI-based resting-state functional connectivity (rsFC) across the reward network, neuropsychological task performance, and behavioral impulsivity scores, collected from thirty abstinent adult males with prior history of AUD and thirty CTL individuals without a history of AUD. It was found that the RF model achieved a classification accuracy of 86.67% (AUC = 93%) and identified key features of FC and impulsivity that significantly contributed to classifying AUD from CTL individuals. Impulsivity scores were the topmost predictors, followed by twelve rsFC features involving seventeen key reward regions in the brain, such as the ventral tegmental area, nucleus accumbens, anterior insula, anterior cingulate cortex, and other cortical and subcortical structures. Individuals with AUD manifested significant differences in impulsivity and alterations in functional connectivity relative to controls. Specifically, AUD showed heightened impulsivity and hypoconnectivity in nine connections across 13 regions and hyperconnectivity in three connections involving six regions. Relative to controls, visuo-spatial short-term working memory was also found to be impaired in AUD. In conclusion, specific multidomain features of brain connectivity, impulsivity, and neuropsychological performance can be used in a machine learning framework to effectively classify AUD individuals from healthy controls.

Abnormal Large-Scale Neuronal Network in High Myopia

Aim

Resting state functional magnetic resonance imaging (rs-fMRI) was used to analyze changes in functional connectivity (FC) within various brain networks and functional network connectivity (FNC) among various brain regions in patients with high myopia (HM).

Methods

rs-fMRI was used to scan 82 patients with HM (HM group) and 59 healthy control volunteers (HC group) matched for age, sex, and education level. Fourteen resting state networks (RSNs) were extracted, of which 11 were positive. Then, the FCs and FNCs of RSNs in HM patients were examined by independent component analysis (ICA).

Results

Compared with the HC group, FC in visual network 1 (VN1), dorsal attention network (DAN), auditory network 2 (AN2), visual network 3 (VN3), and sensorimotor network (SMN) significantly increased in the HM group. FC in default mode network 1 (DMN1) significantly decreased. Furthermore, some brain regions in default mode network 2 (DMN2), default mode network 3 (DMN3), auditory network 1 (AN1), executive control network (ECN), and significance network (SN) increased while others decreased. FNC analysis also showed that the network connection between the default mode network (DMN) and cerebellar network (CER) was enhanced in the HM group.

Conclusion

Compared with HCs, HM patients showed neural activity dysfunction within and between specific brain networks, particularly in the DMN and CER. Thus, HM patients may have deficits in visual, cognitive, and motor balance functions.

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Prediction of Problematic Smartphone Use: A Machine Learning Approach

While smartphone addiction is becoming a recent concern with the exponential increase in the number of smartphone users, it is difficult to predict problematic smartphone users based on the usage characteristics of individual smartphone users. This study aimed to explore the possibility of predicting smartphone addiction level with mobile phone log data. By Korea Internet and Security Agency (KISA), 29,712 respondents completed the Smartphone Addiction Scale developed in 2017. Integrating basic personal characteristics and smartphone usage information, the data were analyzed using machine learning techniques (decision tree, random forest, and Xgboost) in addition to hypothesis tests. In total, 27 variables were employed to predict smartphone addiction and the accuracy rate was the highest for the random forest (82.59%) model and the lowest for the decision tree model (74.56%). The results showed that users’ general information, such as age group, job classification, and sex did not contribute much to predicting their smartphone addiction level. The study can provide directions for future work on the detection of smartphone addiction with log-data, which suggests that more detailed smartphone’s log-data will enable more accurate results.

