Applications of machine learning in addiction studies: A systematic review

Identifying predictors of multi-year cannabis vaping in U.S. Young adults using machine learning

INTRODUCTION

Increasing number of current cannabis users report using a vaporized form of cannabis and young adults are most likely to vape cannabis. However, the number of studies on cannabis vaping is limited, and predictors of cannabis vaping among U.S. young adults remain unclear. Previous studies on cannabis vaping have known limitations, as they (1) relied heavily on regression-based approaches that often fail to examine complex and non-linear interactive effects, (2) focused on examining cannabis vaping initiation but not on its use over multiple years, and (3) failed to account for recreational cannabis legalization (RCL) status.

METHODS

This study was a secondary analysis of the restricted use files of the Population Assessment of Tobacco and Health Study, Waves 4-6 (December 2016-November 2021). A two-stage machine learning approach, which included Least Absolute Shrinkage and Selection Operator (LASSO) and Classification and Regression Tree (CART), was used to identify predictors of multi-year cannabis vaping while accounting for state-level RCL status among a representative sample of U.S. young adults.

RESULTS

Stratified CART created a five-terminal-node prediction model for states with RCL (split by cannabis use, cigarette use, bullying behavior, and ethnicity) and a different five-terminal-node prediction model for states without RCL (split by cannabis use, heroin use, nicotine vaping, and hookah use).

CONCLUSIONS

Characteristics predicting multi-year cannabis vaping appear to differ from those of cannabis vaping initiation. Results also highlight the importance of accounting for RCL status because predictors of cannabis vaping may differ for individuals living in states with and without RCL.

Impulsivity, trauma history, and interoceptive awareness contribute to completion of a criminal diversion substance use treatment program for women

Introduction

In the US, women are one of the fastest-growing segments of the prison population and more than a quarter of women in state prison are incarcerated for drug offenses. Substance use criminal diversion programs can be effective. It may be beneficial to identify individuals who are most likely to complete the program versus terminate early as this can provide information regarding who may need additional or unique programming to improve the likelihood of successful program completion. Prior research investigating prediction of success in these programs has primarily focused on demographic factors in male samples.

Methods

The current study used machine learning (ML) to examine other non-demographic factors related to the likelihood of completing a substance use criminal diversion program for women. A total of 179 women who were enrolled in a criminal diversion program consented and completed neuropsychological, self-report symptom measures, criminal history and demographic surveys at baseline. Model one entered 145 variables into a machine learning (ML) ensemble model, using repeated, nested cross-validation, predicting subsequent graduation versus termination from the program. An identical ML analysis was conducted for model two, in which 34 variables were entered, including the Women's Risk/Needs Assessment (WRNA).

Results

ML models were unable to predict graduation at an individual level better than chance (AUC = 0.59 [SE = 0.08] and 0.54 [SE = 0.13]). Post-hoc analyses indicated measures of impulsivity, trauma history, interoceptive awareness, employment/financial risk, housing safety, antisocial friends, anger/hostility, and WRNA total score and risk scores exhibited medium to large effect sizes in predicting treatment completion (p < 0.05; ds = 0.29 to 0.81).

Discussion

Results point towards the complexity involved in attempting to predict treatment completion at the individual level but also provide potential targets to inform future research aiming to reduce recidivism.

Unmasking Risky Habits: Identifying and Predicting Problem Gamblers Through Machine Learning Techniques

The use of machine learning techniques to identify problem gamblers has been widely established. However, existing methods often rely on self-reported labeling, such as temporary self-exclusion or account closure. In this study, we propose a novel approach that combines two documented methods. First we create labels for problem gamblers in an unsupervised manner. Subsequently, we develop prediction models to identify these users in real-time. The methods presented in this study offer useful insights that can be leveraged to implement interventions aimed at guiding or discouraging players from engaging in disordered gambling behaviors. This has potential implications for promoting responsible gambling and fostering healthier player habits.

The impact of health information echo chambers on older adults avoidance behavior: the mediating role of information fatigue and the moderating role of trait mindfulness

Background

In the digital media era, the prevalence of algorithm-driven content push has intensified the health information echo chambers phenomenon, characterized by excessive homogenization and overload of information. This phenomenon may negatively impact the older adults, a "digitally vulnerable" group, by limiting their access to diverse health information and potentially inducing health information avoidance behaviors. However, the psychological mechanisms within this impact process remain unclear, and this study aims to explore them. Additionally, current study introduces trait mindfulness as a potential intervention tool in reducing health information avoidance behavior among the older adults.

Methods

This study constructs an impact model based on the Stress-Coping Theory and the Stress-Strain-Outcome (SSO) framework. It identifies health information similarity, relevance, and overload as characteristics of the echo chamber, constituting the Stress part; information fatigue as the Strain; and health information avoidance as the Outcome, with trait mindfulness serving as a moderating factor between Strain and Outcome. A cross-sectional survey of 236 older adults individuals aged 60 and above was conducted, and the collected data were analyzed using SmartPLS and SPSS.

Results

The study found that health information similarity and overload significantly increased health information fatigue among the older adults, thereby promoting avoidance behavior, but no significant correlation was found between relevance and fatigue. While there was no significant correlation between trait mindfulness and health information fatigue, it effectively moderated the avoidance behavior induced by fatigue.

Conclusion

Current study reveals the impact of the health information echo chamber phenomenon on health information avoidance behavior among the older adults and the moderating role of trait mindfulness. It emphasizes the importance of breaking the health information echo chamber and promoting diverse information dissemination to improve the health information behavior of the older adults. Furthermore, the moderating role of trait mindfulness demonstrates positive intervention potential, providing the older adults with a psychological adjustment mechanism to accept and process health information with a more open attitude, thereby reducing unproductive avoidance behavior.

Neonatal brain inflammation enhances methamphetamine-induced reinstated behavioral sensitization in adult rats analyzed with explainable machine learning

Neonatal brain inflammation produced by intraperitoneal (i.p.) injection of lipopolysaccharide (LPS) results in long-lasting brain dopaminergic injury and motor disturbances in adult rats. The goal of the present work is to investigate the effect of neonatal systemic LPS exposure (1 or 2 mg/kg, i.p. injection in postnatal day 5, P5, male rats)-induced dopaminergic injury to examine methamphetamine (METH)-induced behavioral sensitization as an indicator of drug addiction. On P70, subjects underwent a treatment schedule of 5 once daily subcutaneous (s.c.) administrations of METH (0.5 mg/kg) (P70-P74) to induce behavioral sensitization. Ninety-six hours following the 5th treatment of METH (P78), the rats received one dose of 0.5 mg/kg METH (s.c.) to reintroduce behavioral sensitization. Hyperlocomotion is a critical index caused by drug abuse, and METH administration has been shown to produce remarkable locomotor-enhancing effects. Therefore, a random forest model was used as the detector to extract the feature interaction patterns among the collected high-dimensional locomotor data. Our approaches identified neonatal systemic LPS exposure dose and METH-treated dates as features significantly associated with METH-induced behavioral sensitization, reinstated behavioral sensitization, and perinatal inflammation in this experimental model of drug addiction. Overall, the analysis suggests that the implementation of machine learning strategies is sensitive enough to detect interaction patterns in locomotor activity. Neonatal LPS exposure also enhanced METH-induced reduction of dopamine transporter expression and [3H]dopamine uptake, reduced mitochondrial complex I activity, and elevated interleukin-1β and cyclooxygenase-2 concentrations in the P78 rat striatum. These results indicate that neonatal systemic LPS exposure produces a persistent dopaminergic lesion leading to a long-lasting change in the brain reward system as indicated by the enhanced METH-induced behavioral sensitization and reinstated behavioral sensitization later in life. These findings indicate that early-life brain inflammation may enhance susceptibility to drug addiction development later in life, which provides new insights for developing potential therapeutic treatments for drug addiction.

