The application of machine learning techniques as an adjunct to clinical decision making in alcohol dependence treatment

Who responds to a multi-component treatment for cannabis use disorder? Using multivariable and machine learning models to classify treatment responders and non-responders

BACKGROUND AND AIMS

Treatments for cannabis use disorder (CUD) have limited efficacy and little is known about who responds to existing treatments. Accurately predicting who will respond to treatment can improve clinical decision-making by allowing clinicians to offer the most appropriate level and type of care. This study aimed to determine whether multivariable/machine learning models can be used to classify CUD treatment responders versus non-responders.

METHODS

This secondary analysis used data from a National Drug Abuse Treatment Clinical Trials Network multi-site outpatient clinical trial in the United States. Adults with CUD (n = 302) received 12 weeks of contingency management, brief cessation counseling and were randomized to receive additionally either (1) N-Acetylcysteine or (2) placebo. Multivariable/machine learning models were used to classify treatment responders (i.e. two consecutive negative urine cannabinoid tests or a 50% reduction in days of use) versus non-responders using baseline demographic, medical, psychiatric and substance use information.

RESULTS

Prediction performance for various machine learning and regression prediction models yielded area under the curves (AUCs) >0.70 for four models (0.72-0.77), with support vector machine models having the highest overall accuracy (73%; 95% CI = 68-78%) and AUC (0.77; 95% CI = 0.72, 0.83). Fourteen variables were retained in at least three of four top models, including demographic (ethnicity, education), medical (diastolic/systolic blood pressure, overall health, neurological diagnosis), psychiatric (depressive symptoms, generalized anxiety disorder, antisocial personality disorder) and substance use (tobacco smoker, baseline cannabinoid level, amphetamine use, age of experimentation with other substances, cannabis withdrawal intensity) characteristics.

CONCLUSIONS

Multivariable/machine learning models can improve on chance prediction of treatment response to outpatient cannabis use disorder treatment, although further improvements in prediction performance are likely necessary for decisions about clinical care.

Using machine learning to determine the shared and unique risk factors for marijuana use among child-welfare versus community adolescents

OBJECTIVE

This study used machine learning (ML) to test an empirically derived set of risk factors for marijuana use. Models were built separately for child welfare (CW) and non-CW adolescents in order to compare the variables selected as important features/risk factors.

METHOD

Data were from a Time 4 (Mage = 18.22) of longitudinal study of the effects of maltreatment on adolescent development (n = 350; CW = 222; non-CW = 128; 56%male). Marijuana use in the past 12 months (none versus any) was obtained from a single item self-report. Risk factors entered into the model included mental health, parent/family social support, peer risk behavior, self-reported risk behavior, self-esteem, and self-reported adversities (e.g., abuse, neglect, witnessing family violence or community violence).

RESULTS

The ML approaches indicated 80% accuracy in predicting marijuana use in the CW group and 85% accuracy in the non-CW group. In addition, the top features differed for the CW and non-CW groups with peer marijuana use emerging as the most important risk factor for CW youth, whereas externalizing behavior was the most important for the non-CW group. The most important common risk factor between group was gender, with males having higher risk.

CONCLUSIONS

This is the first study to examine the shared and unique risk factors for marijuana use for CW and non-CW youth using a machine learning approach. The results support our assertion that there may be similar risk factors for both groups, but there are also risks unique to each population. Therefore, risk factors derived from normative populations may not have the same importance when used for CW youth. These differences should be considered in clinical practice when assessing risk for substance use among adolescents.

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.

Machine learning in liver transplantation: a tool for some unsolved questions?

Machine learning has recently been proposed as a useful tool in many fields of Medicine, with the aim of increasing diagnostic and prognostic accuracy. Models based on machine learning have been introduced in the setting of solid organ transplantation too, where prognosis depends on a complex, multidimensional and nonlinear relationship between variables pertaining to the donor, the recipient and the surgical procedure. In the setting of liver transplantation, machine learning models have been developed to predict pretransplant survival in patients with cirrhosis, to assess the best donor-to-recipient match during allocation processes, and to foresee postoperative complications and outcomes. This is a narrative review on the role of machine learning in the field of liver transplantation, highlighting strengths and pitfalls, and future perspectives.

