Predicting risk for Alcohol Use Disorder using longitudinal data with multimodal biomarkers and family history: a machine learning study

Neuroimaging and natural language processing-based classification of suicidal thoughts in major depressive disorder

Suicide is a growing public health problem around the world. The most important risk factor for suicide is underlying psychiatric illness, especially depression. Detailed classification of suicide in patients with depression can greatly enhance personalized suicide control efforts. This study used unstructured psychiatric charts and brain magnetic resonance imaging (MRI) records from a psychiatric outpatient clinic to develop a machine learning-based suicidal thought classification model. The study included 152 patients with new depressive episodes for development and 58 patients from a geographically different hospital for validation. We developed an eXtreme Gradient Boosting (XGBoost)-based classification models according to the combined types of data: independent components-map weightings from brain T1-weighted MRI and topic probabilities from clinical notes. Specifically, we used 5 psychiatric symptom topics and 5 brain networks for models. Anxiety and somatic symptoms topics were significantly more common in the suicidal group, and there were group differences in the default mode and cortical midline networks. The clinical symptoms plus structural brain patterns model had the highest area under the receiver operating characteristic curve (0.794) versus the clinical notes only and brain MRI only models (0.748 and 0.738, respectively). The results were consistent across performance metrics and external validation. Our findings suggest that focusing on personalized neuroimaging and natural language processing variables improves evaluation of suicidal thoughts.

Enhancing Aviation Safety through AI-Driven Mental Health Management for Pilots and Air Traffic Controllers

This article provides an overview of the mental health challenges faced by pilots and air traffic controllers (ATCs), whose stressful professional lives may negatively impact global flight safety and security. The adverse effects of mental health disorders on their flight performance pose a particular safety risk, especially in sudden unexpected startle situations. Therefore, the early detection, prediction and prevention of mental health deterioration in pilots and ATCs, particularly among those at high risk, are crucial to minimize potential air crash incidents caused by human factors. Recent research in artificial intelligence (AI) demonstrates the potential of machine and deep learning, edge and cloud computing, virtual reality and wearable multimodal physiological sensors for monitoring and predicting mental health disorders. Longitudinal monitoring and analysis of pilots' and ATCs physiological, cognitive and behavioral states could help predict individuals at risk of undisclosed or emerging mental health disorders. Utilizing AI tools and methodologies to identify and select these individuals for preventive mental health training and interventions could be a promising and effective approach to preventing potential air crash accidents attributed to human factors and related mental health problems. Based on these insights, the article advocates for the design of a multidisciplinary mental healthcare ecosystem in modern aviation using AI tools and technologies, to foster more efficient and effective mental health management, thereby enhancing flight safety and security standards. This proposed ecosystem requires the collaboration of multidisciplinary experts, including psychologists, neuroscientists, physiologists, psychiatrists, etc. to address these challenges in modern aviation.

Gene-Based Predictive Modelling for Enhanced Detection of Systemic Lupus Erythematosus Using CNN-Based DL Algorithm

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune disease that presents with a diverse array of clinical signs and unpredictable disease progression. Conventional diagnostic methods frequently fall short in terms of sensitivity and specificity, which can result in delayed diagnosis and less-than-optimal management. In this study, we introduce a novel approach for improving the identification of SLE through the use of gene-based predictive modelling and Stacked deep learning classifiers. The study proposes a new method for diagnosing SLE using Stacked Deep Learning Classifiers (SDLC) trained on Gene Expression Omnibus (GEO) database data. By combining transcriptomic data from GEO with clinical features and laboratory results, the SDLC model achieves a remarkable accuracy value of 0.996, outperforming traditional methods. Individual models within the SDLC, such as SBi-LSTM and ACNN, achieved accuracies of 92% and 95%, respectively. The SDLC's ensemble learning approach allows for identifying complex patterns in multi-modal data, enhancing accuracy in diagnosing SLE. This study emphasises the potential of deep learning methods, in conjunction with open repositories like GEO, to advance the diagnosis and management of SLE. Overall, this research shows strong performance and potential for improving precision medicine in managing SLE.

Vulnerable at rest? A resting-state EEG study and psychosocial factors of young adult offspring of alcohol-dependent parents

BACKGROUND

Offspring of parents with alcohol use disorder (AUD) are more susceptible to developing AUD, with an estimated heritability of around 50%. Vulnerability to AUD in first-degree relatives is influenced by biological factors, such as spontaneous brain activity, and high-risk psychosocial characteristics. However, existing resting-state EEG studies in AUD offspring have shown inconsistent findings regarding theta, alpha, and beta band frequencies. Additionally, research consistently demonstrates an increased risk of internalizing and externalizing disorders, self-regulation difficulties, and interpersonal issues among AUD offspring.

METHODS

This study aimed to investigate the absolute power of theta, alpha, and beta frequencies in young adult offspring with a family history of AUD compared to individuals without family history. The psychosocial profiles of the offspring were also examined in relation to individuals without a family history of AUD. Furthermore, the study sought to explore the potential association between differences in frequency bands and psychosocial variables. Resting-state EEG recordings were obtained from 31 young adult healthy offspring of alcohol-dependent individuals and 43 participants with no family history of AUD (age range: 16-25 years). Participants also completed self-report questionnaires assessing anxiety and depressive symptoms, impulsivity, emotion regulation, and social involvement.