Closing the Digital Divide in Interventions for Substance Use Disorder

Digital health interventions are exploding in today's medical practice and have tremendous potential to support the treatment of substance use disorders (SUD). Developers and healthcare providers alike must be cognizant of the potential for digital interventions to exacerbate existing inequities in SUD treatment, particularly as they relate to Social Determinants of Health (SDoH). To explore this evolving area of study, this manuscript will review the existing concepts of the digital divide and digital inequities, and the role SDoH play as drivers of digital inequities. We will then explore how the data used and modeling strategies can create bias in digital health tools for SUD. Finally, we will discuss potential solutions and future directions to bridge these gaps including smartphone ownership, Wi-Fi access, digital literacy, and mitigation of historical, algorithmic, and measurement bias. Thoughtful design of digital interventions is quintessential to reduce the risk of bias, decrease the digital divide, and create equitable health outcomes for individuals with SUD.

The Influence of Using Novel Predictive Technologies on Judgments of Stigma, Empathy, and Compassion among Healthcare Professionals

BACKGROUND

Our objective was to evaluate whether the description of a machine learning (ML) app or brain imaging technology to predict the onset of schizophrenia or alcohol use disorder (AUD) influences healthcare professionals' judgments of stigma, empathy, and compassion.

METHODS

We randomized healthcare professionals (N = 310) to one vignette about a person whose clinician seeks to predict schizophrenia or an AUD, using a ML app, brain imaging, or a psychosocial assessment. Participants used scales to measure their judgments of stigma, empathy, and compassion.

RESULTS

Participants randomized to the ML vignette endorsed less anger and more fear relative to the psychosocial vignette, and the brain imaging vignette elicited higher pity ratings. The brain imaging and ML vignettes evoked lower personal responsibility judgments compared to the psychosocial vignette. Physicians and nurses reported less empathy than clinical psychologists.

CONCLUSIONS

The use of predictive technologies may reinforce essentialist views about mental health and substance use that may increase specific aspects of stigma and reduce others.

Examining predictors of cocaine withdrawal syndrome at the end of detoxification treatment in women with cocaine use disorder

BACKGROUND

Detoxification is frequently recommended as a treatment for moderate to severe Cocaine Use Disorder (CUD). However, the response to detoxification varies among patients, and previous studies have focused mostly on patterns of drug use behavior to test associations with treatment outcomes, overlooking the potential impact of psychosocial factors, other clinical variables, and individual life experiences. In this study we comprehensively examined several variables aiming to find the most relevant predictors to classify patients with severe versus non-severe cocaine withdrawal symptoms at the end of detoxification.

METHODS

Data from 284 women with CUD who enrolled in a 3-week detoxification program was used in this longitudinal study. Psychosocial, clinical, and drug use behavior characteristics were evaluated, generating a dataset with 256 potential predictors. We tested six different machine learning classification algorithms.

RESULTS

The best classification algorithm achieved an average accuracy and ROC-AUC of approximately 70%. The 16 features selected as best predictors were the severity of psychiatric, family, and social problems and the level of exposure to childhood maltreatment. Features associated with drug-use behavior included days consuming drugs and having craving symptoms in the last month before treatment, number of previous drug/alcohol-related treatments, and a composite score of addiction severity. The level of cocaine withdrawal syndrome at the beginning of detoxification was also a key feature for classification. A network analysis revealed the pattern of association between predictors.

CONCLUSION

These variables can be assessed in real-world clinical settings, potentially helping clinicians to identify individuals with severe cocaine withdrawal that is likely to be sustained over the course of detoxification.

Machine learning for predicting opioid use disorder from healthcare data: A systematic review

INTRODUCTION

The US opioid epidemic has been one of the leading causes of injury-related deaths according to the CDC Injury Center. The increasing availability of data and tools for machine learning (ML) resulted in more researchers creating datasets and models to help analyze and mitigate the crisis. This review investigates peer-reviewed journal papers that applied ML models to predict opioid use disorder (OUD). The review is split into two parts. The first part summarizes the current research in OUD prediction with ML. The second part evaluates how ML techniques and processes were used to achieve these results and suggests improvements to refine further attempts to use ML for OUD prediction.

METHODS

The review includes peer-reviewed journal papers published on or after 2012 that use healthcare data to predict OUD. We searched Google Scholar, Semantic Scholar, PubMed, IEEE Xplore, and Science.gov in September of 2022. Data extracted includes the study's goal, dataset used, cohort selected, types of ML models created, model evaluation metrics, and the details of the ML tools and techniques used to create the models.

RESULTS

The review analyzed 16 papers. Three papers created their dataset, five used a publicly available dataset, and the remaining eight used a private dataset. Cohort size ranged from the low hundreds to over half a million. Six papers used one type of ML model, and the remaining ten used up to five different ML models. The reported ROC AUC was higher than 0.8 for all but one of the papers. Five papers used only non-interpretable models, and the other 11 used interpretable models exclusively or in combination with non-interpretable ones. The interpretable models were the highest or second-highest ROC AUC values. Most papers did not sufficiently describe the ML techniques and tools used to produce their results. Only three papers published their source code.

CONCLUSIONS

We found that while there are indications that ML methods applied to OUD prediction may be valuable, the lack of details and transparency in creating the ML models limits their usefulness. We end the review with recommendations to improve studies on this critical healthcare subject.

An Interpretable and Predictive Connectivity-Based Neural Signature for Chronic Cannabis Use

BACKGROUND

Cannabis is one of the most widely used substances in the world, with usage trending upward in recent years. However, although the psychiatric burden associated with maladaptive cannabis use has been well established, reliable and interpretable biomarkers associated with chronic use remain elusive. In this study, we combine large-scale functional magnetic resonance imaging with machine learning and network analysis and develop an interpretable decoding model that offers both accurate prediction and novel insights into chronic cannabis use.

METHODS

Chronic cannabis users (n = 166) and nonusing healthy control subjects (n = 124) completed a cue-elicited craving task during functional magnetic resonance imaging. Linear machine learning methods were used to classify individuals into chronic users and nonusers based on whole-brain functional connectivity. Network analysis was used to identify the most predictive regions and communities.

RESULTS

We obtained high (∼80% out-of-sample) accuracy across 4 different classification models, demonstrating that task-evoked connectivity can successfully differentiate chronic cannabis users from nonusers. We also identified key predictive regions implicating motor, sensory, attention, and craving-related areas, as well as a core set of brain networks that contributed to successful classification. The most predictive networks also strongly correlated with cannabis craving within the chronic user group.

CONCLUSIONS

This novel approach produced a neural signature of chronic cannabis use that is both accurate in terms of out-of-sample prediction and interpretable in terms of predictive networks and their relation to cannabis craving.

Deficient dynamics of prefrontal-striatal and striatal-default mode network (DMN) neural circuits in internet gaming disorder

BACKGROUND

Studies have proven that individuals with internet gaming disorder (IGD) show impaired cognitive control over game craving; however, the neural mechanism underlying this process remains unclear. Accordingly, the present study aimed to investigate the dynamic features of brain functional networks of individuals with IGD during rest, which have barely been understood until now.

METHODS

Resting-state fMRI data were collected from 333 subjects (123 subjects with IGD (males/females: 73/50) and 210 healthy controls (males/females: 135/75)). First, the data-driven methodology, named co-activation pattern analysis, was applied to investigate the dynamic features of nucleus accumbens (the core region involved in craving/reward processing and addiction)-centered brain networks in IGD. Further, machine learning analysis was conducted to investigate the prediction effect of the dynamic features on participants' addiction severity.