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.

Digital Phenotyping to Enhance Substance Use Treatment During the COVID-19 Pandemic

Due to the COVID-19 pandemic, many clinical addiction treatment programs have been required to transition to telephonic or virtual visits. Novel solutions are needed to enhance substance use treatment during a time when many patients are disconnected from clinical care and social support. Digital phenotyping, which leverages the unique functionality of smartphone sensors (GPS, social behavior, and typing patterns), can buttress clinical treatment in a remote, scalable fashion. Specifically, digital phenotyping has the potential to improve relapse prediction and intervention, relapse detection, and overdose intervention. Digital phenotyping may enhance relapse prediction through coupling machine learning algorithms with the enormous amount of collected behavioral data. Activity-based analysis in real time can potentially be used to prevent relapse by warning substance users when they approach locational triggers such as bars or liquor stores. Wearable devices detect when a person has relapsed to substances through measuring physiological changes such as electrodermal activity and locomotion. Despite the initial promise of this approach, privacy, security, and barriers to access are important issues to address.

Substance Use Disorders and COVID-19: Multi-Faceted Problems Which Require Multi-Pronged Solutions

COVID-19 shocked health and economic systems leaving millions of people without employment and safety nets. The pandemic disproportionately affects people with substance use disorders (SUDs) due to the collision between SUDs and COVID-19. Comorbidities and risk environments for SUDs are likely risk factors for COVID-19. The pandemic, in turn, diminishes resources that people with SUD need for their recovery and well-being. This article presents an interdisciplinary and international perspective on how COVID-19 and the related systemic shock impact on individuals with SUDs directly and indirectly. We highlight a need to understand SUDs as biopsychosocial disorders and use evidence-based policies to destigmatize SUDs. We recommend a suite of multi-sectorial actions and strategies to strengthen, modernize and complement addiction care systems which will become resilient and responsive to future systemic shocks similar to the COVID-19 pandemic.

A Machine-Learning Approach to Predicting Smoking Cessation Treatment Outcomes

AIMS

Most cigarette smokers want to quit smoking and more than half make an attempt every year, but less than 10% remain abstinent for at least 6 months. Evidence-based tobacco use treatment improves the likelihood of quitting, but more than two-thirds of individuals relapse when provided even the most robust treatments. Identifying for whom treatment is effective will improve the success of our treatments and perhaps identify strategies for improving current approaches.

METHODS

Two cohorts (training: N = 90, validation: N = 71) of cigarette smokers enrolled in group cognitive-behavioral therapy (CBT). Generalized estimating equations were used to identify baseline predictors of outcome, as defined by breath carbon monoxide and urine cotinine. Significant measures were entered as candidate variables to predict quit status. The resulting decision trees were used to predict cessation outcomes in a validation cohort.

RESULTS

In the training cohort, the decision trees significantly improved on chance classification of smoking status following treatment and at 6-month follow-up. The first split of all decision trees, which was delay discounting, significantly improved on chance classification rates in both the training and validation cohort. Delay discounting emerged as the single best predictor of group CBT treatment response with an average baseline discount rate of ln(k) = -7.1, correctly predicting smoking status of 80% of participants at posttreatment and 81% of participants at follow-up.

CONCLUSIONS

This study provides a first step toward personalized care for smoking cessation though future work is needed to identify individuals that are likely to be successful in treatments beyond group CBT.

IMPLICATIONS

This study provides a first step toward personalized care for smoking cessation. Using a novel machine-learning approach, baseline measures of clinical and executive functioning are used to predict smoking cessation outcomes following group CBT. A decision point is recommended for the single best predictor of treatment outcomes, delay discounting, to inform future research or clinical practice in an effort to better allocate patients to treatments that are likely to work.

Personalized prediction of smartphone-based psychotherapeutic micro-intervention success using machine learning

BACKGROUND

Tailoring healthcare to patients' individual needs is a central goal of precision medicine. Combining smartphone-based interventions with machine learning approaches may help attaining this goal. The aim of our study was to explore the predictability of the success of smartphone-based psychotherapeutic micro-interventions in eliciting mood changes using machine learning.