RESULTS

The results revealed no significant differences in spontaneous brain activity between the offspring and participants without a family history of AUD. However, in terms of psychosocial factors, the offspring exhibited significantly lower social involvement than the control group.

CONCLUSIONS

This study does not provide evidence suggesting vulnerability in offspring based on differences in spontaneous brain activity. Moreover, this investigation highlights the importance of interventions aimed at enhancing social connections in offspring. Such interventions can not only reduce the risk of developing AUD, given its strong association with increased feelings of loneliness but also improve the overall well-being of the offspring.

Multimodal-based machine learning approach to classify features of internet gaming disorder and alcohol use disorder: A sensor-level and source-level resting-state electroencephalography activity and neuropsychological study

OBJECTIVES

Addictions have recently been classified as substance use disorder (SUD) and behavioral addiction (BA), but the concept of BA is still debatable. Therefore, it is necessary to conduct further neuroscientific research to understand the mechanisms of BA to the same extent as SUD. The present study used machine learning (ML) algorithms to investigate the neuropsychological and neurophysiological aspects of addictions in individuals with internet gaming disorder (IGD) and alcohol use disorder (AUD).

METHODS

We developed three models for distinguishing individuals with IGD from those with AUD, individuals with IGD from healthy controls (HCs), and individuals with AUD from HCs using ML algorithms, including L1-norm support vector machine, random forest, and L1-norm logistic regression (LR). Three distinct feature sets were used for model training: a unimodal-electroencephalography (EEG) feature set combined with sensor- and source-level feature; a unimodal-neuropsychological feature (NF) set included sex, age, depression, anxiety, impulsivity, and general cognitive function, and a multimodal (EEG + NF) feature set.

RESULTS

The LR model with the multimodal feature set used for the classification of IGD and AUD outperformed the other models (accuracy: 0.712). The important features selected by the model highlighted that the IGD group had differential delta and beta source connectivity between right intrahemispheric regions and distinct sensor-level EEG activities. Among the NFs, sex and age were the important features for good model performance.

CONCLUSIONS

Using ML techniques, we demonstrated the neurophysiological and neuropsychological similarities and differences between IGD (a BA) and AUD (a SUD).

Chronic Ethanol Exposure Produces Persistent Impairment in Cognitive Flexibility and Decision Signals in the Striatum

Lack of cognitive flexibility is a hallmark of substance use disorders and has been associated with drug-induced synaptic plasticity in the dorsomedial striatum (DMS). Yet the possible impact of altered plasticity on real-time striatal neural dynamics during decision-making is unclear. Here, we identified persistent impairments induced by chronic ethanol (EtOH) exposure on cognitive flexibility and striatal decision signals. After a substantial withdrawal period from prior EtOH vapor exposure, male, but not female, rats exhibited reduced adaptability and exploratory behavior during a dynamic decision-making task. Reinforcement learning models showed that prior EtOH exposure enhanced learning from rewards over omissions. Notably, neural signals in the DMS related to the decision outcome were enhanced, while those related to choice and choice-outcome conjunction were reduced, in EtOH-treated rats compared to the controls. These findings highlight the profound impact of chronic EtOH exposure on adaptive decision-making, pinpointing specific changes in striatal representations of actions and outcomes as underlying mechanisms for cognitive deficits.

Genomic Machine Learning Meta-regression: Insights on Associations of Study Features With Reported Model Performance

Many studies have been conducted with the goal of correctly predicting diagnostic status of a disorder using the combination of genomic data and machine learning. It is often hard to judge which components of a study led to better results and whether better reported results represent a true improvement or an uncorrected bias inflating performance. We extracted information about the methods used and other differentiating features in genomic machine learning models. We used these features in linear regressions predicting model performance. We tested for univariate and multivariate associations as well as interactions between features. Of the models reviewed, 46% used feature selection methods that can lead to data leakage. Across our models, the number of hyperparameter optimizations reported, data leakage due to feature selection, model type, and modeling an autoimmune disorder were significantly associated with an increase in reported model performance. We found a significant, negative interaction between data leakage and training size. Our results suggest that methods susceptible to data leakage are prevalent among genomic machine learning research, resulting in inflated reported performance. Best practice guidelines that promote the avoidance and recognition of data leakage may help the field avoid biased results.

The Collaborative Study on the Genetics of Alcoholism: Overview

Alcohol use disorders (AUD) are commonly occurring, heritable and polygenic disorders with etiological origins in the brain and the environment. To outline the causes and consequences of alcohol-related milestones, including AUD, and their related psychiatric comorbidities, the Collaborative Study on the Genetics of Alcoholism (COGA) was launched in 1989 with a gene-brain-behavior framework. COGA is a family based, diverse (~25% self-identified African American, ~52% female) sample, including data on 17,878 individuals, ages 7-97 years, in 2246 families of which a proportion are densely affected for AUD. All participants responded to questionnaires (e.g., personality) and the Semi-Structured Assessment for the Genetics of Alcoholism (SSAGA) which gathers information on psychiatric diagnoses, conditions and related behaviors (e.g., parental monitoring). In addition, 9871 individuals have brain function data from electroencephalogram (EEG) recordings while 12,009 individuals have been genotyped on genome-wide association study (GWAS) arrays. A series of functional genomics studies examine the specific cellular and molecular mechanisms underlying AUD. This overview provides the framework for the development of COGA as a scientific resource in the past three decades, with individual reviews providing in-depth descriptions of data on and discoveries from behavioral and clinical, brain function, genetic and functional genomics data. The value of COGA also resides in its data sharing policies, its efforts to communicate scientific findings to the broader community via a project website and its potential to nurture early career investigators and to generate independent research that has broadened the impact of gene-brain-behavior research into AUD.