RESULTS

Compared to controls, subjects in the IGD group showed decreased resilience, betweenness centrality and occurrence in the prefrontal-striatal neural circuit, and decreased in-degree in the striatal-default mode network (DMN) circuit. Moreover, these decreased dynamic features could significantly predict participants' addiction severity.

LIMITATIONS

The causal relationship between IGD and the abnormal dynamic features cannot be identified in this study. All the subjects were university students.

CONCLUSIONS

The present results revealed the underlying brain networks of uncontrollable craving and game-seeking behaviors in individuals with IGD during rest. The decreased dynamics of the prefrontal-striatal and striatal-DMN neural circuits might be potential biomarkers for predicting the addiction severity of IGD and potential targets for effective interventions to reduce game craving of this disorder.

Machine learning applications in tobacco research: a scoping review

OBJECTIVE

Identify and review the body of tobacco research literature that self-identified as using machine learning (ML) in the analysis.

DATA SOURCES

MEDLINE, EMABSE, PubMed, CINAHL Plus, APA PsycINFO and IEEE Xplore databases were searched up to September 2020. Studies were restricted to peer-reviewed, English-language journal articles, dissertations and conference papers comprising an empirical analysis where ML was identified to be the method used to examine human experience of tobacco. Studies of genomics and diagnostic imaging were excluded.

STUDY SELECTION

Two reviewers independently screened the titles and abstracts. The reference list of articles was also searched. In an iterative process, eligible studies were classified into domains based on their objectives and types of data used in the analysis.

DATA EXTRACTION

Using data charting forms, two reviewers independently extracted data from all studies. A narrative synthesis method was used to describe findings from each domain such as study design, objective, ML classes/algorithms, knowledge users and the presence of a data sharing statement. Trends of publication were visually depicted.

DATA SYNTHESIS

74 studies were grouped into four domains: ML-powered technology to assist smoking cessation (n=22); content analysis of tobacco on social media (n=32); smoker status classification from narrative clinical texts (n=6) and tobacco-related outcome prediction using administrative, survey or clinical trial data (n=14). Implications of these studies and future directions for ML researchers in tobacco control were discussed.

CONCLUSIONS

ML represents a powerful tool that could advance the research and policy decision-making of tobacco control. Further opportunities should be explored.

Neuroeconomic predictors of smoking cessation outcomes: A preliminary study of delay discounting in treatment-seeking adult smokers

Large proportions of smokers are unsuccessful in evidence-based smoking cessation treatment and identifying prognostic predictors may inform improvements in treatment. Steep discounting of delayed rewards (delay discounting) is a robust predictor of poor smoking cessation outcome, but the underlying neural predictors have not been investigated. Forty-one treatment-seeking adult smokers completed a functional magnetic resonance imaging (fMRI) delay discounting paradigm prior to initiating a 9-week smoking cessation treatment protocol. Behavioral performance significantly predicted treatment outcomes (verified 7-day abstinence, n = 18; relapse, n = 23). Participants in the relapse group exhibited smaller area under the curve (d = 1.10) and smaller AUC was correlated with fewer days to smoking relapse (r = 0.56, p < 0.001) Neural correlates of discounting included medial and dorsolateral prefrontal cortex, posterior cingulate, precuneus and anterior insula, and interactions between choice type and relapse status were present for the dorsolateral prefrontal cortex, precuneus and the striatum. This initial investigation implicates differential neural activity in regions associated with frontal executive and default mode activity, as well as motivational circuits. Larger samples are needed to improve the resolution in identifying the neural underpinnings linking steep delay discounting to smoking cessation.

Predicting the severity of internet gaming disorder with resting-state brain features: A multi-voxel pattern analysis

BACKGROUND

Internet gaming disorder (IGD) has become a worldwide mental health concern; however, the neural mechanism underlying this disorder remains unclear. Multivoxel pattern analysis (MVPA), a newly developed data-driven approach, can be used to investigate the neural features of IGD based on massive neural data.

METHODS

Resting-state fMRI data from four hundred and two participants with varying levels of IGD severity were recruited. Regional homogeneity (ReHo) and the amplitude of low-frequency fluctuation (ALFF) were calculated and subsequently decoded by applying MVPA. The highly weighted regions in both predictive models were selected as regions of interest for further graph theory and Granger causality analysis (GCA) to explore how they affect IGD severity.

RESULTS

The results revealed that the neural patterns of ReHo and ALFF can independently and significantly predict IGD severity. The highly weighted regions that contributed to both predictive models were the right precentral gyrus and left postcentral gyrus. Moreover, topological properties of the right precentral gyrus were significantly correlated with IGD severity; further GCA revealed effective connectivity from the right precentral gyrus to left precentral gyrus and dorsal anterior cingulate cortex, both of which were significantly associated with IGD severity.

CONCLUSIONS

The present study demonstrated that IGD has distinctive neural patterns, and this pattern could be found by machine learning. In addition, the neural features in the right precentral gyrus play a key role in predicting IGD severity. The current study revealed the neural features of IGD and provided a potential target for IGD interventions using brain modulation.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Correlates of past year suicidal thoughts among sexual and gender minority young adults: A machine learning analysis

Sexual and gender minority populations are at elevated risk of experiencing suicidal thoughts and attempting suicide. The COVID-19 pandemic exacerbated mental health and substance use challenges among this population. We aimed to examine the relative importance and effects of intersectional factors and strong interactions associated with the risk of suicidal thoughts among Canadian lesbian, gay, bisexual, transgender, queer, questioning, intersex and Two Spirit (LGBTQI2S+) young adults. A cross-sectional online survey was conducted among LGBTQI2S + participants aged 16-29 years living in two Canadian provinces (Ontario, Quebec). Among 1414 participants (mean age 21.90 years), 61% (n = 857) participants reported suicidal thoughts in last 12 months. We built a random forest model to predict the risk of having past year suicidal thoughts, which achieved high performance with an area under the receiver operating characteristic curve (AUC) of 0.84. The top 10 correlates identified were: seeking help from health professionals for mental health or substance use issues since the start of the pandemic, current self-rated mental health status, insulted by parents or adults in childhood, ever heard that being identifying as LGBTQI2S+ is not normal, age in years, past week feeling depressed, lifetime diagnosis of mental illness, lifetime diagnosis of depressive disorder, past week feeling sad, ever pretended to be straight or cisgender to be accepted. The increase in the risk of suicidal thoughts for those having mental health challenges or facing minority stressors is more pronounced in those living in urban areas or being unemployed than those living in rural areas or being employed.

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.

Practical foundations of machine learning for addiction research. Part I. Methods and techniques

Machine learning assembles a broad set of methods and techniques to solve a wide range of problems, such as identifying individuals with substance use disorders (SUD), finding patterns in neuroimages, understanding SUD prognostic factors and their association, or determining addiction genetic underpinnings. However, the addiction research field underuses machine learning. This two-part narrative review focuses on machine learning tools and concepts, providing an introductory insight into their capabilities to facilitate their understanding and acquisition by addiction researchers. This first part presents supervised and unsupervised methods such as linear models, naive Bayes, support vector machines, artificial neural networks, and k-means. We illustrate each technique with examples of its use in current addiction research. We also present some open-source programming tools and methodological good practices that facilitate using these techniques. Throughout this work, we emphasize a continuum between applied statistics and machine learning, we show their commonalities, and provide sources for further reading to deepen the understanding of these methods. This two-part review is a primer for the next generation of addiction researchers incorporating machine learning in their projects. Researchers will find a bridge between applied statistics and machine learning, ways to expand their analytical toolkit, recommendations to incorporate well-established good practices in addiction data analysis (e.g., stating the rationale for using newer analytical tools, calculating sample size, improving reproducibility), and the vocabulary to enhance collaboration between researchers who do not conduct data analyses and those who do.