METHODS

Participants conducted daily smartphone-based psychotherapeutic micro-interventions, guided by short video clips, for 13 consecutive days. Participants chose one of four intervention techniques used in psychotherapeutic approaches. Mood changes were assessed using the Multidimensional Mood State Questionnaire. Micro-intervention success was predicted using random forest (RF) tree-based mixed-effects logistic regression models. Data from 27 participants were used, totaling 324 micro-interventions, randomly split 100 times into training and test samples, using within-subject and between-subject sampling.

RESULTS

Mood improved from pre- to post-intervention in 137 sessions (initial success-rate: 42.3%). The RF approach resulted in predictions of micro-intervention success significantly better than the initial success-rate within and between subjects (positive predictive value: 0.732 (95%-CI: 0.607; 0.820) and 0.698 (95%-CI: 0.564; 0.805), respectively). Prediction quality was highest using the RF approach within subjects (rand accuracy: 0.75 (95%-CI: 0.641; 0.840), Matthew's correlation coefficient: 0.483 (95%-CI: 0.323; 0.723)).

LIMITATIONS

The RF approach does not allow firm conclusions about the exact contribution of each factor to the algorithm's predictions. We included a limited number of predictors and did not compare whether predictability differed between psychotherapeutic techniques.

CONCLUSIONS

Our findings may pave the way for translation and encourage scrutinizing personalized prediction in the psychotherapeutic context to improve treatment efficacy.

Using Machine Learning to Classify Individuals With Alcohol Use Disorder Based on Treatment Seeking Status

OBJECTIVE

The authors used a decision tree classifier to reduce neuropsychological, behavioral and laboratory measures to a subset of measures that best predicted whether an individual with alcohol use disorder (AUD) seeks treatment.

METHOD

Clinical measures (N = 178) from 778 individuals with AUD were used to construct an alternating decision tree (ADT) with 10 measures that best classified individuals as treatment or not treatment-seeking for AUD. ADT's were validated by two methods: using cross-validation and an independent dataset (N = 236). For comparison, two other machine learning techniques were used as well as two linear models.

RESULTS

The 10 measures in the ADT classifier were drinking behavior, depression and drinking-related psychological problems, as well as substance dependence. With cross-validation, the ADT classified 86% of individuals correctly. The ADT classified 78% of the independent dataset correctly. Only the simple logistic model was similar in accuracy; however, this model needed more than twice as many measures as ADT to classify at comparable accuracy.

INTERPRETATION

While there has been emphasis on understanding differences between those with AUD and controls, it is also important to understand, within those with AUD, the features associated with clinically important outcomes. Since the majority of individuals with AUD do not receive treatment, it is important to understand the clinical features associated with treatment utilization; the ADT reported here correctly classified the majority of individuals with AUD with 10 clinically relevant measures, misclassifying < 7% of treatment seekers, while misclassifying 38% of non-treatment seekers. These individual clinically relevant measures can serve, potentially, as separate targets for treatment.

FUNDING

Funding for this work was provided by the Intramural Research Programs of the National Institute on Alcohol Abuse and Alcoholism (NIAAA), National Institute on Drug Abuse (NIDA) and the Center for Information Technology (CIT).

