Use of a machine learning framework to predict substance use disorder treatment success

Machine learning applications in studying mental health among immigrants and racial and ethnic minorities: an exploratory scoping review

BACKGROUND

The use of machine learning (ML) in mental health (MH) research is increasing, especially as new, more complex data types become available to analyze. By examining the published literature, this review aims to explore the current applications of ML in MH research, with a particular focus on its use in studying diverse and vulnerable populations, including immigrants, refugees, migrants, and racial and ethnic minorities.

METHODS

From October 2022 to March 2024, Google Scholar, EMBASE, and PubMed were queried. ML-related, MH-related, and population-of-focus search terms were strung together with Boolean operators. Backward reference searching was also conducted. Included peer-reviewed studies reported using a method or application of ML in an MH context and focused on the populations of interest. We did not have date cutoffs. Publications were excluded if they were narrative or did not exclusively focus on a minority population from the respective country. Data including study context, the focus of mental healthcare, sample, data type, type of ML algorithm used, and algorithm performance were extracted from each.

RESULTS

Ultimately, 13 peer-reviewed publications were included. All the articles were published within the last 6 years, and over half of them studied populations within the US. Most reviewed studies used supervised learning to explain or predict MH outcomes. Some publications used up to 16 models to determine the best predictive power. Almost half of the included publications did not discuss their cross-validation method.

CONCLUSIONS

The included studies provide proof-of-concept for the potential use of ML algorithms to address MH concerns in these special populations, few as they may be. Our review finds that the clinical application of these models for classifying and predicting MH disorders is still under development.

Improving treatment completion for young adults with substance use disorder: Machine learning-based prediction algorithms

Substance use disorder (SUD) treatment completion was intertwined with various factors. However, few studies have explored the intersections of psychosocial and system-related factors with SUD treatment completion, particularly for individuals receiving publicly funded SUD treatment services. This study aimed to examine the intersections of these factors with treatment completion. We analyzed the psycho-social assessment data of 2909 young adults who participated in publicly funded outpatient-based substance use treatments in 2021. The Chi-square Automatic Interaction Detection (CHAID) approach was employed to examine intersections for SUD treatment completion. The analysis highlights the significance of multiple factors and their interactions in predicting SUD treatment completion. The results indicate that SUD treatment outcomes varied based on the level of improvement rates in total actionable items (TAI) improvement rates, underscoring the importance of monitoring individual progress in treatment. Specifically, among young adults with the highest TAI, those residing in rural communities were less likely to complete treatment compared to their urban counterparts. For individuals with TAI improvement rates at the middle level, there was a significant intersection with criminal justice involvement. Within this subgroup, individuals who had both justice system involvement and opioid use disorders had a relatively low SUD treatment completion rate, while those with non-opioid-related SUD exhibited a higher completion rate. The study illustrates the importance of considering multiple factors and their interactions, including TAI improvement rates, family strengths, demographic characteristics, and social determinants, in predicting SUD treatment completion among young adults.

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.

Exploring predictors of substance use disorder treatment engagement with machine learning: The impact of social determinants of health in the therapeutic landscape

BACKGROUND

Improved knowledge of factors that influence treatment engagement could help treatment providers and systems better engage patients. The present study used machine learning to explore associations between individual- and neighborhood-level factors, and SUD treatment engagement.

METHODS

This was a secondary analysis of the Global Appraisal of Individual Needs (GAIN) dataset and United States Census Bureau data utilizing random forest machine learning and generalized linear mixed modelling. Our sample (N = 15,873) included all people entering SUD treatment at GAIN sites from 2006 to 2012. Predictors included an array of demographic, psychosocial, treatment-specific, and clinical measures, as well as environment-level measures for the neighborhood in which patients received treatment.

RESULTS

Greater odds of treatment engagement were predicted by adolescent age and psychiatric comorbidity, and at the neighborhood-level, by low unemployment and high population density. Lower odds of treatment engagement were predicted by Black/African American race, and at the neighborhood-level by high rate of public assistance and high income inequality. Regardless of the degree of treatment engagement, individuals receiving treatment in areas with high unemployment, alcohol sale outlet concentration, and poverty had greater substance use and related problems at baseline. Although these differences reduced with treatment and over time, disparities remained.

CONCLUSIONS

Neighborhood-level factors appear to play an important role in SUD treatment engagement. Regardless of whether individuals engage with treatment, greater loading on social determinants of health such as unemployment, alcohol sale outlet density, and poverty in the therapeutic landscape are associated with worse SUD treatment outcomes.

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.

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

The core idea behind precision medicine is to pinpoint the subpopulations that differ from one another in terms of disease risk, drug responsiveness, and treatment outcomes due to differences in biology and other traits. Biomarkers are found through genomic sequencing. Multi-dimensional clinical and biological data are created using these biomarkers. Better analytic methods are needed for these multidimensional data, which can be accomplished by using artificial intelligence (AI). An updated review of 80 latest original publications is presented on four main fronts-preventive medicine, medication development, treatment outcomes, and diagnostic medicine-All these studies effectively illustrated the significance of AI in precision medicine. Artificial intelligence (AI) has revolutionized precision medicine by swiftly analyzing vast amounts of data to provide tailored treatments and predictive diagnostics. Through machine learning algorithms and high-resolution imaging, AI assists in precise diagnoses and early disease detection. AI's ability to decode complex biological factors aids in identifying novel therapeutic targets, allowing personalized interventions and optimizing treatment outcomes. Furthermore, AI accelerates drug discovery by navigating chemical structures and predicting drug-target interactions, expediting the development of life-saving medications. With its unrivaled capacity to comprehend and interpret data, AI stands as an invaluable tool in the pursuit of enhanced patient care and improved health outcomes. It's evident that AI can open a new horizon for precision medicine by translating complex data into actionable information. To get better results in this regard and to fully exploit the great potential of AI, further research is required on this pressing subject.