External validation of a machine learning classifier to identify unhealthy alcohol use in hospitalized patients

BACKGROUND AND AIMS

Unhealthy alcohol use (UAU) is one of the leading causes of global morbidity. A machine learning approach to alcohol screening could accelerate best practices when integrated into electronic health record (EHR) systems. This study aimed to validate externally a natural language processing (NLP) classifier developed at an independent medical center.

DESIGN

Retrospective cohort study.

SETTING

The site for validation was a midwestern United States tertiary-care, urban medical center that has an inpatient structured universal screening model for unhealthy substance use and an active addiction consult service.

PARTICIPANTS/CASES

Unplanned admissions of adult patients between October 23, 2017 and December 31, 2019, with EHR documentation of manual alcohol screening were included in the cohort (n = 57 605).

MEASUREMENTS

The Alcohol Use Disorders Identification Test (AUDIT) served as the reference standard. AUDIT scores ≥5 for females and ≥8 for males served as cases for UAU. To examine error in manual screening or under-reporting, a post hoc error analysis was conducted, reviewing discordance between the NLP classifier and AUDIT-derived reference. All clinical notes excluding the manual screening and AUDIT documentation from the EHR were included in the NLP analysis.

FINDINGS

Using clinical notes from the first 24 hours of each encounter, the NLP classifier demonstrated an area under the receiver operating characteristic curve (AUCROC) and precision-recall area under the curve (PRAUC) of 0.91 (95% CI = 0.89-0.92) and 0.56 (95% CI = 0.53-0.60), respectively. At the optimal cut point of 0.5, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 0.66 (95% CI = 0.62-0.69), 0.98 (95% CI = 0.98-0.98), 0.35 (95% CI = 0.33-0.38), and 1.0 (95% CI = 1.0-1.0), respectively.

CONCLUSIONS

External validation of a publicly available alcohol misuse classifier demonstrates adequate sensitivity and specificity for routine clinical use as an automated screening tool for identifying at-risk patients.

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.

A Systematic Review and Bibliometric Analysis of Applications of Artificial Intelligence and Machine Learning in Vascular Surgery

INTRODUCTION

Artificial intelligence (AI) and machine learning (ML) have seen increasingly intimate integration with medicine and healthcare in the last two decades. The objective of this study was to summarize all current applications of AI and ML in the vascular surgery literature and to conduct a bibliometric analysis of the published studies.

METHODS

A comprehensive literature search was conducted through EMBASE, MEDLINE, and Ovid HealthStar from inception until February 19, 2021. Reporting of this study was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Title and abstract screening, full-text screening, and data extraction were conducted in duplicate. Data extracted included study meta-data, the clinical area of study within vascular surgery, type of AI/ML method used, data set, and the application of AI/ML. Publishing journals were classified as having either a clinical scope or technical scope. Author academic background was classified as clinical, non-clinical (e.g., engineering) or both, depending on author affiliation.

RESULTS

The initial search identified 7434 studies, of which 249 were included for final analysis. The rate of publications is exponentially increasing, with 158 (63%) studies being published in the last 5 years. Studies were most commonly related to carotid artery disease (118, 47%), abdominal aortic aneurysms (51, 20%), and peripheral arterial disease (26, 10%). Study authors employed an average of 1.50 (range: 1-6) distinct AI methods in their studies. The application of AI/ML methods broadly related to predictive models (54, 22%), image segmentation (49, 19.4%), diagnostic methods (46, 18%), or multiple combined applications (91, 37%). The most commonly used AI/ML methods were artificial neural networks (155/378 use cases, 41%), support vector machines (64, 17%), k-nearest neighbors algorithm (26, 7%), and random forests (23, 6%). Data sets to which these AI/ML methods were applied frequently involved ultrasound images (87, 35%), CT images (42, 17%), clinical data (34, 14%) or multiple data sets (36, 14%). Overall, 22 (9%) studies were published in journals specific to vascular surgery, with the majority (147/249, 59%) being published in journals with a scope related to computer science or engineering. Among 1576 publishing authors, 46% had exclusively a clinical background, 48% a non-clinical background, and 5% had both a clinical and non-clinical background.

CONCLUSION

There is an exponentially growing body of literature describing the use of AI and ML in vascular surgery. There is a focus on carotid artery disease and abdominal aortic disease, with many other areas of vascular surgery underrepresented. Neural networks and support vector machines composed most AI methods in the literature. As AI/ML continues to see more expanded applications in the field, it is important that vascular surgeons appreciate its potential and limitations. Additionally, as it sees increasing use, there is a need for clinicians with expertise in AI/ML methods who can optimize its transition into daily practice.

Identifying risk profiles for marijuana vaping among U.S. young adults by recreational marijuana legalization status: A machine learning approach

INTRODUCTION

This study attempted to identify risk profiles of marijuana vaping by state-level recreational marijuana legalization (RML) status among U.S. young adults (YA).

METHODS

Data were drawn from the most recent two waves of restricted use files of the Population Assessment of Tobacco and Health Study with state identifiers. We analyzed 6155 young adult (18-24 years) respondents who were naïve to marijuana vaping at Wave 4 and had matched data at Wave 5. We employed a two-stage machine learning approach to predict marijuana vaping initiation at Wave 5 with predictors measured at Wave 4.

RESULTS

Among YA who had never vaped marijuana at Wave 4, 19% of those who lived in the states with RML and 15% of those who lived in the states without RML reported marijuana vaping at Wave 5. Substance-use-related predictors were rarely found as leading predictors in the states with RML. In the states without RML, substance use behaviors, including electronic nicotine delivery systems and smokeless tobacco use, and the presence of externalizing symptoms emerged as predictors for marijuana vaping. Results also revealed that nonlinear interactions between the predictors of marijuana vaping.

CONCLUSIONS

Our results highlight the importance of accounting for the RML status in developing risk profiles of marijuana vaping. Externalizing symptoms may be a behavioral endophenotype of marijuana vaping in the states without RML. Machine learning appears to be a promising analytical approach to identify complex interactions between factors in predicting an emerging risk behavior such as marijuana vaping.

Predictors of perceived success in quitting smoking by vaping: A machine learning approach

Prior research has suggested that a set of unique characteristics may be associated with adult cigarette smokers who are able to quit smoking using e-cigarettes (vaping). In this cross-sectional study, we aimed to identify and rank the importance of these characteristics using machine learning. During July and August 2019, an online survey was administered to a convenience sample of 889 adult smokers (age ≥ 20) in Ontario, Canada who tried vaping to quit smoking in the past 12 months. Fifty-one person-level characteristics, including a Vaping Experiences Score, were assessed in a gradient boosting machine model to classify the status of perceived success in vaping-assisted smoking cessation. This model was trained using cross-validation and tested using the receiver operating characteristic (ROC) curve. The top five most important predictors were identified using a score between 0% and 100% that represented the relative importance of each variable in model training. About 20% of participants (N = 174, 19.6%) reported success in vaping-assisted smoking cessation. The model achieved relatively high performance with an area under the ROC curve of 0.865 and classification accuracy of 0.831 (95% CI [confidence interval] 0.780 to 0.874). The top five most important predictors of perceived success in vaping-assisted smoking cessation were more positive experiences measured by the Vaping Experiences Score (100%), less previously failed quit attempts by vaping (39.0%), younger age (21.9%), having vaped 100 times (16.8%), and vaping shortly after waking up (15.8%). Our findings provide strong statistical evidence that shows better vaping experiences are associated with greater perceived success in smoking cessation by vaping. Furthermore, our study confirmed the strength of machine learning techniques in vaping-related outcomes research based on observational data.