Accelerated Aging of the Amygdala in Alcohol Use Disorders: Relevance to the Dark Side of Addiction

Here we assessed changes in subcortical volumes in alcohol use disorder (AUD). A simple morphometry-based classifier (MC) was developed to identify subcortical volumes that distinguished 32 healthy controls (HCs) from 33 AUD patients, who were scanned twice, during early and later withdrawal, to assess the effect of abstinence on MC-features (Discovery cohort). We validated the novel classifier in an independent Validation cohort (19 AUD patients and 20 HCs). MC-accuracy reached 80% (Discovery) and 72% (Validation). MC features included the hippocampus, amygdala, cerebellum, putamen, corpus callosum, and brain stem, which were smaller and showed stronger age-related decreases in AUD than HCs, and the ventricles and cerebrospinal fluid, which were larger in AUD and older participants. The volume of the amygdala showed a positive association with anxiety and negative urgency in AUD. Repeated imaging during the third week of detoxification revealed slightly larger subcortical volumes in AUD patients, consistent with partial recovery during abstinence. The steeper age-associated volumetric reductions in stress- and reward-related subcortical regions in AUD are consistent with accelerated aging, whereas the amygdalar associations with negative urgency and anxiety in AUD patients support its involvement in the "dark side of addiction".

ISOMAP and machine learning algorithms for the construction of embedded functional connectivity networks of anatomically separated brain regions from resting state fMRI data of patients with Schizophrenia

We construct Functional Connectivity Networks (FCN) from resting state fMRI (rsfMRI) recordings towards the classification of brain activity between healthy and schizophrenic subjects using a publicly available dataset (the COBRE dataset) of 145 subjects (74 healthy controls and 71 schizophrenic subjects). First, we match the anatomy of the brain of each individual to the Desikan-Killiany brain atlas. Then, we use the conventional approach of correlating the parcellated time series to construct FCN and ISOMAP, a nonlinear manifold learning algorithm to produce low-dimensional embeddings of the correlation matrices. For the classification analysis, we computed five key local graph-theoretic measures of the FCN and used the LASSO and Random Forest (RF) algorithms for feature selection. For the classification we used standard linear Support Vector Machines. The classification performance is tested by a double cross-validation scheme (consisting of an outer and an inner loop of "Leave one out" cross-validation (LOOCV)). The standard cross-correlation methodology produced a classification rate of 73.1%, while ISOMAP resulted in 79.3%, thus providing a simpler model with a smaller number of features as chosen from LASSO and RF, namely the participation coefficient of the right thalamus and the strength of the right lingual gyrus.

Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research

By promising more accurate diagnostics and individual treatment recommendations, deep neural networks and in particular convolutional neural networks have advanced to a powerful tool in medical imaging. Here, we first give an introduction into methodological key concepts and resulting methodological promises including representation and transfer learning, as well as modelling domain-specific priors. After reviewing recent applications within neuroimaging-based psychiatric research, such as the diagnosis of psychiatric diseases, delineation of disease subtypes, normative modeling, and the development of neuroimaging biomarkers, we discuss current challenges. This includes for example the difficulty of training models on small, heterogeneous and biased data sets, the lack of validity of clinical labels, algorithmic bias, and the influence of confounding variables.

Quantitative Identification of Functional Connectivity Disturbances in Neuropsychiatric Lupus Based on Resting-State fMRI: A Robust Machine Learning Approach

Neuropsychiatric systemic lupus erythematosus (NPSLE) is an autoimmune entity comprised of heterogenous syndromes affecting both the peripheral and central nervous system. Research on the pathophysiological substrate of NPSLE manifestations, including functional neuroimaging studies, is extremely limited. The present study examined person-specific patterns of whole-brain functional connectivity in NPSLE patients (n = 44) and age-matched healthy control participants (n = 39). Static functional connectivity graphs were calculated comprised of connection strengths between 90 brain regions. These connections were subsequently filtered through rigorous surrogate analysis, a technique borrowed from physics, novel to neuroimaging. Next, global as well as nodal network metrics were estimated for each individual functional brain network and were input to a robust machine learning algorithm consisting of a random forest feature selection and nested cross-validation strategy. The proposed pipeline is data-driven in its entirety, and several tests were performed in order to ensure model robustness. The best-fitting model utilizing nodal graph metrics for 11 brain regions was associated with 73.5% accuracy (74.5% sensitivity and 73% specificity) in discriminating NPSLE from healthy individuals with adequate statistical power. Closer inspection of graph metric values suggested an increased role within the functional brain network in NSPLE (indicated by higher nodal degree, local efficiency, betweenness centrality, or eigenvalue efficiency) as compared to healthy controls for seven brain regions and a reduced role for four areas. These findings corroborate earlier work regarding hemodynamic disturbances in these brain regions in NPSLE. The validity of the results is further supported by significant associations of certain selected graph metrics with accumulated organ damage incurred by lupus, with visuomotor performance and mental flexibility scores obtained independently from NPSLE patients.