RESEARCH IN CONTEXT

Evidence Before This Study: Less than 10% of persons who meet lifetime criteria for Alcohol Use Disorder (AUD) receive treatment. As the etiology of AUD represents a complex interaction between neurobiological, social, environmental and psychological factors, low treatment utilization likely stems from barriers on multiple levels. Given this issue, it is important from both a research and clinical standpoint to determine what characteristics are associated with treatment utilization in addition to merely asking individuals if they wish to enter treatment. At the level of clinical research, if there are phenotypic differences between treatment and nontreatment-seekers that directly influence outcomes of early-phase studies, these phenotypic differences are a potential confound in assessing the utility of an experimental treatment for AUD. At the level of clinical practice, distinguishing between treatment- and nontreatment-seekers may help facilitate a targeted treatment approach. Previous efforts to understand the differences between these populations of individuals with AUD leveraged the multidimensional data collected in clinical research settings for AUD that are not well suited to traditional regression methods.Added Value of This Study: Alternating decision trees are well suited to deep-phenotyping data collected in clinical research settings as this approach handles nonparametric, skewed, and missing data whose relationships are nonlinear. This approach has proved to be superior in some cases to conventional clinical methods to solve diagnostic problems in medicine. We used a decision tree classifier to understand treatment- and non-treatment seeking group differences. The decision tree classifier approach chose a subset of factors arranged in an alternating decision tree that best predicts a given outcome. Assuming that the input measures are clinically relevant, the alternating decision tree that is generated has clinical value. Unlike other machine learning approaches, in addition to its predictive value, the nodes in the tree and their arrangement in a hierarchy have clinical utility. With the "if-then" logic of the tree, the clinician can learn what features become important and which recede in importance as the logic of the tree is followed. The decision tree classifier approach reduced 178 characterization measures (both categorical and continuous) in multiple domains to a decision tree comprised of 10 measures that together best classified subjects by treatment seeking status (yes/no).Implications After All the Available Evidence: We leveraged a large data set comprised of 178 clinical measures and using the decision tree approach, we have reduced these to a subset of 10 measures that accurately classified individuals with alcohol dependence by treatment utilization. From this analysis, drinking behavior variables and depression measures are strong treatment seeking predictors. Having identified a cluster of factors that predicts treatment seeking, we can assess the influence of these factors directly on the clinical study outcome measures themselves. In clinical practice these factors can be separate targets for treatment. In clinical research, the group differences my directly influence research outcomes for treatment of AUD.

Machine learning vs addiction therapists: A pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication

BACKGROUND AND OBJECTIVES

Clinical staff providing addiction treatment predict patient outcome poorly. Prognoses based on linear statistics are rarely replicated. Addiction is a complex non-linear behavior. Incorporating non-linear models, Machine Learning (ML) has successfully predicted treatment outcome when applied in other areas of medicine. Using identical assessment data across the two groups, this study compares the accuracy of ML models versus clinical staff to predict alcohol dependence treatment outcome in behavior therapy using patient data only.

METHODS

Machine learning models (n = 28) were constructed ('trained') using demographic and psychometric assessment data from 780 previously treated patients who had undertaken a 12 week, abstinence-based Cognitive Behavioral Therapy program for alcohol dependence. Independent predictions applying assessment data for an additional 50 consecutive patients were obtained from 10 experienced addiction therapists and the 28 trained ML models. The predictive accuracy of the ML models and the addiction therapists was then compared with further investigation of the 10 best models selected by cross-validated accuracy on the training-set. Variables selected as important for prediction by staff and the most accurate ML model were examined.

RESULTS

The most accurate ML model (Fuzzy Unordered Rule Induction Algorithm, 74%) was significantly more accurate than the four least accurate clinical staff (51%-40%). However, the robustness of this finding may be limited by the moderate area under the receiver operator curve (AUC = 0.49). There was no significant difference in mean aggregate predictive accuracy between 10 clinical staff (56.1%) and the 28 best models (58.57%). Addiction therapists favoured demographic and consumption variables compared with the ML model using more questionnaire subscales.

CONCLUSIONS

The majority of staff and ML models were not more accurate than suggested by chance. However, the best performing prediction models may provide useful adjunctive information to standard clinically available prognostic data to more effectively target treatment approaches in clinical settings.

Towards enhanced metabolomic data analysis of mass spectrometry image: Multivariate Curve Resolution and Machine Learning