A machine learning approach to identifying pregnant women's risk for persistent post-traumatic stress following childbirth

INTRO

Recent literature identifies childbirth as a potentially traumatic event, following which mothers may develop symptoms of Post-Traumatic-Stress-Following-Childbirth (PTS-FC). Especially when persistent, PTS-FC may interfere with mothers' caregiving and associated infant development, underscoring the need for accurate predictive screening of risk. Drawing on recent developments in advanced statistical modeling, the aim of the current study was to identify a set of prenatal indicators and prediction rules that may accurately identify pregnant women's risk for developing symptoms of PTS-FC which persist throughout the early postpartum period.

METHODS

182 women from the general population completed a comprehensive set of approximately 200 potentially predictive questions during pregnancy, and subsequently reported on their acute stress and PTS-FC at three days, one month, and three months postpartum (self-report and clinician-administered interview). Based on the postpartum acute stress and PTS-FC data, women were classified into profiles of "Stable-High-PTS-FC" and "Stable-Low-PTS-FC" by means of Latent-Class Analyses. Prenatal data were modeled to identify women at risk for "Stable-High PTS-FC".

RESULTS

Employing machine-learning decision-tree analyses, a total of 36 questions and 7 prediction-rules were selected. Based on a cost-rate of 15 versus 100 for false-negative "Stable-Low-PTS-FC" versus false-negative "Stable-High-PTS-FC", the final model showed 80.6% accuracy for "Stable-High-PTS-FC" prediction.

DISCUSSION

This study identifies a short set of questions and prediction rules that may be included in future large-scale validation studies aimed at developing and validating a brief PTS-FC screening instrument that could be implemented in general population prenatal healthcare practice. Accurate screening would allow for selective administering of preventive interventions towards women at risk.

White matter microstructure differences in individuals with dependence on cocaine, methamphetamine, and nicotine: Findings from the ENIGMA-Addiction working group

BACKGROUND

Nicotine and illicit stimulants are very addictive substances. Although associations between grey matter and dependence on stimulants have been frequently reported, white matter correlates have received less attention.

METHODS

Eleven international sites ascribed to the ENIGMA-Addiction consortium contributed data from individuals with dependence on cocaine (n = 147), methamphetamine (n = 132) and nicotine (n = 189), as well as non-dependent controls (n = 333). We compared the fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD) and mean diffusivity (MD) of 20 bilateral tracts. Also, we compared the performance of various machine learning algorithms in deriving brain-based classifications on stimulant dependence.

RESULTS

The cocaine and methamphetamine groups had lower regional FA and higher RD in several association, commissural, and projection white matter tracts. The methamphetamine dependent group additionally showed lower regional AD. The nicotine group had lower FA and higher RD limited to the anterior limb of the internal capsule. The best performing machine learning algorithm was the support vector machine (SVM). The SVM successfully classified individuals with dependence on cocaine (AUC = 0.70, p < 0.001) and methamphetamine (AUC = 0.71, p < 0.001) relative to non-dependent controls. Classifications related to nicotine dependence proved modest (AUC = 0.62, p = 0.014).

CONCLUSIONS

Stimulant dependence was related to FA disturbances within tracts consistent with a role in addiction. The multivariate pattern of white matter differences proved sufficient to identify individuals with stimulant dependence, particularly for cocaine and methamphetamine.

Application of machine learning in oral and maxillofacial surgery

Oral and maxillofacial anatomy is extremely complex, and medical imaging is critical in the diagnosis and treatment of soft and bone tissue lesions. Hence, there exists accumulating imaging data without being properly utilized over the last decades. As a result, problems are emerging regarding how to integrate and interpret a large amount of medical data and alleviate clinicians’ workload. Recently, artificial intelligence has been developing rapidly to analyze complex medical data, and machine learning is one of the specific methods of achieving this goal, which is based on a set of algorithms and previous results. Machine learning has been considered useful in assisting early diagnosis, treatment planning, and prognostic estimation through extracting key features and building mathematical models by computers. Over the past decade, machine learning techniques have been applied to the field of oral and maxillofacial surgery and increasingly achieved expert-level performance. Thus, we hold a positive attitude towards developing machine learning for reducing the number of medical errors, improving the quality of patient care, and optimizing clinical decision-making in oral and maxillofacial surgery. In this review, we explore the clinical application of machine learning in maxillofacial cysts and tumors, maxillofacial defect reconstruction, orthognathic surgery, and dental implant and discuss its current problems and solutions.

Machine Learning Applications in Mental Health and Substance Use Research Among the LGBTQ2S+ Population: Scoping Review

BACKGROUND

A high risk of mental health or substance addiction issues among sexual and gender minority populations may have more nuanced characteristics that may not be easily discovered by traditional statistical methods.

OBJECTIVE

This review aims to identify literature studies that used machine learning (ML) to investigate mental health or substance use concerns among the lesbian, gay, bisexual, transgender, queer or questioning, and two-spirit (LGBTQ2S+) population and direct future research in this field.

METHODS

The MEDLINE, Embase, PubMed, CINAHL Plus, PsycINFO, IEEE Xplore, and Summon databases were searched from November to December 2020. We included original studies that used ML to explore mental health or substance use among the LGBTQ2S+ population and excluded studies of genomics and pharmacokinetics. Two independent reviewers reviewed all papers and extracted data on general study findings, model development, and discussion of the study findings.

RESULTS

We included 11 studies in this review, of which 81% (9/11) were on mental health and 18% (2/11) were on substance use concerns. All studies were published within the last 2 years, and most were conducted in the United States. Among mutually nonexclusive population categories, sexual minority men were the most commonly studied subgroup (5/11, 45%), whereas sexual minority women were studied the least (2/11, 18%). Studies were categorized into 3 major domains: web content analysis (6/11, 54%), prediction modeling (4/11, 36%), and imaging studies (1/11, 9%).

CONCLUSIONS

ML is a promising tool for capturing and analyzing hidden data on mental health and substance use concerns among the LGBTQ2S+ population. In addition to conducting more research on sexual minority women, different mental health and substance use problems, as well as outcomes and future research should explore newer environments, data sources, and intersections with various social determinants of health.

Multi-site clustering and nested feature extraction for identifying autism spectrum disorder with resting-state fMRI

Brain functional connectivity (FC) derived from resting-state functional magnetic resonance imaging (rs-fMRI) has been widely employed to study neuropsychiatric disorders such as autism spectrum disorder (ASD). Existing studies usually suffer from (1) significant data heterogeneity caused by different scanners or studied populations in multiple sites, (2) curse of dimensionality caused by millions of voxels in each fMRI scan and a very limited number (tens or hundreds) of training samples, and (3) poor interpretability, which hinders the identification of reproducible disease biomarkers. To this end, we propose a Multi-site Clustering and Nested Feature Extraction (MC-NFE) method for fMRI-based ASD detection. Specifically, we first divide multi-site training data into ASD and healthy control (HC) groups. To model inter-site heterogeneity within each category, we use a similarity-driven multiview linear reconstruction model to learn latent representations and perform subject clustering within each group. We then design a nested singular value decomposition (SVD) method to mitigate inter-site heterogeneity and extract FC features by learning both local cluster-shared features across sites within each category and global category-shared features across ASD and HC groups, followed by a linear support vector machine (SVM) for ASD detection. Experimental results on 609 subjects with rs-fMRI from the ABIDE database with 21 imaging sites suggest that the proposed MC-NFE outperforms several state-of-the-art methods in ASD detection. The most discriminative FCs identified by the MC-NFE are mainly located in default mode network, salience network, and cerebellum region, which could be used as potential biomarkers for fMRI-based ASD analysis.