Towards a brain-based predictome of mental illness

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

A NEW CAD SYSTEM FOR BREAST CANCER CLASSIFICATION USING DISCRIMINATION POWER ANALYSIS OF WAVELET’S COEFFICIENTS AND SUPPORT VECTOR MACHINE

The Computer-Aided Diagnostic (CAD) system is an important tool that helps radiologists to provide a second opinion for the early detection of breast cancer and therefore, aids to reduce the mortality rates. In this work, we try to develop a new (CAD) system to classify mammograms into benign or malignant. The proposed system consists of three main steps. The preprocessing stage consists of noise filtering, elimination of unwanted objects and suppressing the pectoral muscle. The Seeded Region Growing (SRG) segmentation technique is applied in a triangular region that contains the pectoral muscle to localize it and extract the region of interest (ROI). The features extraction step is performed by applying the discrete wavelet transform (DWT) to each obtained ROI, and the most discriminating coefficients are selected using the discrimination power analysis (DPA) method. Finally, the classification is carried out by the support vector machine (SVM), artificial neural networks (ANN), random forest (RF) and Naive Bayes (NB) classifiers. The evaluation of the proposed system on the mini-MIAS database shows its effectiveness compared to other recently published CAD systems, and a classification accuracy of about 99.41% with the SVM classifier was obtained.

Random Forest Classification of Alcohol Use Disorder Using EEG Source Functional Connectivity, Neuropsychological Functioning, and Impulsivity Measures

: Individuals with alcohol use disorder (AUD) manifest a variety of impairments that can be attributed to alterations in specific brain networks. The current study aims to identify features of EEG-based functional connectivity, neuropsychological performance, and impulsivity that can classify individuals with AUD (N = 30) from unaffected controls (CTL, N = 30) using random forest classification. The features included were: (i) EEG source functional connectivity (FC) of the default mode network (DMN) derived using eLORETA algorithm, (ii) neuropsychological scores from the Tower of London test (TOLT) and the visual span test (VST), and (iii) impulsivity factors from the Barratt impulsiveness scale (BIS). The random forest model achieved a classification accuracy of 80% and identified 29 FC connections (among 66 connections per frequency band), 3 neuropsychological variables from VST (total number of correctly performed trials in forward and backward sequences and average time for correct trials in forward sequence) and all four impulsivity scores (motor, non-planning, attentional, and total) as significantly contributing to classifying individuals as either AUD or CTL. Although there was a significant age difference between the groups, most of the top variables that contributed to the classification were not significantly correlated with age. The AUD group showed a predominant pattern of hyperconnectivity among 25 of 29 significant connections, indicating aberrant network functioning during resting state suggestive of neural hyperexcitability and impulsivity. Further, parahippocampal hyperconnectivity with other DMN regions was identified as a major hub region dysregulated in AUD (13 connections overall), possibly due to neural damage from chronic drinking, which may give rise to cognitive impairments, including memory deficits and blackouts. Furthermore, hypoconnectivity observed in four connections (prefrontal nodes connecting posterior right-hemispheric regions) may indicate a weaker or fractured prefrontal connectivity with other regions, which may be related to impaired higher cognitive functions. The AUD group also showed poorer memory performance on the VST task and increased impulsivity in all factors compared to controls. Features from all three domains had significant associations with one another. These results indicate that dysregulated neural connectivity across the DMN regions, especially relating to hyperconnected parahippocampal hub as well as hypoconnected prefrontal hub, may potentially represent neurophysiological biomarkers of AUD, while poor visual memory performance and heightened impulsivity may serve as cognitive-behavioral indices of AUD.