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.

Assessing treatment switch among patients with multiple sclerosis: A machine learning approach

BACKGROUND

Patients with multiple sclerosis (MS) frequently switch their Disease-Modifying Agents (DMA) for effectiveness and safety concerns. This study aimed to develop and compare the random forest (RF) machine learning (ML) model with the logistic regression (LR) model for predicting DMA switching among MS patients.

METHODS

This retrospective longitudinal study used the TriNetX data from a federated electronic medical records (EMR) network. Between September 2010 and May 2017, adults (aged ≥18) MS patients with ≥1 DMA prescription were identified, and the earliest DMA date was assigned as the index date. Patients prescribed any DMAs different from their index DMAs were considered as treatment switch. . The RF and LR models were built with 72 baseline characteristics and trained with 70% of the randomly split data after up-sampling. Area Under the Curves (AUC), accuracy, recall, G-measure, and F-1 score were used to evaluate the model performance.

RESULTS

In this study, 7258 MS patients with ≥1 DMA were identified. Within two years, 16% of MS patients switched to a different DMA. The RF model obtained significantly better discrimination than the LR model (AUC = 0.65 vs. 0.63, p < 0.0001); however, the RF model had a similar predictive performance to the LR model with respect to F- and G-measures (RF: 72% and 73% vs. LR: 72% and 73%, respectively). The most influential features identified from the RF model were age, type of index medication, and year of index.

CONCLUSIONS

Compared to the LR model, RF performed better in predicting DMA switch in MS patients based on AUC measures; however, judged by F- and G-measures, the RF model performed similarly to LR. Further research is needed to understand the role of ML techniques in predicting treatment outcomes for the decision-making process to achieve optimal treatment goals.

Artificial intelligence in psychiatry research, diagnosis, and therapy

Psychiatric disorders are now responsible for the largest proportion of the global burden of disease, and even more challenges have been seen during the COVID-19 pandemic. Artificial intelligence (AI) is commonly used to facilitate the early detection of disease, understand disease progression, and discover new treatments in the fields of both physical and mental health. The present review provides a broad overview of AI methodology and its applications in data acquisition and processing, feature extraction and characterization, psychiatric disorder classification, potential biomarker detection, real-time monitoring, and interventions in psychiatric disorders. We also comprehensively summarize AI applications with regard to the early warning, diagnosis, prognosis, and treatment of specific psychiatric disorders, including depression, schizophrenia, autism spectrum disorder, attention-deficit/hyperactivity disorder, addiction, sleep disorders, and Alzheimer's disease. The advantages and disadvantages of AI in psychiatry are clarified. We foresee a new wave of research opportunities to facilitate and improve AI technology and its long-term implications in psychiatry during and after the COVID-19 era.

Determinants of outpatient substance use disorder treatment length-of-stay and completion: the case of a treatment program in the southeast U.S

Successful outcomes of outpatient substance use disorder treatment result from many factors for clients-including intersections between individual characteristics, choices made, and social determinants. However, prioritizing which of these and in what combination, to address and provide support for remains an open and complex question. Therefore, we ask: What factors are associated with outpatient substance use disorder clients remaining in treatment for > 90 days and successfully completing treatment? To answer this question, we apply a virtual twins machine learning (ML) model to de-identified data for a census of clients who received outpatient substance use disorder treatment services from 2018 to 2021 from one treatment program in the Southeast U.S. We find that primary predictors of outcome success are: (1) attending self-help groups while in treatment, and (2) setting goals for treatment. Secondary predictors are: (1) being linked to a primary care provider (PCP) during treatment, (2) being linked to supplemental nutrition assistance program (SNAP), and (3) attending 6 or more self-help group sessions during treatment. These findings can help treatment programs guide client choice making and help set priorities for social determinant support. Further, the ML method applied can explain intersections between individual and social predictors, as well as outcome heterogeneity associated with subgroup differences.

Using Machine Learning to Predict Treatment Adherence in Patients on Medication for Opioid Use Disorder

OBJECTIVE

Patients receiving medication for opioid use disorder (MOUD) may continue using nonprescribed drugs or have trouble with medication adherence, and it is difficult to predict which patients will continue to do so. In this study, we develop and validate an automated risk-modeling framework to predict opioid abstinence and medication adherence at a patient's next attended appointment and evaluate the predictive performance of machine-learning algorithms versus logistic regression.

METHODS

Urine drug screen and attendance records from 40,005 appointments drawn from 2742 patients at a multilocation office-based MOUD program were used to train logistic regression, logistic ridge regression, and XGBoost models to predict a composite indicator of treatment adherence (opioid-negative and norbuprenorphine-positive urine, no evidence of urine adulteration) at next attended appointment.