Decision tree outcome prediction of acute acetaminophen exposure in the United States: A study of 30,000 cases from the National Poison Data System

Acetaminophen is one of the most commonly used analgesic drugs in the United States. However, the outcomes of acute acetaminophen overdose might be very serious in some cases. Therefore, prediction of the outcomes of acute acetaminophen exposure is crucial. This study is a 6-year retrospective cohort study using National Poison Data System (NPDS) data. A decision tree algorithm was used to determine the risk predictors of acetaminophen exposure. The decision tree model had an accuracy of 0.839, an accuracy of 0.836, a recall of 0.72, a specificity of 0.86 and an F1_score of 0.76 for the test group and an accuracy of 0.848, a recall of 0.85, a recall of 0.74, a specificity of 0.87 and an F1_score of 0.78 for the training group. Our results showed that elevated serum levels of liver enzymes, other liver function test abnormality, anorexia, acidosis, electrolyte abnormality, increased bilirubin, coagulopathy, abdominal pain, coma, increased anion gap, tachycardia and hypotension were the most important factors in determining the outcome of acute acetaminophen exposure. Therefore, the decision tree model is a reliable approach in determining the prognosis of acetaminophen exposure cases and can be used in an emergency room or during hospitalization.

Extended classifier system with continuous real-coded variables for feature extraction of instantaneous pulse-rate variability and respiration of individuals with gaming disorder

Background

Individuals with gaming disorder (GD) exhibit autonomic nervous system responses that indicate dysfunctional emotion regulation. Pulse rate variability (PRV) is a valuable biomarker for investigating the autonomic function of patients with mental disorders. Because individuals with GD dynamically regulate emotions during gaming, the PRV response relating to GD is not well understood. To investigate the dynamic PRV responses of individuals with GD, this study proposed the indexes of instantaneous PRV (iPRV) and instantaneous respiratory frequency (IF_resp) of arterial blood pressure signals using empirical mode decomposition and normalized direct-quadrature algorithms. iPRV consists of low-frequency (LF), high-frequency (HF), and very high-frequency (VHF) bands. Moreover, a novel method of extended classifier system with continuous real-coded variables (XCSR) was used to detect GD and extract GD-related iPRV features using iPRV and IF_resp as input data.

Results

A total of 32 college students without depressive and anxiety symptoms or cardiovascular diseases were recruited in this study. Participants were grouped into the high-risk GD and low-risk GD using both Chen Internet Addiction Scale and Internet Gaming Disorder Questionnaire. Their arterial blood pressures signals were measured while they watched gameplay videos with negative or positive emotional stimuli. Seven participants with high-risk GD exhibited significantly increased normalized VHF (nVHF) PRV and IF_resp readings and significantly decreased normalized LF (nLF) PRV readings and LF/HF PRV ratios (from baseline) during negative or positive gameplay videos stimuli. These participants also exhibited higher nVHF PRV and lower nLF PRV readings and LF/HF PRV ratios when they experienced negative gameplay video stimuli relative to 17 participants with low-risk GD. The classification accuracy of the XCSR reached 90% for both negative and positive video stimuli, and nVHF PRV was most frequently used to detect GD risk.

Conclusions

iPRV and IF_resp can be used to detect GD and analyze the autonomic mechanism of individuals with GD.

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.

Psychiatry in the Digital Age: A Blessing or a Curse?

Social distancing and the shortage of healthcare professionals during the COVID-19 pandemic, the impact of population aging on the healthcare system, as well as the rapid pace of digital innovation are catalyzing the development and implementation of new technologies and digital services in psychiatry. Is this transformation a blessing or a curse for psychiatry? To answer this question, we conducted a literature review covering a broad range of new technologies and eHealth services, including telepsychiatry; computer-, internet-, and app-based cognitive behavioral therapy; virtual reality; digital applied games; a digital medicine system; omics; neuroimaging; machine learning; precision psychiatry; clinical decision support; electronic health records; physician charting; digital language translators; and online mental health resources for patients. We found that eHealth services provide effective, scalable, and cost-efficient options for the treatment of people with limited or no access to mental health care. This review highlights innovative technologies spearheading the way to more effective and safer treatments. We identified artificially intelligent tools that relieve physicians from routine tasks, allowing them to focus on collaborative doctor-patient relationships. The transformation of traditional clinics into digital ones is outlined, and the challenges associated with the successful deployment of digitalization in psychiatry are highlighted.

Investigating predictive factors of dialectical behavior therapy skills training efficacy for alcohol and concurrent substance use disorders: A machine learning study

BACKGROUND

Dialectical Behavior Therapy Skills Training (DBT-ST) as stand-alone treatment has demonstrated promising outcomes for the treatment of alcohol use disorder (AUD) and concurrent substance use disorders (SUDs). However, no studies have so far empirically investigated factors that might predict efficacy of this therapeutic model.

METHODS

275 treatment-seeking individuals with AUD and other SUDs were consecutively admitted to a 3-month DBT-ST program (in- + outpatient; outpatient settings). The machine learning routine applied (i.e. penalized regression combined with a nested cross-validation procedure) was conducted in order to estimate predictive values of a wide panel of clinical variables in a single statistical framework on drop-out and substance-use behaviors, dealing with related multicollinearity, and eliminating redundant variables.

RESULTS

The cross-validated elastic net model significantly predicted the drop-out. The bootstrap analysis revealed that subjects who showed substance-use behaviors during the intervention and who were treated with the mixed setting (i.e., in- and outpatient) program, together with higher ASI alcohol scores were associated with an higher probability of drop-out. On the contrary, older subjects, higher levels of education, together with higher scores of DERS awareness subscale were negatively associated to drop-out. Similarly, lifetime co-diagnoses of anxiety, bipolar, and gambling disorders, together with bulimia nervosa negatively predicted the drop-out. The machine learning model did not identify predictive variables of substance-use behaviors during the treatment.

CONCLUSIONS

The DBT-ST program could be considered a valid therapeutic approach especially when AUD and other SUDs co-occur with other psychiatric conditions and, it is carried out as a full outpatient intervention.

Are Machine Learning Methods the Future for Smoking Cessation Apps?

Smoking cessation apps provide efficient, low-cost and accessible support to smokers who are trying to quit smoking. This article focuses on how up-to-date machine learning algorithms, combined with the improvement of mobile phone technology, can enhance our understanding of smoking behaviour and support the development of advanced smoking cessation apps. In particular, we focus on the pros and cons of existing approaches that have been used in the design of smoking cessation apps to date, highlighting the need to improve the performance of these apps by minimizing reliance on self-reporting of environmental conditions (e.g., location), craving status and/or smoking events as a method of data collection. Lastly, we propose that making use of more advanced machine learning methods while enabling the processing of information about the user’s circumstances in real time is likely to result in dramatic improvement in our understanding of smoking behaviour, while also increasing the effectiveness and ease-of-use of smoking cessation apps, by enabling the provision of timely, targeted and personalised intervention.