AUD-DSS: a decision support system for early detection of patients with alcohol use disorder

BACKGROUND

Alcohol use disorder (AUD) causes significant morbidity, mortality, and injuries. According to reports, approximately 5% of all registered deaths in Denmark could be due to AUD. The problem is compounded by the late identification of patients with AUD, a situation that can cause enormous problems, from psychological to physical to economic problems. Many individuals suffering from AUD never undergo specialist treatment during their addiction due to obstacles such as taboo and the poor performance of current screening tools. Therefore, there is a lack of rapid intervention. This can be mitigated by the early detection of patients with AUD. A clinical decision support system (DSS) powered by machine learning (ML) methods can be used to diagnose patients' AUD status earlier.

METHODS

This study proposes an effective AUD prediction model (AUDPM), which can be used in a DSS. The proposed model consists of four distinct components: (1) imputation to address missing values using the k-nearest neighbours approach, (2) recursive feature elimination with cross validation to select the most relevant subset of features, (3) a hybrid synthetic minority oversampling technique-edited nearest neighbour approach to remove noise and balance the distribution of the training data, and (4) an ML model for the early detection of patients with AUD. Two data sources, including a questionnaire and electronic health records of 2571 patients, were collected from Odense University Hospital in the Region of Southern Denmark for the AUD-Dataset. Then, the AUD-Dataset was used to build ML models. The results of different ML models, such as support vector machine, K-nearest neighbour, decision tree, random forest, and extreme gradient boosting, were compared. Finally, a combination of all these models in an ensemble learning approach was selected for the AUDPM.

RESULTS

The results revealed that the proposed ensemble AUDPM outperformed other single models and our previous study results, achieving 0.96, 0.94, 0.95, and 0.97 precision, recall, F1-score, and accuracy, respectively. In addition, we designed and developed an AUD-DSS prototype.

CONCLUSION

It was shown that our proposed AUDPM achieved high classification performance. In addition, we identified clinical factors related to the early detection of patients with AUD. The designed AUD-DSS is intended to be integrated into the existing Danish health care system to provide novel information to clinical staff if a patient shows signs of harmful alcohol use; in other words, it gives staff a good reason for having a conversation with patients for whom a conversation is relevant.

Predictive risk markers in alcoholism

The medical disorders of alcoholism rank among the leading public health problems worldwide and the need for predictive and prognostic risk markers for assessing alcohol use disorders (AUD) has been widely acknowledged. Early-phase detection of problem drinking and associated tissue toxicity are important prerequisites for timely initiations of appropriate treatments and improving patient's committing to the objective of reducing drinking. Recent advances in clinical chemistry have provided novel approaches for a specific detection of heavy drinking through assays of unique ethanol metabolites, phosphatidylethanol (PEth) or ethyl glucuronide (EtG). Carbohydrate-deficient transferrin (CDT) measurements can be used to indicate severe alcohol problems. Hazardous drinking frequently manifests as heavy episodic drinking or in combinations with other unfavorable lifestyle factors, such as smoking, physical inactivity, poor diet or adiposity, which aggravate the metabolic consequences of alcohol intake in a supra-additive manner. Such interactions are also reflected in multiple disease outcomes and distinct abnormalities in biomarkers of liver function, inflammation and oxidative stress. Use of predictive biomarkers either alone or as part of specifically designed biological algorithms helps to predict both hepatic and extrahepatic morbidity in individuals with such risk factors. Novel approaches for assessing progression of fibrosis, a major determinant of prognosis in AUD, have also been made available. Predictive algorithms based on the combined use of biomarkers and clinical observations may prove to have a major impact on clinical decisions to detect AUD in early pre-symptomatic stages, stratify patients according to their substantially different disease risks and predict individual responses to treatment.

Identification of clinical factors related to prediction of alcohol use disorder from electronic health records using feature selection methods

BACKGROUND

High dimensionality in electronic health records (EHR) causes a significant computational problem for any systematic search for predictive, diagnostic, or prognostic patterns. Feature selection (FS) methods have been indicated to be effective in feature reduction as well as in identifying risk factors related to prediction of clinical disorders. This paper examines the prediction of patients with alcohol use disorder (AUD) using machine learning (ML) and attempts to identify risk factors related to the diagnosis of AUD.

METHODS

A FS framework consisting of two operational levels, base selectors and ensemble selectors. The first level consists of five FS methods: three filter methods, one wrapper method, and one embedded method. Base selector outputs are aggregated to develop four ensemble FS methods. The outputs of FS method were then fed into three ML algorithms: support vector machine (SVM), K-nearest neighbor (KNN), and random forest (RF) to compare and identify the best feature subset for the prediction of AUD from EHRs.