RESULTS

The XGBoost model had similar accuracy and discriminative ability (accuracy, 88%; area under the receiver operating curve, 0.87) to the two logistic regression models (accuracy, 88%; area under the receiver operating curve, 0.87). The XGBoost model had nearly perfect calibration in independent validation data; the logistic and ridge regression models slightly overestimated adherence likelihood. Historical treatment adherence, attendance rate, and fentanyl-positive urine at current appointment were the strongest contributors to treatment adherence at next attended appointment.

DISCUSSION

There is a need for risk prediction tools to improve delivery of MOUD. This study presents an automated and portable risk-modeling framework to predict treatment adherence at each patient's next attended appointment. The XGBoost algorithm appears to provide similar classification accuracy to logistic regression models; however, XGBoost may offer improved calibration of risk estimates compared with logistic regression.

Using machine learning to study the effect of medication adherence in Opioid Use Disorder

BACKGROUND

Opioid Use Disorder (OUD) and opioid overdose (OD) impose huge social and economic burdens on society and health care systems. Research suggests that Medication for Opioid Use Disorder (MOUD) is effective in the treatment of OUD. We use machine learning to investigate the association between patient's adherence to prescribed MOUD along with other risk factors in patients diagnosed with OUD and potential OD following the treatment.

METHODS

We used longitudinal Medicaid claims for two selected US states to subset a total of 26,685 patients with OUD diagnosis and appropriate Medicaid coverage between 2015 and 2018. We considered patient age, sex, region level socio-economic data, past comorbidities, MOUD prescription type and other selected prescribed medications along with the Proportion of Days Covered (PDC) as a proxy for adherence to MOUD as predictive variables for our model, and overdose events as the dependent variable. We applied four different machine learning classifiers and compared their performance, focusing on the importance and effect of PDC as a variable. We also calculated results based on risk stratification, where our models separate high risk individuals from low risk, to assess usefulness in clinical decision-making.

RESULTS

Among the selected classifiers, the XGBoost classifier has the highest AUC (0.77) closely followed by the Logistic Regression (LR). The LR has the best stratification result: patients in the top 10% of risk scores account for 35.37% of overdose events over the next 12 month observation period. PDC score calculated over the treatment window is one of the most important features, with better PDC lowering risk of OD, as expected. In terms of risk stratification results, of the 35.37% of overdose events that the predictive model could detect within the top 10% of risk scores, 72.3% of these cases were non-adherent in terms of their medication (PDC <0.8). Targeting the top 10% outcome of the predictive model could decrease the total number of OD events by 10.4%.

CONCLUSIONS

The best performing models allow identification of, and focus on, those at high risk of opioid overdose. With MOUD being included for the first time as a factor of interest, and being identified as a significant factor, outreach activities related to MOUD can be targeted at those at highest risk.

Retention in treatment and therapeutic adherence: How are these associated with therapeutic success? An analysis using real-world data

INTRODUCTION

Treatment retention and adherence are used as outcomes in numerous randomized clinical trials and observational studies conducted in the addiction field. Although usual criteria are 3/6 months of treatment retention or number of sessions attended, there is not a methodological support for conclusions using these criteria. This study analyzed the usefulness of retention and adherence to predict therapeutic success.

METHODS

Retrospective observational study using real-world data from electronic health records of 11,907 patients in treatment diagnosed with cocaine, alcohol, cannabis and opiate use disorders or harmful use.

RESULTS

Moderate effect size relations were found between the different type of clinical discharge and months in retention (η2  = 0.12) and proportion of attendance (η2  = 0.10). No relationship was found with the number of sessions attended. Using cut-off points (i.e., 3 or 6 months in treatment or attending 6 therapy sessions) worsens the ability to predict the type of discharge.

DISCUSSIONS/CONCLUSION

Treatment retention and adherence are indicators moderately related to therapeutic success. Research using these indicators to assess the effectiveness of therapies should complement their results with other clinical indicators and quality of life measures.

Machine-learning prediction for hospital length of stay using a French medico-administrative database

INTRODUCTION

Prolonged Hospital Length of Stay (PLOS) is an indicator of deteriorated efficiency in Quality of Care. One goal of public health management is to reduce PLOS by identifying its most relevant predictors. The objective of this study is to explore Machine Learning (ML) models that best predict PLOS.

METHODS

Our dataset was collected from the French Medico-Administrative database (PMSI) as a retrospective cohort study of all discharges in the year 2015 from a large university hospital in France (APHM). The study outcomes were LOS transformed into a binary variable (long vs. short LOS) according to the 90^th percentile (14 days). Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB) and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the area under the ROC curve (AUC).

RESULTS

Our analysis included 73,182 hospitalizations, of which 7,341 (10.0%) led to PLOS. The GB classifier was the most performant model with the highest AUC (0.810), superior to all the other models (all p-values <0.0001). The performance of the RF, GB and NN models (AUC ranged from 0.808 to 0.810) was superior to that of the LR model (AUC = 0.795); all p-values <0.0001. In contrast, LR was superior to CART (AUC = 0.786), p < 0.0001. The variable most predictive of the PLOS was the destination of the patient after hospitalization to other institutions. The typical clinical profile of these patients (17.5% of the sample) was the elderly patient, admitted in emergency, for a trauma, a neurological or a cardiovascular pathology, more often institutionalized, with more comorbidities notably mental health problems, dementia and hemiplegia.

DISCUSSION

The integration of ML, particularly the GB algorithm, may be useful for health-care professionals and bed managers to better identify patients at risk of PLOS. These findings underscore the need to strengthen hospitals through targeted allocation to meet the needs of an aging population.