A CNN-Based Autoencoder and Machine Learning Model for Identifying Betel-Quid Chewers Using Functional MRI Features

Betel quid (BQ) is one of the most commonly used psychoactive substances in some parts of Asia and the Pacific. Although some studies have shown brain function alterations in BQ chewers, it is virtually impossible for radiologists’ to visually distinguish MRI maps of BQ chewers from others. In this study, we aimed to construct autoencoder and machine-learning models to discover brain alterations in BQ chewers based on the features of resting-state functional magnetic resonance imaging. Resting-state functional magnetic resonance imaging (rs-fMRI) was obtained from 16 BQ chewers, 15 tobacco- and alcohol-user controls (TA), and 17 healthy controls (HC). We used an autoencoder and machine learning model to identify BQ chewers among the three groups. A convolutional neural network (CNN)-based autoencoder model and supervised machine learning algorithm logistic regression (LR) were used to discriminate BQ chewers from TA and HC. Classifying the brain MRIs of HC, TA controls, and BQ chewers by conducting leave-one-out-cross-validation (LOOCV) resulted in the highest accuracy of 83%, which was attained by LR with two rs-fMRI feature sets. In our research, we constructed an autoencoder and machine-learning model that was able to identify BQ chewers from among TA controls and HC, which were based on data from rs-fMRI, and this might provide a helpful approach for tracking BQ chewers in the future.

Impulsivity-Compulsivity Axis: Evidence of Its Clinical Validity to Individually Classify Subjects on the Use/Abuse of Information and Communication Technologies

The compulsive habit model proposed by Everitt and Robbins has accumulated important empirical evidence. One of their proposals is the existence of an axis, on which each a person with a particular addiction can be located depending on the evolutionary moment of his/her addictive process. The objective of the present study is to contribute in addressing the identification of such axis, as few studies related to it have been published to date. To do so, the use/abuse of Information and Communication Technologies (ICT) was quantified on an initial sample of 807 subjects. Questionnaires were also delivered to measure impulsivity, compulsivity and symptoms of prefrontal dysfunction. Evidence of the existence of the proposed axis was obtained by means of Machine Learning techniques, thus allowing the classification of each subject along the continuum. The present study provides preliminary evidence of the existence of the Impulsivity-Compulsivity axis, as well as an IT tool so that each patient that starts getting treatment for an addiction can be statistically classified as “impulsive” or “compulsive.” This would allow the matching of each person with the most appropriate treatment depending on his/her moment in the addiction/abuse process, thus facilitating the individualized design of each therapeutic process and a possible improvement of the results of the treatment.

Identifying emerging predictors for adolescent electronic nicotine delivery systems use: A machine learning analysis of the Population Assessment of Tobacco and Health Study

Intervention strategies to prevent adolescents from using electronic nicotine delivery systems (ENDS) should be based on robust predictors of ENDS use that may differ from predictors of conventional cigarette use. Literature points to the need for uncovering emerging predictors of ENDS use. This study identified emerging predictors of adolescent ENDS use using machine learning (ML) techniques. We analyzed nationally representative multi-wave longitudinal survey data (2013-2018) drawn from the Population Assessment of Tobacco and Health Study. A sample of adolescents (12-17 years) who never used any tobacco products at baseline and completed Wave 2 (n = 7958), Wave 3 (n = 6260) and Wave 4 (n = 4544) were analyzed. We developed a supervised ML prediction model using the penalized logistic regression to assess self-reported past-month ENDS use (i.e., current use) at Waves 2-4 based on the variables measured at the previous wave. We then extracted important predictors from each model. The penalized logistic regression models showed suitable capability to discriminate between ENDS uses and non-uses at each wave based on the area under the receiver operating characteristic curve and the area under the precision-recall curve. Interestingly, social media use emerged as an important variable in predicting adolescent ENDS use. ML models appear to be a promising method to identify unique population-level predictors for U.S. adolescent ENDS use behaviors. More research is warranted to investigate emerging predictors of ENDS use and experimentally examine the mechanism by which these emerging predictors affect ENDS use behavior across different spectrum of populations.

A machine learning approach to identify correlates of current e-cigarette use in Canada

Aim: Popularity of electronic cigarettes (i.e. e-cigarettes) is soaring in Canada. Understanding person-level correlates of current e-cigarette use (vaping) is crucial to guide tobacco policy, but prior studies have not fully identified these correlates due to model overfitting caused by multicollinearity. This study addressed this issue by using classification tree, a machine learning algorithm. Methods: This population-based cross-sectional study used the Canadian Tobacco, Alcohol, and Drugs Survey (CTADS) from 2017 that targeted residents aged 15 or older. Forty-six person-level characteristics were first screened in a logistic mixed-effects regression procedure for their strength in predicting vaper type (current vs. former vaper) among people who reported to have ever vaped. A 9:1 ratio was used to randomly split the data into a training set and a validation set. A classification tree model was developed using the cross-validation method on the training set using the selected predictors and assessed on the validation set using sensitivity, specificity and accuracy. Results: Of the 3,059 people with an experience of vaping, the average age was 24.4 years (standard deviation = 11.0), with 41.9% of them being female and 8.5% of them being aboriginal. There were 556 (18.2%) current vapers. The classification tree model performed relatively well and suggested attraction to e-cigarette flavors was the most important correlate of current vaping, followed by young age (< 18) and believing vaping to be less harmful to oneself than cigarette smoking. Conclusions: People who vape due to flavors are associated with very high risk of becoming current vapers. The findings of this study provide evidence that supports the ongoing ban on flavored vaping products in the US and suggests a similar regulatory intervention may be effective in Canada.

Präzisionspsychiatrie und der Beitrag von Brain Imaging und anderen Biomarkern

'Precision Psychiatry' as the psychiatric variant of 'Precision Medicine' aims to provide high-level diagnosis and treatment based on robust biomarkers and tailored to the individual clinical, neurobiological, and genetic constitution of the patient. The specific peculiarity of psychiatry, in which disease entities are normatively defined based on clinical experience and are also significantly influenced by contemporary history, society and philosophy, has so far made the search for valid and reliable psychobiological connections difficult. Nevertheless, considerable progress has now been made in all areas of psychiatric research, made possible above all by the critical review and renewal of previous concepts of disease and psychopathology, the increased orientation towards neurobiology and genetics, and in particular the use of machine learning methods. Notably, modern machine learning methods make it possible to integrate high-dimensional and multimodal data sets and generate models which provide new psychobiological insights and offer the possibility of individualized, biomarker-driven single-subject prediction of diagnosis, therapy response and prognosis. The aim of the present review is therefore to introduce the concept of 'Precision Psychiatry' to the interested reader, to concisely present modern, machine learning methods required for this, and to clearly present the current state and future of biomarker-based 'precision psychiatry'.

Predicting alcohol dependence treatment outcomes: a prospective comparative study of clinical psychologists versus 'trained' machine learning models

BACKGROUND AND AIMS

Clinical staff are typically poor at predicting alcohol dependence treatment outcomes. Machine learning (ML) offers the potential to model complex clinical data more effectively. This study tested the predictive accuracy of ML algorithms demonstrated to be effective in predicting alcohol dependence outcomes, compared with clinical judgement and traditional linear regression.

DESIGN

Prospective study. ML models were trained on 1016 previously treated patients (training-set) who attended a hospital-based alcohol and drug clinic. ML models (n = 27), clinical psychologists (n = 10) and a 'traditional' logistic regression model (n = 1) predicted treatment outcome during the initial treatment session of an alcohol dependence programme.

SETTING

A 12-week cognitive behavioural therapy (CBT)-based abstinence programme for alcohol dependence in a hospital-based alcohol and drug clinic in Australia.

PARTICIPANTS

Prospective predictions were made for 220 new patients (test-set; 70.91% male, mean age = 35.78 years, standard deviation = 9.19). Sixty-nine (31.36%) patients successfully completed treatment.