RESULTS

In terms of feature reduction, the embedded FS method could significantly reduce the number of features from 361 to 131. In terms of classification performance, RF based on 272 features selected by our proposed ensemble method (Union FS) with the highest accuracy in predicting patients with AUD, 96%, outperformed all other models in terms of AUROC, AUPRC, Precision, Recall, and F1-Score. Considering the limitations of embedded and wrapper methods, the best overall performance was achieved by our proposed Union Filter FS, which reduced the number of features to 223 and improved Precision, Recall, and F1-Score in RF from 0.77, 0.65, and 0.71 to 0.87, 0.81, and 0.84, respectively. Our findings indicate that, besides gender, age, and length of stay at the hospital, diagnosis related to digestive organs, bones, muscles and connective tissue, and the nervous systems are important clinical factors related to the prediction of patients with AUD.

CONCLUSION

Our proposed FS method could improve the classification performance significantly. It could identify clinical factors related to prediction of AUD from EHRs, thereby effectively helping clinical staff to identify and treat AUD patients and improving medical knowledge of the AUD condition. Moreover, the diversity of features among female and male patients as well as gender disparity were investigated using FS methods and ML techniques.

Multimodal machine learning in precision health: A scoping review

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.

RNA biomarkers for alcohol use disorder

Alcohol use disorder (AUD) is highly prevalent and one of the leading causes of disability in the US and around the world. There are some molecular biomarkers of heavy alcohol use and liver damage which can suggest AUD, but these are lacking in sensitivity and specificity. AUD treatment involves psychosocial interventions and medications for managing alcohol withdrawal, assisting in abstinence and reduced drinking (naltrexone, acamprosate, disulfiram, and some off-label medications), and treating comorbid psychiatric conditions (e.g., depression and anxiety). It has been suggested that various patient groups within the heterogeneous AUD population would respond more favorably to specific treatment approaches. For example, there is some evidence that so-called reward-drinkers respond better to naltrexone than acamprosate. However, there are currently no objective molecular markers to separate patients into optimal treatment groups or any markers of treatment response. Objective molecular biomarkers could aid in AUD diagnosis and patient stratification, which could personalize treatment and improve outcomes through more targeted interventions. Biomarkers of treatment response could also improve AUD management and treatment development. Systems biology considers complex diseases and emergent behaviors as the outcome of interactions and crosstalk between biomolecular networks. A systems approach that uses transcriptomic (or other -omic data, e.g., methylome, proteome, metabolome) can capture genetic and environmental factors associated with AUD and potentially provide sensitive, specific, and objective biomarkers to guide patient stratification, prognosis of treatment response or relapse, and predict optimal treatments. This Review describes and highlights state-of-the-art research on employing transcriptomic data and artificial intelligence (AI) methods to serve as molecular biomarkers with the goal of improving the clinical management of AUD. Considerations about future directions are also discussed.

Clinical, environmental, and genetic risk factors for substance use disorders: characterizing combined effects across multiple cohorts

Substance use disorders (SUDs) incur serious social and personal costs. The risk for SUDs is complex, with risk factors ranging from social conditions to individual genetic variation. We examined whether models that include a clinical/environmental risk index (CERI) and polygenic scores (PGS) are able to identify individuals at increased risk of SUD in young adulthood across four longitudinal cohorts for a combined sample of N = 15,134. Our analyses included participants of European (NEUR = 12,659) and African (NAFR = 2475) ancestries. SUD outcomes included: (1) alcohol dependence, (2) nicotine dependence; (3) drug dependence, and (4) any substance dependence. In the models containing the PGS and CERI, the CERI was associated with all three outcomes (ORs = 01.37-1.67). PGS for problematic alcohol use, externalizing, and smoking quantity were associated with alcohol dependence, drug dependence, and nicotine dependence, respectively (OR = 1.11-1.33). PGS for problematic alcohol use and externalizing were also associated with any substance dependence (ORs = 1.09-1.18). The full model explained 6-13% of the variance in SUDs. Those in the top 10% of CERI and PGS had relative risk ratios of 3.86-8.04 for each SUD relative to the bottom 90%. Overall, the combined measures of clinical, environmental, and genetic risk demonstrated modest ability to distinguish between affected and unaffected individuals in young adulthood. PGS were significant but added little in addition to the clinical/environmental risk index. Results from our analysis demonstrate there is still considerable work to be done before tools such as these are ready for clinical applications.

Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data

Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease characterized by flares ranging from mild to life-threatening. Severe flares and complications can require hospitalizations, which account for most of the direct costs of SLE care. This study investigates two machine learning approaches in predicting SLE hospitalizations using longitudinal data from 925 patients enrolled in a multicenter electronic health record (EHR)-based lupus cohort. Our first Differential approach accounts for the time dependencies in sequential data by introducing additional lagged variables between consecutive time steps. We next evaluate the performance of LSTM, a state-of-the-art deep learning model designed for time series. Our experimental results demonstrate that both methods can effectively predict lupus hospitalizations, but each has its strengths and limitations. Specifically, the Differential approach can be integrated into any non-temporal machine learning algorithms and is preferred for tasks with short observation periods. On the contrary, the LSTM model is desirable for studies utilizing long observation intervals attributing to its capability in capturing long-term dependencies embedded in the longitudinal data. Furthermore, the Differential approach has more options in handling class imbalance in the underlying data and delivers stable performance across different prognostic horizons. LSTM, on the other hand, demands more class-balanced training data and outperforms the Differential approach when there are sufficient positive samples facilitating model training. Capitalizing on our experimental results, we further study the optimal length of patient monitoring periods for different prediction horizons.