Biomedical Research on Substances of Abuse: The Italian Case Study

Substances of abuse have the potential to cause addiction, habituation or altered consciousness. Most of the research on these substances focuses on addiction, and is carried out through observational and clinical studies on humans, or experimental studies on animals. The transposition of the EU Directive 2010/63 into Italian law in 2014 (IT Law 2014/26) includes a ban on the use of animals for research on substances of abuse. Since then, in Italy, public debate has continued on the topic, while the application of the Article prohibiting animal research in this area has been postponed every couple of years. In the light of this debate, we briefly review a range of methodologies - including animal and non-animal, as well as patient or population-based studies - that have been employed to address the biochemical, neurobiological, toxicological, clinical and behavioural effects of substances of abuse and their dependency. We then discuss the implications of the Italian ban on the use of animals for such research, proposing concrete and evidence-based solutions to allow scientists to pursue high-quality basic and translational studies within the boundaries of the regulatory and legislative framework.

Use of machine learning to examine disparities in completion of substance use disorder treatment

The objective of this work is to examine disparities in the completion of substance use disorder treatment in the U.S. Our data is from the Treatment Episode Dataset Discharge (TEDS-D) datasets from the U.S. Substance Abuse and Mental Health Services Administration (SAMHSA) for 2017-2019. We apply a two-stage virtual twins model (random forest + decision tree) where, in the first stage (random forest), we determine differences in treatment completion probability associated with race/ethnicity, income source, no co-occurrence of mental health disorders, gender (biological), no health insurance, veteran status, age, and primary substance (alcohol or opioid). In the second stage (decision tree), we identify subgroups associated with probability differences, where such subgroups are more or less likely to complete treatment. We find the subgroups most likely to complete substance use disorder treatment, when the subgroup represents more than 1% of the sample, are those with no mental health condition co-occurrence (4.8% more likely when discharged from an ambulatory outpatient treatment program, representing 62% of the sample; and 10% more likely for one of the more specifically defined subgroups representing 10% of the sample), an income source of job-related wages/salary (4.3% more likely when not having used in the 30 days primary to discharge and when primary substance is not alcohol only, representing 28% of the sample), and white non-Hispanics (2.7% more likely when discharged from residential long-term treatment, representing 9% of the sample). Important implications are that: 1) those without a co-occurring mental health condition are the most likely to complete treatment, 2) those with job related wages or income are more likely to complete treatment, and 3) racial/ethnicity disparities persist in favor of white non-Hispanic individuals seeking to complete treatment. Thus, additional resources may be needed to combat such disparities.

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.

Optimizing Substance Use Treatment Selection Using Reinforcement Learning

Substance use disorder (SUD) exacts a substantial economic and social cost in the United States, and it is crucial for SUD treatment providers to match patients with feasible, effective, and affordable treatment plans. The availability of large SUD patient datasets allows for machine learning techniques to predict patient-level SUD outcomes, yet there has been almost no research on whether machine learning can be used to optimize or personalize which treatment plans SUD patients receive. We use contextual bandits (a reinforcement learning technique) to optimally map patients to SUD treatment plans, based on dozens of patient-level and geographic covariates. We also use near-optimal policies to incorporate treatments’ time-intensiveness and cost into our recommendations, to aid treatment providers and policymakers in allocating treatment resources. Our personalized treatment recommendation policies are estimated to yield higher remission rates than observed in our original dataset, and they suggest clinical insights to inform future research on data-driven SUD treatment matching.

Correlates of cannabis use disorder in the United States: A comparison of logistic regression, classification trees, and random forests

Although several recent studies have examined psychosocial and demographic correlates of cannabis use disorder (CUD) in adults, few, if any, recent studies have evaluated the performance of machine learning methods relative to standard logistic regression for identifying correlates of CUD. The present study used pooled data from the 2015-2018 National Survey on Drug Use and Health to evaluate psychosocial and demographic correlates of CUD in adults. In addition, we compared the performance of logistic regression, classification trees, and random forest methods in classifying CUD. When comparing the performance of each method on the test data set, classification trees (AUC = 0.84, 95%CI: 0.82, 0.85) and random forest (AUC = 0.83, 95%CI: 0.82, 8.05) performed similarly and superior to logistic regression (AUC = 0.77, 95%CI: 0.74, 0.79). Results of the random forests reveal that marital status, risk propensity, age, and cocaine dependence variables contributed most to node purity, whereas model accuracy would decrease significantly if county type, income, race, and education variables were excluded from the model. One possible approach to improving the efficiency, interpretability, and clinical insights of CUD correlates is the employment of machine learning techniques.