Large amounts of data are generally produced from mass spectrometry imaging (MSI) experiments in obtaining the molecular and spatial information of biological samples. Traditionally, MS images are constructed using manually selected ions, and it is very challenging to comprehensively analyze MSI results due to their large data sizes and highly complex data structures. To overcome these barriers, it is obligatory to develop advanced data analysis approaches to handle the increasingly large MSI data. In the current study, we focused on the method development of using Multivariate Curve Resolution (MCR) and Machine Learning (ML) approaches. We aimed to effectively extract the essential information present in the large and complex MSI data and enhance the metabolomic data analysis of biological tissues. Multivariate Curve Resolution-Alternating Least Squares (MCR-ALS) algorithm was used to obtain major patterns of spatial distribution and grouped metabolites with the same spatial distribution patterns. In addition, both supervised and unsupervised ML methods were established to analyze the MSI data. In the supervised ML approach, Random Forest method was selected, and the model was trained using the selected datasets based on the distribution pattern obtained from MCR-ALS analyses. In the unsupervised ML approach, both DBSCAN (Density-based Spatial Clustering of Applications with Noise) and CLARA (Clustering Large Applications) were applied to cluster the MSI datasets. It is worth noting that similar patterns of spatial distribution were discovered through MSI data analysis using MCR-ALS, supervised ML, and unsupervised ML. Our protocols of data analysis can be applied to process the data acquired using many other types of MSI techniques, and to extract the overall features present in MSI results that are intractable using traditional data analysis approaches.

e-Addictology: An Overview of New Technologies for Assessing and Intervening in Addictive Behaviors

BACKGROUND

New technologies can profoundly change the way we understand psychiatric pathologies and addictive disorders. New concepts are emerging with the development of more accurate means of collecting live data, computerized questionnaires, and the use of passive data. Digital phenotyping, a paradigmatic example, refers to the use of computerized measurement tools to capture the characteristics of different psychiatric disorders. Similarly, machine learning-a form of artificial intelligence-can improve the classification of patients based on patterns that clinicians have not always considered in the past. Remote or automated interventions (web-based or smartphone-based apps), as well as virtual reality and neurofeedback, are already available or under development.

OBJECTIVE

These recent changes have the potential to disrupt practices, as well as practitioners' beliefs, ethics and representations, and may even call into question their professional culture. However, the impact of new technologies on health professionals' practice in addictive disorder care has yet to be determined. In the present paper, we therefore present an overview of new technology in the field of addiction medicine.

METHOD

Using the keywords [e-health], [m-health], [computer], [mobile], [smartphone], [wearable], [digital], [machine learning], [ecological momentary assessment], [biofeedback] and [virtual reality], we searched the PubMed database for the most representative articles in the field of assessment and interventions in substance use disorders.

RESULTS

We screened 595 abstracts and analyzed 92 articles, dividing them into seven categories: e-health program and web-based interventions, machine learning, computerized adaptive testing, wearable devices and digital phenotyping, ecological momentary assessment, biofeedback, and virtual reality.

CONCLUSION

This overview shows that new technologies can improve assessment and interventions in the field of addictive disorders. The precise role of connected devices, artificial intelligence and remote monitoring remains to be defined. If they are to be used effectively, these tools must be explained and adapted to the different profiles of physicians and patients. The involvement of patients, caregivers and other health professionals is essential to their design and assessment.

Computational neuroscience approach to biomarkers and treatments for mental disorders

Psychiatry research has long experienced a stagnation stemming from a lack of understanding of the neurobiological underpinnings of phenomenologically defined mental disorders. Recently, the application of computational neuroscience to psychiatry research has shown great promise in establishing a link between phenomenological and pathophysiological aspects of mental disorders, thereby recasting current nosology in more biologically meaningful dimensions. In this review, we highlight recent investigations into computational neuroscience that have undertaken either theory- or data-driven approaches to quantitatively delineate the mechanisms of mental disorders. The theory-driven approach, including reinforcement learning models, plays an integrative role in this process by enabling correspondence between behavior and disorder-specific alterations at multiple levels of brain organization, ranging from molecules to cells to circuits. Previous studies have explicated a plethora of defining symptoms of mental disorders, including anhedonia, inattention, and poor executive function. The data-driven approach, on the other hand, is an emerging field in computational neuroscience seeking to identify disorder-specific features among high-dimensional big data. Remarkably, various machine-learning techniques have been applied to neuroimaging data, and the extracted disorder-specific features have been used for automatic case-control classification. For many disorders, the reported accuracies have reached 90% or more. However, we note that rigorous tests on independent cohorts are critically required to translate this research into clinical applications. Finally, we discuss the utility of the disorder-specific features found by the data-driven approach to psychiatric therapies, including neurofeedback. Such developments will allow simultaneous diagnosis and treatment of mental disorders using neuroimaging, thereby establishing 'theranostics' for the first time in clinical psychiatry.