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.

A prospective investigation of youth alcohol experimentation and reward responsivity in the ABCD study

Rationale

Greater risk-taking behaviors, such as alcohol experimentation, are associated with different patterns of brain functioning in regions implicated in reward (nucleus accumbens, NA) and cognitive control (inferior frontal gyrus, IFG). These neural features have been observed in youth with greater risk-taking tendencies prior to substance use initiation, suggesting NA-IFG disruption may serve as an early marker for subsequent substance use disorders. Prospective studies are needed to determine if NA-IFG neural disruption predicts future substance use in school-age children, including those with minimal use of alcohol (e.g., sipping). The present large-sample prospective study sought to use machine learning to: (1) examine alcohol sipping at ages 9, 10 as a potential behavioral indicator of concurrent underlying altered neural responsivity to reward, and (2) determine if alcohol sipping and NA-IFG activation at ages 9, 10 can be used to predict which youth reported increased alcohol use at ages 11, 12. Additionally, low-level alcohol use and brain functioning at ages 9, 10 were examined as predictors of substance use and brain functioning at ages 11, 12.

Design and methods

This project used data from the baseline (Time 1) and two-year follow-up (Time 2) assessments of the Adolescent Brain Cognitive Development (ABCD) Study (Release 3.0). Support Vector Machine (SVM) learning determined if: (1) NA-IFG neural activity could correctly identify youth who reported alcohol sipping at Time 1 (n = 7409, mean age = 119.34 months, SD = 7.53; 50.27% female), and (2) NA-IFG and alcohol sipping frequency at Time 1 could correctly identify youth who reported drinking alcohol at Time 2 (n = 4000, mean age = 143.25 months, SD = 7.63; 47.53% female). Linear regression was also used to examine the relationship between alcohol sipping and NA-IFG activity at Time 1 and substance use and NA-IFG activity at Time 2. Data were also examined to characterize the environmental context in which youth first tried sips of alcohol (e.g., with or without parental permission, as part of a religious experience).

Results

Approximately 24% of the sample reported having tried sips of alcohol by ages 9, 10. On average, youth reported trying sips of alcohol 4.87 times (SD = 23.19) with age of first sip occurring at 7.36 years old (SD = 1.91). The first SVM model classified youth according to alcohol sipping status at Time 1 no better than chance with an accuracy of 0.35 (balanced accuracy = 0.52, sensitivity = 0.24, specificity = 0.80). The second SVM model classified youth according to alcohol drinking status at Time 2 with an accuracy of 0.76 (balanced accuracy = 0.56, sensitivity = 0.21, specificity = 0.91). Linear regression demonstrated that frequency of alcohol sipping at Time 1 predicted frequency of alcohol use at Time 2 (p < 0.001, adjusted R 2 = 0.075). Alcohol sipping at Time 1 was not linearly associated with NA or IFG activity at Time 2 (all ps > 0.05), and NA activity at Time 1 and Time 2 were not related (all ps > 0.05). Activity in the three subsections of the IFG at Time 1 predicted activity in those same regions at Time 2 (all ps < 0.02).

Conclusions and implications

Early sips of alcohol appear to predict alcohol use in early adolescence. Findings do not provide strong evidence for minimal early alcohol use (sipping) as a behavioral marker of underlying alterations in NA-IFG neural responsivity to reward. Improving our understanding of the neural and behavioral factors that indicate a greater propensity for future substance use is crucial for identifying at-risk youth and potential targets for preventative efforts.

Electroencephalography Microstate Alterations in Otogenic Vertigo: A Potential Disease Marker

Objectives

A huge population, especially the elderly, suffers from otogenic vertigo. However, the multi-modal vestibular network changes, secondary to periphery vestibular dysfunction, have not been fully elucidated. We aim to identify potential microstate electroencephalography (EEG) signatures for otogenic vertigo in this study.

Materials and Methods

Patients with recurrent otogenic vertigo and age-matched healthy adults were recruited. We performed 256-channel EEG recording of all participants at resting state. Neuropsychological questionnaires and vestibular function tests were taken as a measurement of patients’ symptoms and severity. We clustered microstates into four classes (A, B, C, and D) and identified their dynamic and syntax alterations of them. These features were further fed into a support vector machine (SVM) classifier to identify microstate signatures for vertigo.

Results

We compared 40 patients to 45 healthy adults, finding an increase in the duration of Microstate A, and both the occurrence and time coverage of Microstate D. The coverage and occurrence of Microstate C decreased significantly, and the probabilities of non-random transitions between Microstate A and D, as well as Microstate B and C, also changed. To distinguish the patients, the SVM classifier, which is built based on these features, got a balanced accuracy of 0.79 with a sensitivity of 0.78 and a specificity of 0.8.

Conclusion

There are several temporal dynamic alterations of EEG microstates in patients with otogenic vertigo, especially in Microstate D, reflecting the underlying process of visual-vestibular reorganization and attention redistribution. This neurophysiological signature of microstates could be used to identify patients with vertigo in the future.