Patterns and correlates of patient-reported helpfulness of treatment for common mental and substance use disorders in the WHO World Mental Health Surveys

Patient-reported helpfulness of treatment is an important indicator of quality in patient-centered care. We examined its pathways and predictors among respondents to household surveys who reported ever receiving treatment for major depression, generalized anxiety disorder, social phobia, specific phobia, post-traumatic stress disorder, bipolar disorder, or alcohol use disorder. Data came from 30 community epidemiological surveys - 17 in high-income countries (HICs) and 13 in low- and middle-income countries (LMICs) - carried out as part of the World Health Organization (WHO)'s World Mental Health (WMH) Surveys. Respondents were asked whether treatment of each disorder was ever helpful and, if so, the number of professionals seen before receiving helpful treatment. Across all surveys and diagnostic categories, 26.1% of patients (N=10,035) reported being helped by the very first professional they saw. Persisting to a second professional after a first unhelpful treatment brought the cumulative probability of receiving helpful treatment to 51.2%. If patients persisted with up through eight professionals, the cumulative probability rose to 90.6%. However, only an estimated 22.8% of patients would have persisted in seeing these many professionals after repeatedly receiving treatments they considered not helpful. Although the proportion of individuals with disorders who sought treatment was higher and they were more persistent in HICs than LMICs, proportional helpfulness among treated cases was no different between HICs and LMICs. A wide range of predictors of perceived treatment helpfulness were found, some of them consistent across diagnostic categories and others unique to specific disorders. These results provide novel information about patient evaluations of treatment across diagnoses and countries varying in income level, and suggest that a critical issue in improving the quality of care for mental disorders should be fostering persistence in professional help-seeking if earlier treatments are not helpful.

Analysis of the coexistence of gaming and viewing activities in Twitch users and their relationship with pathological gaming: a multilayer perceptron approach

The enormous expansion of the video game sector, driven by the emergence of live video game streaming platforms and the professionalisation of this hobby through e-sports, has spurred interest in research on the relationships with potential adverse effects derived from cumulative use. This study explores the co-occurrence of the consumption and viewing of video games, based on an analysis of the motivations for using these services, the perceived positive uses, and the gamer profile. To that end, a multilayer perceptron artificial neural network is developed and tested on a sample of 970 video game users. The results show that the variables with a significant influence on pathological gaming are the motivation of a sense of belonging to the different platforms, as well as the positive uses relating to making friends and the possibility of making this hobby a profession. Furthermore, the individual effects of each of the variables have been estimated. The results indicate that the social component linked to the positive perception of making new friends and the self-perceived level as a gamer have been identified as possible predictors, when it comes to a clinical assessment of the adverse effects. Conversely, the variables age and following specific streamers are found to play a role in reducing potential negative effects.

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.

Machine Learning-Based Analysis and Prediction of Unplanned 30-Day Readmissions After Pituitary Adenoma Resection: A Multi-Institutional Retrospective Study With External Validation

BACKGROUND

Unplanned readmission after transsphenoidal resection of pituitary adenoma can occur in up to 10% of patients but is unpredictable.

OBJECTIVE

To develop a reliable system for predicting unplanned readmission and create a validated method for stratifying patients by risk.

METHODS

Data sets were retrospectively collected from the National Surgical Quality Improvement Program and 2 tertiary academic medical centers. Eight machine learning classifiers were fit to the National Surgical Quality Improvement Program data, optimized using Bayesian parameter optimization and evaluated on the external data. Permutation analysis identified the relative importance of predictive variables, and a risk stratification system was built using the trained machine learning models.

RESULTS

Readmissions were accurately predicted by several classification models with an area under the receiving operator characteristic curve of 0.76 (95% CI 0.68-0.83) on the external data set. Permutation analysis identified the most important variables for predicting readmission as preoperative sodium level, returning to the operating room, and total operation time. High-risk and medium-risk patients, as identified by the proposed risk stratification system, were more likely to be readmitted than low-risk patients, with relative risks of 12.2 (95% CI 5.9-26.5) and 4.2 (95% CI 2.3-8.7), respectively. Overall risk stratification showed high discriminative capability with a C-statistic of 0.73.

CONCLUSION

In this multi-institutional study with outside validation, unplanned readmissions after pituitary adenoma resection were accurately predicted using machine learning techniques. The features identified in this study and the risk stratification system developed could guide clinical and surgical decision making, reduce healthcare costs, and improve the quality of patient care by better identifying high-risk patients for closer perioperative management.

Identifying individual and environmental predictors of opioid and psychostimulant use among adolescents and young adults following outpatient treatment

BACKGROUND

The United States (US) continues to grapple with a drug overdose crisis. While opioids remain the main driver of overdose deaths, deaths involving psychostimulants such as methamphetamine are increasing with and without opioid involvement. Recent treatment admission data reflect overdose fatality trends suggesting greater psychostimulant use, both alone and in combination with opioids. Adolescents and young adults are particularly vulnerable with generational trends showing that these populations have particularly high relapse rates following treatment.

METHODS

We assessed demographic, psychosocial, psychological comorbidity, and environmental factors (percent below the poverty line, percent unemployed, neighborhood homicide rate, population density) that confer risk for opioid and/or psychostimulant use following substance use disorder treatment using two complementary machine learning approaches-random forest and least absolute shrinkage and selection operator (LASSO) modelling-with latency to opioid and/or psychostimulant as the outcome variable.

RESULTS

Individual level predictors varied by substance use disorder severity, with age, tobacco use, criminal justice involvement, race/ethnicity, and mental health diagnoses emerging at top predictors. Environmental variabels including US region, neighborhood poverty, population, and homicide rate around patients' treatment facility emerged as either protective or risk factors for latency to opioid and/or psychostimulant use.

CONCLUSIONS

Environmental variables emerged as one of the top predictors of latency to use across all levels of substance use disorder severity. Results highlight the need for tailored treatments based on severity, and implicate environmental variables as important factors influencing treatment outcomes.

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.

Predictive modeling of service discontinuation in transitional age youth with recent behavioral health service use

OBJECTIVE

To develop and test predictive models of discontinuation of behavioral health service use within 12 months in transitional age youth with recent behavioral health service use.