Random Forest Classification of Alcohol Use Disorder Using fMRI Functional Connectivity, Neuropsychological Functioning, and Impulsivity Measures

Individuals with alcohol use disorder (AUD) are known to manifest a variety of neurocognitive impairments that can be attributed to alterations in specific brain networks. The current study aims to identify specific features of brain connectivity, neuropsychological performance, and impulsivity traits that can classify adult males with AUD (n = 30) from healthy controls (CTL, n = 30) using the Random Forest (RF) classification method. The predictor variables were: (i) fMRI-based within-network functional connectivity (FC) of the Default Mode Network (DMN), (ii) neuropsychological scores from the Tower of London Test (TOLT), and the Visual Span Test (VST), and (iii) impulsivity factors from the Barratt Impulsiveness Scale (BIS). The RF model, with a classification accuracy of 76.67%, identified fourteen DMN connections, two neuropsychological variables (memory span and total correct scores of the forward condition of the VST), and all impulsivity factors as significantly important for classifying participants into either the AUD or CTL group. Specifically, the AUD group manifested hyperconnectivity across the bilateral anterior cingulate cortex and the prefrontal cortex as well as between the bilateral posterior cingulate cortex and the left inferior parietal lobule, while showing hypoconnectivity in long-range anterior-posterior and interhemispheric long-range connections. Individuals with AUD also showed poorer memory performance and increased impulsivity compared to CTL individuals. Furthermore, there were significant associations among FC, impulsivity, neuropsychological performance, and AUD status. These results confirm the previous findings that alterations in specific brain networks coupled with poor neuropsychological functioning and heightened impulsivity may characterize individuals with AUD, who can be efficiently identified using classification algorithms such as Random Forest.

A Novel CGM Metric-Gradient and Combining Mean Sensor Glucose Enable to Improve the Prediction of Nocturnal Hypoglycemic Events in Patients with Diabetes

Nocturnal hypoglycemia is a serious complication of insulin-treated diabetes, and it is often asymptomatic. A novel CGM metric-gradient was proposed in this paper, and a method of combining mean sensor glucose (MSG) and gradient was presented for the prediction of nocturnal hypoglycemia. For this purpose, the data from continuous glucose monitoring (CGM) encompassing 1,921 patients with diabetes were analyzed, and a total of 302 nocturnal hypoglycemic events were recorded. The MSG and gradient values were calculated, respectively, and then combined as a new metric (i.e., MSG+gradient). In addition, the prediction was conducted by four algorithms, namely, logistic regression, support vector machine, random forest, and long short-term memory. The results revealed that the gradient of CGM showed a downward trend before hypoglycemic events happened. Additionally, the results indicated that the specificity and sensitivity based on the proposed method were better than the conventional metrics of low blood glucose index (LBGI), coefficient of variation (CV), mean absolute glucose (MAG), lability index (LI), etc., and the complex metrics of MSG+LBGI, MSG+CV, MSG+MAG, and MSG+LI, etc. Specifically, the specificity and sensitivity were greater than 96.07% and 96.03% at the prediction horizon of 15 minutes and greater than 87.79% and 90.07% at the prediction horizon of 30 minutes when the proposed method was adopted to predict nocturnal hypoglycemic events in the aforementioned four algorithms. Therefore, the proposed method of combining MSG and gradient may enable to improve the prediction of nocturnal hypoglycemic events. Future studies are warranted to confirm the validity of this metric.