Feature Fusion and Detection in Alzheimer’s Disease Using a Novel Genetic Multi-Kernel SVM Based on MRI Imaging and Gene Data

Voxel-based morphometry provides an opportunity to study Alzheimer’s disease (AD) at a subtle level. Therefore, identifying the important brain voxels that can classify AD, early mild cognitive impairment (EMCI) and healthy control (HC) and studying the role of these voxels in AD will be crucial to improve our understanding of the neurobiological mechanism of AD. Combining magnetic resonance imaging (MRI) imaging and gene information, we proposed a novel feature construction method and a novel genetic multi-kernel support vector machine (SVM) method to mine important features for AD detection. Specifically, to amplify the differences among AD, EMCI and HC groups, we used the eigenvalues of the top 24 Single Nucleotide Polymorphisms (SNPs) in a p-value matrix of 24 genes associated with AD for feature construction. Furthermore, a genetic multi-kernel SVM was established with the resulting features. The genetic algorithm was used to detect the optimal weights of 3 kernels and the multi-kernel SVM was used after training to explore the significant features. By analyzing the significance of the features, we identified some brain regions affected by AD, such as the right superior frontal gyrus, right inferior temporal gyrus and right superior temporal gyrus. The findings proved the good performance and generalization of the proposed model. Particularly, significant susceptibility genes associated with AD were identified, such as CSMD1, RBFOX1, PTPRD, CDH13 and WWOX. Some significant pathways were further explored, such as the calcium signaling pathway (corrected p-value = 1.35 × 10⁻⁶) and cell adhesion molecules (corrected p-value = 5.44 × 10⁻⁴). The findings offer new candidate abnormal brain features and demonstrate the contribution of these features to AD.

Common Laboratory Parameters Are Useful for Screening for Alcohol Use Disorder: Designing a Predictive Model Using Machine Learning

The diagnosis of alcohol use disorder (AUD) remains a difficult challenge, and some patients may not be adequately diagnosed. This study aims to identify an optimum combination of laboratory markers to detect alcohol consumption, using data science. An analytical observational study was conducted with 337 subjects (253 men and 83 women, with a mean age of 44 years (10.61 Standard Deviation (SD)). The first group included 204 participants being treated in the Addictive Behaviors Unit (ABU) from Albacete (Spain). They met the diagnostic criteria for AUD specified in the Diagnostic and Statistical Manual of mental disorders fifth edition (DSM-5). The second group included 133 blood donors (people with no risk of AUD), recruited by cross-section. All participants were also divided in two groups according to the WHO classification for risk of alcohol consumption in Spain, that is, males drinking more than 28 standard drink units (SDUs) or women drinking more than 17 SDUs. Medical history and laboratory markers were selected from our hospital's database. A correlation between alterations in laboratory markers and the amount of alcohol consumed was established. We then created three predicted models (with logistic regression, classification tree, and Bayesian network) to detect risk of alcohol consumption by using laboratory markers as predictive features. For the execution of the selection of variables and the creation and validation of predictive models, two tools were used: the scikit-learn library for Python, and the Weka application. The logistic regression model provided a maximum AUD prediction accuracy of 85.07%. Secondly, the classification tree provided a lower accuracy of 79.4%, but easier interpretation. Finally, the Naive Bayes network had an accuracy of 87.46%. The combination of several common biochemical markers and the use of data science can enhance detection of AUD, helping to prevent future medical complications derived from AUD.

Using machine learning to predict heavy drinking during outpatient alcohol treatment

BACKGROUND

Accurate clinical prediction supports the effective treatment of alcohol use disorder (AUD) and other psychiatric disorders. Traditional statistical techniques have identified patient characteristics associated with treatment outcomes. However, less work has focused on systematically leveraging these associations to create optimal predictive models. The current study demonstrates how machine learning can be used to predict clinical outcomes in people completing outpatient AUD treatment.

METHOD

We used data from the COMBINE multisite clinical trial (n = 1383) to develop and test predictive models. We identified three priority prediction targets, including (1) heavy drinking during the first month of treatment, (2) heavy drinking during the last month of treatment, and (3) heavy drinking between weekly/bi-weekly sessions. Models were generated using the random forest algorithm. We used "leave sites out" partitioning to externally validate the models in trial sites that were not included in the model training. Stratified model development was used to test for sex differences in the relative importance of predictive features.

RESULTS

Models predicting heavy alcohol use during the first and last months of treatment showed internal cross-validation area under the curve (AUC) scores ranging from 0.67 to 0.74. AUC was comparable in the external validation using data from held-out sites (AUC range = 0.69 to 0.72). The model predicting between-session heavy drinking showed strong classification accuracy in internal cross-validation (AUC = 0.89) and external test samples (AUC range = 0.80 to 0.87). Stratified analyses showed substantial sex differences in optimal feature sets.

CONCLUSION

Machine learning techniques can predict alcohol treatment outcomes using routinely collected clinical data. This technique has the potential to greatly improve clinical prediction accuracy without requiring expensive or invasive assessment methods. More research is needed to understand how best to deploy these models.