Identifying Future Drinkers: Behavioral Analysis of Monkeys Initiating Drinking to Intoxication is Predictive of Future Drinking Classification

BACKGROUND

The Monkey Alcohol Tissue Research Resource (MATRR) is a repository and analytics platform for detailed data derived from well-documented nonhuman primate (NHP) alcohol self-administration studies. This macaque model has demonstrated categorical drinking norms reflective of human drinking populations, resulting in consumption pattern classifications of very heavy drinking (VHD), heavy drinking (HD), binge drinking (BD), and low drinking (LD) individuals. Here, we expand on previous findings that suggest ethanol drinking patterns during initial drinking to intoxication can reliably predict future drinking category assignment.

METHODS

The classification strategy uses a machine-learning approach to examine an extensive set of daily drinking attributes during 90 sessions of induction across 7 cohorts of 5 to 8 monkeys for a total of 50 animals. A Random Forest classifier is employed to accurately predict categorical drinking after 12 months of self-administration.

RESULTS

Predictive outcome accuracy is approximately 78% when classes are aggregated into 2 groups, "LD and BD" and "HD and VHD." A subsequent 2-step classification model distinguishes individual LD and BD categories with 90% accuracy and between HD and VHD categories with 95% accuracy. Average 4-category classification accuracy is 74%, and provides putative distinguishing behavioral characteristics between groupings.

CONCLUSIONS

We demonstrate that data derived from the induction phase of this ethanol self-administration protocol have significant predictive power for future ethanol consumption patterns. Importantly, numerous predictive factors are longitudinal, measuring the change of drinking patterns through 3 stages of induction. Factors during induction that predict future heavy drinkers include being younger at the time of first intoxication and developing a shorter latency to first ethanol drink. Overall, this analysis identifies predictive characteristics in future very heavy drinkers that optimize intoxication, such as having increasingly fewer bouts with more drinks. This analysis also identifies characteristic avoidance of intoxicating topographies in future low drinkers, such as increasing number of bouts and waiting longer before the first ethanol drink.

Individualized relapse prediction: Personality measures and striatal and insular activity during reward-processing robustly predict relapse

BACKGROUND

Nearly half of individuals with substance use disorders relapse in the year after treatment. A diagnostic tool to help clinicians make decisions regarding treatment does not exist for psychiatric conditions. Identifying individuals with high risk for relapse to substance use following abstinence has profound clinical consequences. This study aimed to develop neuroimaging as a robust tool to predict relapse.

METHODS

68 methamphetamine-dependent adults (15 female) were recruited from 28-day inpatient treatment. During treatment, participants completed a functional MRI scan that examined brain activation during reward processing. Patients were followed 1 year later to assess abstinence. We examined brain activation during reward processing between relapsing and abstaining individuals and employed three random forest prediction models (clinical and personality measures, neuroimaging measures, a combined model) to generate predictions for each participant regarding their relapse likelihood.

RESULTS

18 individuals relapsed. There were significant group by reward-size interactions for neural activation in the left insula and right striatum for rewards. Abstaining individuals showed increased activation for large, risky relative to small, safe rewards, whereas relapsing individuals failed to show differential activation between reward types. All three random forest models yielded good test characteristics such that a positive test for relapse yielded a likelihood ratio 2.63, whereas a negative test had a likelihood ratio of 0.48.

CONCLUSIONS

These findings suggest that neuroimaging can be developed in combination with other measures as an instrument to predict relapse, advancing tools providers can use to make decisions about individualized treatment of substance use disorders.