DATA SOURCES

Administrative claims for Medicaid beneficiaries aged 15-26 years in Connecticut.

STUDY DESIGN

We compared the performance of a decision tree, random forest, and gradient boosting machine learning algorithms to logistic regression in predicting service discontinuation within 12 months among beneficiaries using behavioral health services.

DATA EXTRACTION

We identified 33,532 transitional age youth with ≥1 claim for a primary behavioral health diagnosis in 2016 and Medicaid enrollment of ≥11 months in 2016 and ≥11 months in 2017.

PRINCIPAL FINDINGS

Classification accuracy for identifying youth who discontinued behavioral health service use was highest for gradient boosting (80%, AUC = 0.86), decision tree (79%, AUC = 0.84), and random forest (79%, AUC = 0.86), as compared with logistic regression (71%, AUC = 0.71).

CONCLUSIONS

Predictive models based on Medicaid claims can assist in identifying transitional age youth who are at risk of discontinuing from behavioral health care within 12 months, thus allowing for proactive assessment and outreach to promote continuity of care for younger persons who have behavioral health needs.

Machine Learning for Predicting Risk of Early Dropout in a Recovery Program for Opioid Use Disorder

Background: An increase in opioid use has led to an opioid crisis during the last decade, leading to declarations of a public health emergency. In response to this call, the Houston Emergency Opioid Engagement System (HEROES) was established and created an emergency access pathway into long-term recovery for individuals with an opioid use disorder. A major contributor to the success of the program is retention of the enrolled individuals in the program. Methods: We have identified an increase in dropout from the program after 90 and 120 days. Based on more than 700 program participants, we developed a machine learning approach to predict the individualized risk for dropping out of the program. Results: Our model achieved sensitivity of 0.81 and specificity of 0.65 for dropout at 90 days and improved the performance to sensitivity of 0.86 and specificity of 0.66 for 120 days. Additionally, we identified individual risk factors for dropout, including previous overdose and relapse and improvement in reported quality of life. Conclusions: Our informatics approach provides insight into an area where programs may allocate additional resources in order to retain high-risk individuals and increase the chances of success in recovery.

Predicting Substance Use Treatment Failure with Transfer Learning

Transfer learning, which involves repurposing a trained model on a related task, may allow for better predictions with substance use data than models that are trained using the target data alone. This approach may also be useful for small clinical datasets. The current study examined a method of classifying substance use treatment success using transfer learning. Transfer learning was used to classify data from a nationwide database. We trained a convolutional neural network on a heroin use treatment dataset, then trained and tested on a smaller opioid use treatment dataset. We compared this model with a baseline model that did not benefit from transfer learning, and a tuned random forest (RF). The goal was to see if model weights transfer across related substances and from large to small datasets. The transfer model outperformed the RF model and baseline model. These findings suggest leveraging the power of large datasets for transfer learning may be an effective approach in predicting substance use disorder (SUD) treatment outcomes. It is possible to achieve a score that performs better than RF using transfer learning.

Characteristics associated with treatment seeking for smoking cessation among heavy-drinking research participants

OBJECTIVE

Treatment seeking for smoking cessation has tremendous clinical implications with the potential to reduce tobacco-related morbidity and mortality. The present study seeks to elucidate clinical variables that distinguish treatment seeking versus non-treatment seeking status for smoking cessation in a large sample of heavy drinking smokers using data-driven methods.

MATERIALS AND METHODS

This secondary data analysis examines n = 911 (n = 267 female) individuals who were daily smokers and heavy drinkers (≥ 7 drinks per week for women, ≥ 14 for men) that were enrolled in either a treatment-seeking study (N = 450) or a non-treatment seeking study (N = 461) using identical pharmacotherapies. Participants completed measures of demographics, alcohol and cigarette use, alcohol craving, the Barratt Impulsiveness Scale (BIS-11), and the Wisconsin Inventory of Smoking Dependence Motives (WISDM-68). These measures were used in a random forest model to identify predictors of treatment seeking status.

RESULTS

The top variables of importance in identifying treatment seeking status were: age, drinks per drinking day, cigarettes per smoking day, BIS-11 cognitive impulsivity, WISDM social environmental goads, WISDM loss of control, WISDM craving, and WISDM tolerance. Age and drinks per drinking day were two of the most robust predictors, followed by measures of nicotine craving and tolerance.

CONCLUSION

Individuals who are daily smokers and consume more drinks per drinking day are less likely to belong to the smoking cessationtreatment-seeking group. Targeting heavy drinking smokers, particularly younger individuals, may be necessary to engage this group in smoking cessation efforts and to reduce the burden of disease of nicotine dependence earlier in the lifespan.

Towards the Development of a Substance Abuse Index (SEI) through Informatics

Substance abuse or drug dependence is a prevalent phenomenon, and is on the rise in United States. Important contributing factors for the prevalence are the addictive nature of certain medicinal/prescriptive drugs, individual dispositions (biological, physiological, and psychological), and other external influences (e.g., pharmaceutical advertising campaigns). However, currently there is no comprehensive computational or machine learning framework that allows systematic studies of substance abuse and its factors with majority of the works using subjective surveys questionnaires and focusing on classification techniques. Lacking standardized methods and/or measures to prescribe medication and to study substance abuse makes it difficult to advance through collective research efforts. Thus, in this paper, we propose to test the feasibility of developing a, objective substance effect index, SEI, that can measure the tendency of an individual towards substance abuse. To that end, we combine the benefits of Electronics Medical Records (EMR) with machine learning technology by defining SEI as a function of EMR data and using logistics regression to obtain a closed form expression for SEI. We conduct various evaluations to validate the proposed model, and the results show that further work towards the development of SEI will not only provide researchers with standard computational measure for substance abuse, but may also allow them to study certain attribute interactions to gain further insights into substance abuse tendencies.