Internal consistency and test-retest reliability of the P3 event-related potential (ERP) elicited by alcoholic and non-alcoholic beverage pictures

Addiction researchers are interested in the ability of neural signals, like the P3 component of the ERP, to index individual differences in liability factors like motivational reactivity to alcohol/drug cues. The reliability of these measures directly impacts their ability to index individual differences, yet little attention has been paid to their psychometric properties. The present study fills this gap by examining within-session internal consistency reliability (ICR) and between-session test-retest reliability (TRR) of the P3 amplitude elicited by images of alcoholic beverages (Alcohol Cue P3) and non-alcoholic drinks (NADrink Cue P3) as well as the difference between them, which isolates alcohol cue-specific reactivity in the P3 (ACR-P3). Analyses drew on data from a large sample of alcohol-experienced emerging adults (session 1 N = 211, 55% female, aged 18-20 yr; session 2 N = 98, 66% female, aged 19-21 yr). Evaluated against domain-general thresholds, ICR was excellent (M ± SD; r= 0.902 ± 0.030) and TRR was fair (r = 0.706 ± 0.020) for Alcohol Cue P3 and NADrink Cue P3, whereas for ACR-P3, ICR and TRR were poor (r = 0.370 ± 0.071; r = 0.201 ± 0.042). These findings indicate that individual differences in the P3 elicited by cues for ingested liquid rewards are highly reliable and substantially stable over 8-10 months. Individual differences in alcohol cue-specific P3 reactivity were less reliable and less stable. The conditions under which alcohol/drug cue-specific reactivity in neural signals is adequately reliable and stable remain to be discovered.

The Vulnerability to Methamphetamine Dependence and Genetics: A Case-Control Study Focusing on Genetic Polymorphisms at Chromosomal Region 5q31.3

OBJECTIVES

Methamphetamine (METH) is a central nervous psychostimulant and one of the most frequently used illicit drugs. Numerous genetic loci that influence complex traits, including alcohol abuse, have been discovered; however, genetic analyses for METH dependence remain limited. An increased histone deacetylase 3 (HDAC3) expression has been detected in Fos-positive neurons in the dorsomedial striatum following withdrawal after METH self-administration. Herein, we aimed to systematically investigate the contribution of HDAC3 to the vulnerability to METH dependence in a Han Chinese population.

METHODS

In total, we recruited 1,221 patients with METH dependence and 2,328 age- and gender-matched controls. For genotyping, we selected 14 single nucleotide polymorphisms (SNPs) located within ± 3 kb regions of HDAC3. The associations between genotyped genetic polymorphisms and the vulnerability to METH dependence were examined by single marker- and haplotype-based methods using PLINK. The effects of expression quantitative trait loci (eQTLs) on targeted gene expressions were investigated using the Genotype-Tissue Expression (GTEx) database.

RESULTS

The SNP rs14251 was identified as a significant association signal (χ² = 9.84, P = 0.0017). An increased risk of METH dependence was associated with the A allele (minor allele) of rs14251 [odds ratio (95% CI) = 1.25 (1.09-1.43)]. The results of in silico analyses suggested that SNP rs14251 could be a potential eQTL signal for FCHSD1, PCDHGB6, and RELL2, but not for HDAC3, in various human tissues.

CONCLUSION

We demonstrated that genetic polymorphism rs14251 located at 5q31.3 was significantly associated with the vulnerability to METH dependence in Han Chinese population.

Functional validation of a finding from a mouse genome-wide association study shows that Azi2 influences the acute locomotor stimulant response to methamphetamine

In a previous genome-wide association study (GWAS) using outbred Carworth Farms White (CFW) mice, we identified a locus that influenced the stimulant response to methamphetamine and colocalized with an eQTL for Azi2. Based on those findings, we hypothesized that heritable differences in Azi2 expression were causally related to the differential response to methamphetamine. To test that hypothesis, we created a mutant Azi2 allele on an inbred C57BL/6J background. The mutant allele enhanced the locomotor response to methamphetamine. However, the GWAS had suggested that lower Azi2 would decrease the locomotor response to methamphetamine. We also sought to explore the mechanism by which Azi2 influenced methamphetamine sensitivity. A recent publication reported that the 3'UTR of Azi2 mRNA downregulates the expression of Slc6a3, which encodes the dopamine transporter, which is a key target of methamphetamine. We evaluated the relationship between Azi2, Azi2 3'UTR and Slc6a3 expression in the ventral tegmental area of wildtype, mutant Azi2 heterozygotes and mutant Azi2 homozygotes and in a new cohort of outbred CFW mice where both allele mapped in our prior GWAS were segregating. We did not observe any correlation between Azi2 and Slc6a3 in either cohort. However, RNA sequencing confirmed that the Azi2 mutation altered Azi2 expression and also revealed a number of potentially important genes and pathways that were regulated by Azi2, including the metabotropic glutamate receptor group III pathway and nicotinic acetylcholine receptor signaling pathway. Our results support a role for Azi2 in methamphetamine sensitivity; however, the exact mechanism does not appear to involve regulation of Slc6a3.

Patterns of high-risk drinking among medical students: A web-based survey with machine learning

BACKGROUND

Prior studies have found increased rates of alcohol consumption among physicians and medical students. The present study aims to build machine learning (ML) models to identify patterns of high-risk drinking (HRD), including alcohol use disorder, within this population.

METHODS

We analyzed data collected through a web-based survey among Brazilian medical students. Variables included sociodemographic data, personal information, university status, and mental health. Stratification for HRD was carried out based on the AUDIT-C scores. Three ML algorithms were used to build classifiers to predict HRD among medical students: elastic net regularization, random forest, and artificial neural networks. Model interpretation techniques were adopted to assess the most influential predictors for models' decisions, which represent potential factors associated with HRD.