How well can post-traumatic stress disorder be predicted from pre-trauma risk factors? An exploratory study in the WHO World Mental Health Surveys

Post-traumatic stress disorder (PTSD) should be one of the most preventable mental disorders, since many people exposed to traumatic experiences (TEs) could be targeted in first response settings in the immediate aftermath of exposure for preventive intervention. However, these interventions are costly and the proportion of TE-exposed people who develop PTSD is small. To be cost-effective, risk prediction rules are needed to target high-risk people in the immediate aftermath of a TE. Although a number of studies have been carried out to examine prospective predictors of PTSD among people recently exposed to TEs, most were either small or focused on a narrow sample, making it unclear how well PTSD can be predicted in the total population of people exposed to TEs. The current report investigates this issue in a large sample based on the World Health Organization (WHO)'s World Mental Health Surveys. Retrospective reports were obtained on the predictors of PTSD associated with 47,466 TE exposures in representative community surveys carried out in 24 countries. Machine learning methods (random forests, penalized regression, super learner) were used to develop a model predicting PTSD from information about TE type, socio-demographics, and prior histories of cumulative TE exposure and DSM-IV disorders. DSM-IV PTSD prevalence was 4.0% across the 47,466 TE exposures. 95.6% of these PTSD cases were associated with the 10.0% of exposures (i.e., 4,747) classified by machine learning algorithm as having highest predicted PTSD risk. The 47,466 exposures were divided into 20 ventiles (20 groups of equal size) ranked by predicted PTSD risk. PTSD occurred after 56.3% of the TEs in the highest-risk ventile, 20.0% of the TEs in the second highest ventile, and 0.0-1.3% of the TEs in the 18 remaining ventiles. These patterns of differential risk were quite stable across demographic-geographic sub-samples. These results demonstrate that a sensitive risk algorithm can be created using data collected in the immediate aftermath of TE exposure to target people at highest risk of PTSD. However, validation of the algorithm is needed in prospective samples, and additional work is warranted to refine the algorithm both in terms of determining a minimum required predictor set and developing a practical administration and scoring protocol that can be used in routine clinical practice.

Neuroticism and impulsivity: their hierarchical organization in the personality characterization of drug-dependent patients from a decision tree learning perspective

OBJECTIVE

Neuroticism and impulsivity are the personality variables most consistently associated with drug-dependent patients. To date, no data mining procedures have been applied to explore the differential role of personality variables in this population.

METHODS

The personality profile of 336 drug-dependent patients was compared with that of a sample of community participants in the context of a decision tree learning approach using the Alternative Five Factor Model. The resulting discriminant model was cross-validated.

RESULTS

Neuroticism and impulsivity were the most relevant variables in the resulting model, but their association appeared to be hierarchically organized. In the personality characterization of these patients, neuroticism became the main discriminant dimension, whereas impulsivity played a differential role, explained by means of an interaction effect. Decision tree learning models appear to be a heuristic theoretical and empirical approximation to the study of relevant variables, such as personality traits, in drug-dependency research.

Predictive modeling of addiction lapses in a mobile health application

The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support.

Predictors of heavy drinking during and following treatment

Alcohol dependence has been described as a relapsing condition and it has been proposed that alcohol lapses could potentially be explained by dynamic associations between contextual, interpersonal, and intrapersonal risk factors. Yet, few studies have tested the associations between risk factors in the prediction of lapse dynamics. The current study was a secondary analysis of data from the COMBINE study (n = 1,383; COMBINE Study Research Group, 2003). The goal of the current study was to examine static (alcohol dependence severity, treatment history, marital status, psychiatric symptoms) and dynamic (negative affect, craving, stress) predictors of heavy drinking during the course of treatment and up to one year following treatment. Results from dynamic latent difference score models indicated that higher levels of static and dynamic risk and increased dynamic risk over time were significantly associated with greater increases in heavy drinking. Likewise, more frequent heavy drinking and higher static risk predicted higher levels of dynamic risk. In addition, changes in dynamic risk factors significantly mediated the association between changes in heavy drinking and both psychiatric symptoms and treatment history. It is important to note that while the effects of static and dynamic risk factors in the prediction of heavy drinking were statistically significant, the magnitude of the effects were small. The current study provided partial support for a dynamic model of relapse; however future research using intensive longitudinal data collection and more advanced statistical techniques could further elucidate lapse dynamics and potentially improve relapse prevention planning.