Predicting Success of a Digital Self-Help Intervention for Alcohol and Substance Use With Machine Learning

Background

Digital self-help interventions for reducing the use of alcohol tobacco and other drugs (ATOD) have generally shown positive but small effects in controlling substance use and improving the quality of life of participants. Nonetheless, low adherence rates remain a major drawback of these digital interventions, with mixed results in (prolonged) participation and outcome. To prevent non-adherence, we developed models to predict success in the early stages of an ATOD digital self-help intervention and explore the predictors associated with participant's goal achievement.

Methods

We included previous and current participants from a widely used, evidence-based ATOD intervention from the Netherlands (Jellinek Digital Self-help). Participants were considered successful if they completed all intervention modules and reached their substance use goals (i.e., stop/reduce). Early dropout was defined as finishing only the first module. During model development, participants were split per substance (alcohol, tobacco, cannabis) and features were computed based on the log data of the first 3 days of intervention participation. Machine learning models were trained, validated and tested using a nested k-fold cross-validation strategy.

Results

From the 32,398 participants enrolled in the study, 80% of participants did not complete the first module of the intervention and were excluded from further analysis. From the remaining participants, the percentage of success for each substance was 30% for alcohol, 22% for cannabis and 24% for tobacco. The area under the Receiver Operating Characteristic curve was the highest for the Random Forest model trained on data from the alcohol and tobacco programs (0.71 95%CI 0.69-0.73) and (0.71 95%CI 0.67-0.76), respectively, followed by cannabis (0.67 95%CI 0.59-0.75). Quitting substance use instead of moderation as an intervention goal, initial daily consumption, no substance use on the weekends as a target goal and intervention engagement were strong predictors of success.

Discussion

Using log data from the first 3 days of intervention use, machine learning models showed positive results in identifying successful participants. Our results suggest the models were especially able to identify participants at risk of early dropout. Multiple variables were found to have high predictive value, which can be used to further improve the intervention.

Machine learning prediction of dropping out of outpatients with alcohol use disorders

BACKGROUND

Alcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to continue outpatient treatment, predicting and managing patients who might discontinue treatment becomes necessary. Accordingly, we developed a machine learning (ML) algorithm to predict which the risk of patients dropping out of outpatient treatment schemes.

METHODS

A total of 839 patients were selected out of 2,206 patients admitted for AUD in three hospitals under the Catholic Central Medical Center in Korea. We implemented six ML models-logistic regression, support vector machine, k-nearest neighbor, random forest, neural network, and AdaBoost-and compared the prediction performances thereof.

RESULTS

Among the six models, AdaBoost was selected as the final model for recommended use owing to its area under the receiver operating characteristic curve (AUROC) of 0.72. The four variables affecting the prediction based on feature importance were the length of hospitalization, age, residential area, and diabetes.

CONCLUSION

An ML algorithm was developed herein to predict the risk of patients with AUD in Korea discontinuing outpatient treatment. By testing and validating various machine learning models, we determined the best performing model, AdaBoost, as the final model for recommended use. Using this model, clinicians can manage patients with high risks of discontinuing treatment and establish patient-specific treatment strategies. Therefore, our model can potentially enable patients with AUD to successfully complete their treatments by identifying them before they can drop out.

Maturity of gray matter structures and white matter connectomes, and their relationship with psychiatric symptoms in youth

Brain predicted age difference, or BrainPAD, compares chronological age to an age estimate derived by applying machine learning (ML) to MRI brain data. BrainPAD studies in youth have been relatively limited, often using only a single MRI modality or a single ML algorithm. Here, we use multimodal MRI with a stacked ensemble ML approach that iteratively applies several ML algorithms (AutoML). Eligible participants in the Healthy Brain Network (N = 489) were split into training and test sets. Morphometry estimates, white matter connectomes, or both were entered into AutoML to develop BrainPAD models. The best model was then applied to a held‐out evaluation dataset, and associations with psychometrics were estimated. Models using morphometry and connectomes together had a mean absolute error of 1.18 years, outperforming models using a single MRI modality. Lower BrainPAD values were associated with more symptoms on the CBCL (p_corr = .012) and lower functioning on the Children's Global Assessment Scale (p_corr = .012). Higher BrainPAD values were associated with better performance on the Flanker task (p_corr = .008). Brain age prediction was more accurate using ComBat‐harmonized brain data (MAE = 0.26). Associations with psychometric measures remained consistent after ComBat harmonization, though only the association with CGAS reached statistical significance in the reduced sample. Our findings suggest that BrainPAD scores derived from unharmonized multimodal MRI data using an ensemble ML approach may offer a clinically relevant indicator of psychiatric and cognitive functioning in youth.

AI in patient flow: applications of artificial intelligence to improve patient flow in NHS acute mental health inpatient units

Introduction

Growing demand for mental health services, coupled with funding and resource limitations, creates an opportunity for novel technological solutions including artificial intelligence (AI). This study aims to identify issues in patient flow on mental health units and align them with potential AI solutions, ultimately devising a model for their integration at service level.