RESULTS

A total of 4840 medical students were included in the study. The prevalence of HRD was 53.03%. The three ML models built were able to distinguish individuals with HRD from low-risk drinking (LRD) with very similar performance. The average AUC scores in the cross-validation procedure were around 0.72, and this performance was replicated in the test set. The most important features for the ML models were the use of tobacco and cannabis, monthly family income, marital status, sexual orientation, and physical activities.

CONCLUSIONS

This study proposes that ML models may serve as tools for initial screening of students regarding their susceptibility for at-risk drinking or alcohol use disorder. In addition, we identified several key factors associated with HRD that could be further investigated and explored for preventive and assistance measures.

Machine Learning for Risk Group Identification and User Data Collection in a Herpes Simplex Virus Patient Registry: Algorithm Development and Validation Study

BACKGROUND

Researching people with herpes simplex virus (HSV) is challenging because of poor data quality, low user engagement, and concerns around stigma and anonymity.

OBJECTIVE

This project aimed to improve data collection for a real-world HSV registry by identifying predictors of HSV infection and selecting a limited number of relevant questions to ask new registry users to determine their level of HSV infection risk.

METHODS

The US National Health and Nutrition Examination Survey (NHANES, 2015-2016) database includes the confirmed HSV type 1 and type 2 (HSV-1 and HSV-2, respectively) status of American participants (14-49 years) and a wealth of demographic and health-related data. The questionnaires and data sets from this survey were used to form two data sets: one for HSV-1 and one for HSV-2. These data sets were used to train and test a model that used a random forest algorithm (devised using Python) to minimize the number of anonymous lifestyle-based questions needed to identify risk groups for HSV.

RESULTS

The model selected a reduced number of questions from the NHANES questionnaire that predicted HSV infection risk with high accuracy scores of 0.91 and 0.96 and high recall scores of 0.88 and 0.98 for the HSV-1 and HSV-2 data sets, respectively. The number of questions was reduced from 150 to an average of 40, depending on age and gender. The model, therefore, provided high predictability of risk of infection with minimal required input.

CONCLUSIONS

This machine learning algorithm can be used in a real-world evidence registry to collect relevant lifestyle data and identify individuals' levels of risk of HSV infection. A limitation is the absence of real user data and integration with electronic medical records, which would enable model learning and improvement. Future work will explore model adjustments, anonymization options, explicit permissions, and a standardized data schema that meet the General Data Protection Regulation, Health Insurance Portability and Accountability Act, and third-party interface connectivity requirements.

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".

Predicting alcohol use disorder remission: a longitudinal multimodal multi-featured machine learning approach

Predictive models for recovering from alcohol use disorder (AUD) and identifying related predisposition biomarkers can have a tremendous impact on addiction treatment outcomes and cost reduction. Our sample (N = 1376) included individuals of European (EA) and African (AA) ancestry from the Collaborative Study on the Genetics of Alcoholism (COGA) who were initially assessed as having AUD (DSM-5) and reassessed years later as either having AUD or in remission. To predict this difference in AUD recovery status, we analyzed the initial data using multimodal, multi-features machine learning applications including EEG source-level functional brain connectivity, Polygenic Risk Scores (PRS), medications, and demographic information. Sex and ancestry age-matched stratified analyses were performed with supervised linear Support Vector Machine application and were calculated twice, once when the ancestry was defined by self-report and once defined by genetic data. Multifeatured prediction models achieved higher accuracy scores than models based on a single domain and higher scores in male models when the ancestry was based on genetic data. The AA male group model with PRS, EEG functional connectivity, marital and employment status features achieved the highest accuracy of 86.04%. Several discriminative features were identified, including collections of PRS related to neuroticism, depression, aggression, years of education, and alcohol consumption phenotypes. Other discriminated features included being married, employed, medication, lower default mode network and fusiform connectivity, and higher insula connectivity. Results highlight the importance of increasing genetic homogeneity of analyzed groups, identifying sex, and ancestry-specific features to increase prediction scores revealing biomarkers related to AUD remission.

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.

Biomarkers in Psychiatry: Concept, Definition, Types and Relevance to the Clinical Reality

During the last years, an extraordinary effort has been made to identify biomarkers as potential tools for improving prevention, diagnosis, drug response and drug development in psychiatric disorders. Contrary to other diseases, mental illnesses are classified by diagnostic categories with a broad variety list of symptoms. Consequently, patients diagnosed from the same psychiatric illness present a great heterogeneity in their clinical presentation. This fact together with the incomplete knowledge of the neurochemical alterations underlying mental disorders, contribute to the limited efficacy of current pharmacological options. In this respect, the identification of biomarkers in psychiatry is becoming essential to facilitate diagnosis through the developing of markers that allow to stratify groups within the syndrome, which in turn may lead to more focused treatment options. In order to shed light on this issue, this review summarizes the concept and types of biomarkers including an operational definition for therapeutic development. Besides, the advances in this field were summarized and sorted into five categories, which include genetics, transcriptomics, proteomics, metabolomics, and epigenetics. While promising results were achieved, there is a lack of biomarker investigations especially related to treatment response to psychiatric conditions. This review includes a final conclusion remarking the future challenges required to reach the goal of developing valid, reliable and broadly-usable biomarkers for psychiatric disorders and their treatment. The identification of factors predicting treatment response will reduce trial-and-error switches of medications facilitating the discovery of new effective treatments, being a crucial step towards the establishment of greater personalized medicine.