A Novel Deep-Learning-Based Bug Severity Classification Technique Using Convolutional Neural Networks and Random Forest with Boosting

The accurate severity classification of a bug report is an important aspect of bug fixing. The bug reports are submitted into the bug tracking system with high speed, and owing to this, bug repository size has been increasing at an enormous rate. This increased bug repository size introduces biases in the bug triage process. Therefore, it is necessary to classify the severity of a bug report to balance the bug triaging process. Previously, many machine learning models were proposed for automation of bug severity classification. The accuracy of these models is not up to the mark because they do not extract the important feature patterns for learning the classifier. This paper proposes a novel deep learning model for multiclass severity classification called Bug Severity classification to address these challenges by using a Convolutional Neural Network and Random forest with Boosting (BCR). This model directly learns the latent and highly representative features. Initially, the natural language techniques preprocess the bug report text, and then n-gram is used to extract the features. Further, the Convolutional Neural Network extracts the important feature patterns of respective severity classes. Lastly, the random forest with boosting classifies the multiple bug severity classes. The average accuracy of the proposed model is 96.34% on multiclass severity of five open source projects. The average F-measures of the proposed BCR and the existing approach were 96.43% and 84.24%, respectively, on binary class severity classification. The results prove that the proposed BCR approach enhances the performance of bug severity classification over the state-of-the-art techniques.

Alcohol in the Aging Brain - The Interplay Between Alcohol Consumption, Cognitive Decline and the Cardiovascular System

As our society grows older new challenges for medicine and healthcare emerge. Age-related changes of the body have been observed in essential body functions, particularly in the loco-motor system, in the cardiovascular system and in cognitive functions concerning both brain plasticity and changes in behavior. Nutrition and lifestyle, such as nicotine intake and chronic alcohol consumption, also contribute to biological changes in the brain. This review addresses the effect of alcohol consumption on cognitive decline, changes in brain plasticity in the aging brain and on cardiovascular health in aging. Thus, studies on the interplay of chronic alcohol intake and either cognitive decline or cognitive preservation are outlined. Because of the inconsistency in the literature of whether alcohol consumption preserves cognitive functions in the aging brain or whether it accelerates cognitive decline, it is crucial to consider individual contributing factors such as culture, health and lifestyle in future studies.

Quantifying performance of machine learning methods for neuroimaging data

Machine learning is increasingly being applied to neuroimaging data. However, most machine learning algorithms have not been designed to accommodate neuroimaging data, which typically has many more data points than subjects, in addition to multicollinearity and low signal-to-noise. Consequently, the relative efficacy of different machine learning regression algorithms for different types of neuroimaging data are not known. Here, we sought to quantify the performance of a variety of machine learning algorithms for use with neuroimaging data with various sample sizes, feature set sizes, and predictor effect sizes. The contribution of additional machine learning techniques - embedded feature selection and bootstrap aggregation (bagging) - to model performance was also quantified. Five machine learning regression methods - Gaussian Process Regression, Multiple Kernel Learning, Kernel Ridge Regression, the Elastic Net and Random Forest, were examined with both real and simulated MRI data, and in comparison to standard multiple regression. The different machine learning regression algorithms produced varying results, which depended on sample size, feature set size, and predictor effect size. When the effect size was large, the Elastic Net, Kernel Ridge Regression and Gaussian Process Regression performed well at most sample sizes and feature set sizes. However, when the effect size was small, only the Elastic Net made accurate predictions, but this was limited to analyses with sample sizes greater than 400. Random Forest also produced a moderate performance for small effect sizes, but could do so across all sample sizes. Machine learning techniques also improved prediction accuracy for multiple regression. These data provide empirical evidence for the differential performance of various machines on neuroimaging data, which are dependent on number of sample size, features and effect size.

Resting state connectivity best predicts alcohol use severity in moderate to heavy alcohol users

BACKGROUND

In the United States, 13% of adults are estimated to have alcohol use disorder (AUD). Most studies examining the neurobiology of AUD treat individuals with this disorder as a homogeneous group; however, the theories of the neurocircuitry of AUD call for a quantitative and dimensional approach. Previous imaging studies find differences in brain structure, function, and resting-state connectivity in AUD, but few use a multimodal approach to understand the association between severity of alcohol use and the brain differences.