MEASUREMENTS

Treatment success was the primary outcome variable. The cross-validated training-set accuracy of ML models was used to determine optimal parameters for selecting models for prospective prediction. Accuracy, sensitivity, specificity, area under the receiver operator curve (AUC), Brier score and calibration curves were calculated and compared across predictions.

FINDINGS

The mean aggregate accuracy of the ML models (63.06%) was higher than the mean accuracy of psychologist predictions (56.36%). The most accurate ML model achieved 70% accuracy, as did logistic regression. Both were more accurate than psychologists (P < 0.05) and had superior calibration. The high specificity for the selected ML (79%) and logistic regression (90%) meant they were significantly (P < 0.001) more effective than psychologists (50%) at correctly identifying patients whose treatment was unsuccessful. For ML and logistic regression, high specificity came at the expense of sensitivity (26 and 31%, respectively), resulting in poor prediction of successful patients.

CONCLUSIONS

Machine learning models and logistic regression appear to be more accurate than psychologists at predicting treatment outcomes in an abstinence programme for alcohol dependence, but sensitivity is low.

Machine learning-based analysis of adolescent gambling factors

BACKGROUND AND AIMS

Problem gambling among adolescents has recently attracted attention because of easy access to gambling in online environments and its serious effects on adolescent lives. We proposed a machine learning-based analysis method for predicting the degree of problem gambling.

METHODS

Of the 17,520 respondents in the 2018 National Survey on Youth Gambling Problems dataset (collected by the Korea Center on Gambling Problems), 5,045 students who had gambled in the past 3 months were included in this study. The Gambling Problem Severity Scale was used to provide the binary label information. After the random forest-based feature selection method, we trained four models: random forest (RF), support vector machine (SVM), extra trees (ETs), and ridge regression.

RESULTS

The online gambling behavior in the past 3 months, experience of winning money or goods, and gambling of personal relationship were three factors exhibiting the high feature importance. All four models demonstrated an area under the curve (AUC) of >0.7; ET showed the highest AUC (0.755), RF demonstrated the highest accuracy (71.8%), and SVM showed the highest F1 score (0.507) on a testing set.

DISCUSSION

The results indicate that machine learning models can convey meaningful information to support predictions regarding the degree of problem gambling.

CONCLUSION

Machine learning models trained using important features showed moderate accuracy in a large-scale Korean adolescent dataset. These findings suggest that the method will help screen adolescents at risk of problem gambling. We believe that expandable machine learning-based approaches will become more powerful as more datasets are collected.

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

This conceptual paper describes the current state of mental health services, identifies critical problems, and suggests how to solve them. I focus on the potential contributions of artificial intelligence and precision mental health to improving mental health services. Toward that end, I draw upon my own research, which has changed over the last half century, to highlight the need to transform the way we conduct mental health services research. I identify exemplars from the emerging literature on artificial intelligence and precision approaches to treatment in which there is an attempt to personalize or fit the treatment to the client in order to produce more effective interventions.

Using alcohol consumption diary data from an internet intervention for outcome and predictive modeling: a validation and machine learning study

BACKGROUND

Alcohol use disorder (AUD) is highly prevalent and presents a large treatment gap. Self-help internet interventions are an attractive approach to lowering thresholds for seeking help and disseminating evidence-based programs at scale. Internet interventions for AUD however suffer from high attrition and since continuous outcome measurements are uncommon, little is known about trajectories and processes. The current study investigates whether data from a non-mandatory alcohol consumption diary, common in internet interventions for AUD, approximates drinks reported at follow-up, and whether data from the first half of the intervention predict treatment success.

METHODS

N = 607 participants enrolled in a trial of online self-help for AUD, made an entry in the non-mandatory consumption diary (total of 9117 entries), and completed the follow-up assessment. Using multiple regression and a subset of calendar data overlapping with the follow-up, scaling factors were derived to account for missing entries per participant and week. Generalized estimating equations with an inverse time predictor were then used to calculate point-estimates of drinks per week at follow-up, the confidence intervals of which were compared to that from the measurement at follow-up. Next, calendar data form the first half of the intervention were retained and summary functions used to create 18 predictors for random forest machine learning models, the classification accuracies of which were ultimately estimated using nested cross-validation.

RESULTS

While the raw calendar data substantially underestimated drinks reported at follow-up, the confidence interval of the trajectory-derived point-estimate from the adjusted data overlapped with the confidence interval of drinks reported at follow-up. Machine learning models achieved prediction accuracies of 64% (predicting non-hazardous drinking) and 48% (predicting AUD severity decrease), in both cases with higher sensitivity than specificity.

CONCLUSIONS

Data from a non-mandatory alcohol consumption diary, adjusted for missing entries, approximates follow-up data at a group level, suggesting that such data can be used to reveal trajectories and processes during treatment and possibly be used to impute missing follow-up data. At an individual level, however, calendar data from the first half of the intervention did not have high predictive accuracy, presumable due to a high rate of missing data and unclear missing mechanisms.

Precision Psychiatry Applications with Pharmacogenomics: Artificial Intelligence and Machine Learning Approaches

A growing body of evidence now suggests that precision psychiatry, an interdisciplinary field of psychiatry, precision medicine, and pharmacogenomics, serves as an indispensable foundation of medical practices by offering the accurate medication with the accurate dose at the accurate time to patients with psychiatric disorders. In light of the latest advancements in artificial intelligence and machine learning techniques, numerous biomarkers and genetic loci associated with psychiatric diseases and relevant treatments are being discovered in precision psychiatry research by employing neuroimaging and multi-omics. In this review, we focus on the latest developments for precision psychiatry research using artificial intelligence and machine learning approaches, such as deep learning and neural network algorithms, together with multi-omics and neuroimaging data. Firstly, we review precision psychiatry and pharmacogenomics studies that leverage various artificial intelligence and machine learning techniques to assess treatment prediction, prognosis prediction, diagnosis prediction, and the detection of potential biomarkers. In addition, we describe potential biomarkers and genetic loci that have been discovered to be associated with psychiatric diseases and relevant treatments. Moreover, we outline the limitations in regard to the previous precision psychiatry and pharmacogenomics studies. Finally, we present a discussion of directions and challenges for future research.

Entropy and Algorithm of Obtaining Decision Trees in a Way Approximated to the Natural Intelligence

The classification of knowledge of a specified subject area is an actual task. The well-known methods of obtaining decision trees using entropy are not suitable for the classification of the subject area knowledge. So, a new algorithm of obtaining decision trees, whose way of obtaining is approximated to the natural intelligence, is suggested in the article. Here, the knowledge of a subject area is presented as a complex of answers to questions, which help to find the solution to a current task. The connection of entropy with the appearance of knowledge, the classification of previous knowledge, and the definitions used in decision trees are also analyzed in the article. The latter is necessary to compare the suggested algorithm approximated to the natural intelligence with the traditional method, using a small example. The article contains the analysis of solving a classification task for such a subject area as optimization methods.

An Ensemble Classifier with Case-Based Reasoning System for Identifying Internet Addiction

Internet usage has increased dramatically in recent decades. With this growing usage trend, the negative impacts of Internet usage have also increased significantly. One recurring concern involves users with Internet addiction, whose Internet usage has become excessive and disrupted their lives. In order to detect users with Internet addiction and disabuse their inappropriate behavior early, a secure Web service-based EMBAR (ensemble classifier with case-based reasoning) system is proposed in this study. The EMBAR system monitors users in the background and can be used for Internet usage monitoring in the future. Empirical results demonstrate that our proposed ensemble classifier with case-based reasoning (CBR) in the proposed EMBAR system for identifying users with potential Internet addiction offers better performance than other classifiers.