METHODS

Adults (ages 22-60) with problem drinking patterns (n = 59) completed a behavioral and neuroimaging protocol at the National Institutes of Health. Alcohol severity was quantified with the Alcohol Use Disorders Identification Test (AUDIT). In a 3 T MRI scanner, participants underwent a structural MRI as well as resting-state, monetary incentive delay, and face matching fMRI scans. Machine learning was applied and trained using the neural data from MRI scanning. The model was tested for generalizability in a validation sample (n = 24).

RESULTS

The resting state-connectivity features model best predicted AUD severity in the naïve sample, compared to task fMRI, structural MRI, combined MRI features, or demographic features. Network connectivity features between salience network, default mode network, executive control network, and sensory networks explained 33% of the variance associated with AUDIT in this model.

CONCLUSIONS

These findings indicate that the neural effects of AUD vary according to severity. Our results emphasize the utility of resting state fMRI as a neuroimaging biomarker for quantitative clinical evaluation of AUD.

Novel Machine Learning Identifies Brain Patterns Distinguishing Diagnostic Membership of Human Immunodeficiency Virus, Alcoholism, and Their Comorbidity of Individuals

The incidence of alcohol use disorder (AUD) in human immunodeficiency virus (HIV) infection is twice that of the rest of the population. This study documents complex radiologically identified, neuroanatomical effects of AUD+HIV comorbidity by identifying structural brain systems that predicted diagnosis on an individual basis. Applying novel machine learning analysis to 549 participants (199 control subjects, 222 with AUD, 68 with HIV, 60 with AUD+HIV), 298 magnetic resonance imaging brain measurements were automatically reduced to small subsets per group. Significance of each diagnostic pattern was inferred from its accuracy in predicting diagnosis and performance on six cognitive measures. While all three diagnostic patterns predicted the learning and memory score, the AUD+HIV pattern was the largest and had the highest predication accuracy (78.1%). Providing a roadmap for analyzing large, multimodal datasets, the machine learning analysis revealed imaging phenotypes that predicted diagnostic membership of magnetic resonance imaging scans of individuals with AUD, HIV, and their comorbidity.

A Review of the Potential Mechanisms of Action of Baclofen in Alcohol Use Disorder

Baclofen, a GABA-B receptor agonist, is a promising treatment for alcohol use disorder (AUD). Its mechanism of action in this condition is unknown. GABA-B receptors interact with many biological systems potentially involved in AUD, including transduction pathways and neurotransmitter systems. Preclinical studies have shown that GABA-B receptors are involved in memory storage and retrieval, reward, motivation, mood and anxiety; neuroimaging studies in humans show that baclofen produces region-specific alterations in cerebral activity; GABA-B receptor activation may have neuroprotective effects; baclofen also has anti-inflammatory properties that may be of interest in the context of addiction. However, none of these biological effects fully explain the mechanism of action of baclofen in AUD. Data from clinical studies have provided a certain number of elements which may be useful for the comprehension of its mechanism of action: baclofen typically induces a state of indifference toward alcohol; the effective dose of baclofen in AUD is extremely variable from one patient to another; higher treatment doses correlate with the severity of the addiction; many of the side effects of baclofen resemble those of alcohol, raising the possibility that baclofen acts as a substitution drug; usually, however, there is no tolerance to the effects of baclofen during long-term AUD treatment. In the present article, the biological effects of baclofen are reviewed in the light of its clinical effects in AUD, assuming that, in many instances, clinical effects can be reliable indicators of underlying biological processes. In conclusion, it is proposed that baclofen may suppress the Pavlovian association between cues and rewards through an action in a critical part of the dopaminergic network (the amygdala), thereby normalizing the functional connectivity in the reward network. It is also proposed that this action of baclofen is made possible by the fact that baclofen and alcohol act on similar brain systems in certain regions of the brain.