Method

Following a narrative literature review and pilot interview, 20 semi-structured interviews were conducted with AI and mental health experts. Thematic analysis was then used to analyse and synthesise gathered data and construct an enhanced model.

Results

Predictive variables for length-of-stay and readmission rate are not consistent in the literature. There are, however, common themes in patient flow issues. An analysis identified several potential areas for AI-enhanced patient flow. Firstly, AI could improve patient flow by streamlining administrative tasks and optimising allocation of resources. Secondly, real-time data analytics systems could support clinician decision-making in triage, discharge, diagnosis and treatment stages. Finally, longer-term, development of solutions such as digital phenotyping could help transform mental health care to a more preventative, personalised model.

Conclusions

Recommendations were formulated for NHS trusts open to adopting AI patient flow enhancements. Although AI offers many promising use-cases, greater collaborative investment and infrastructure are needed to deliver clinically validated improvements. Concerns around data-use, regulation and transparency remain, and hospitals must continue to balance guidelines with stakeholder priorities. Further research is needed to connect existing case studies and develop a framework for their evaluation.

Applications of artificial intelligence to improve patient flow on mental health inpatient units - Narrative literature review

BACKGROUND

Despite a growing body of research into both Artificial intelligence and mental health inpatient flow issues, few studies adequately combine the two. This review summarises findings in the fields of AI in psychiatry and patient flow from the past 5 years, finds links and identifies gaps for future research.

METHODS

The OVID database was used to access Embase and Medline. Top journals such as JAMA, Nature and The Lancet were screened for other relevant studies. Selection bias was limited by strict inclusion and exclusion criteria.

RESEARCH

3,675 papers were identified in March 2020, of which a limited number focused on AI for mental health unit patient flow. After initial screening, 323 were selected and 83 were subsequently analysed. The literature review revealed a wide range of applications with three main themes: diagnosis (33%), prognosis (39%) and treatment (28%). The main themes that emerged from AI in patient flow studies were: readmissions (41%), resource allocation (44%) and limitations (91%). The review extrapolates those solutions and suggests how they could potentially improve patient flow on mental health units, along with challenges and limitations they could face.

CONCLUSION

Research widely addresses potential uses of AI in mental health, with some focused on its applicability in psychiatric inpatients units, however research rarely discusses improvements in patient flow. Studies investigated various uses of AI to improve patient flow across specialities. This review highlights a gap in research and the unique research opportunity it presents.

Identifying factors associated with opioid cessation in a biracial sample using machine learning

Aim

Racial disparities in opioid use disorder (OUD) management exist, however, and there is limited research on factors that influence opioid cessation in different population groups.

Methods

We employed multiple machine learning prediction algorithms least absolute shrinkage and selection operator, random forest, deep neural network, and support vector machine to assess factors associated with ceasing opioid use in a sample of 1,192 African Americans (AAs) and 2,557 individuals of European ancestry (EAs) who met Diagnostic and Statistical Manual of Mental Disorders, 5th Edition criteria for OUD. Values for nearly 4,000 variables reflecting demographics, alcohol and other drug use, general health, non-drug use behaviors, and diagnoses for other psychiatric disorders, were obtained for each participant from the Semi-Structured Assessment for Drug Dependence and Alcoholism, a detailed semi-structured interview.

Results

Support vector machine models performed marginally better on average than other machine learning methods with maximum prediction accuracies of 75.4% in AAs and 79.4% in EAs. Subsequent stepwise regression considered the 83 most highly ranked variables across all methods and models and identified less recent cocaine use (AAs: odds ratio (OR) = 1.82, P = 9.19 × 10^-5; EAs: OR = 1.91, P = 3.30 × 10^-15), shorter duration of opioid use (AAs: OR = 0.55, P = 5.78 × 10^-6; EAs: OR = 0.69, P = 3.01 × 10^-7), and older age (AAs: OR = 2.44, P = 1.41 × 10^-12; EAs: OR = 2.00, P = 5.74 × 10^-9) as the strongest independent predictors of opioid cessation in both AAs and EAs. Attending self-help groups for OUD was also an independent predictor (P < 0.05) in both population groups, while less gambling severity (OR = 0.80, P = 3.32 × 10^-2) was specific to AAs and post-traumatic stress disorder recovery (OR = 1.93, P = 7.88 × 10^-5), recent antisocial behaviors (OR = 0.64, P = 2.69 × 10^-3), and atheism (OR = 1.45, P = 1.34 × 10^-2) were specific to EAs. Factors related to drug use comprised about half of the significant independent predictors in both AAs and EAs, with other predictors related to non-drug use behaviors, psychiatric disorders, overall health, and demographics.

Conclusions

These proof-of-concept findings provide avenues for hypothesis-driven analysis, and will lead to further research on strategies to improve OUD management in EAs and AAs.

Machine-learning prediction of unplanned 30-day rehospitalization using the French hospital medico-administrative database

Predicting unplanned rehospitalizations has traditionally employed logistic regression models. Machine learning (ML) methods have been introduced in health service research and may improve the prediction of health outcomes. The objective of this work was to develop a ML model to predict 30-day all-cause rehospitalizations based on the French hospital medico-administrative database.This was a retrospective cohort study of all discharges in the year 2015 from acute-care inpatient hospitalizations in a tertiary-care university center comprising 4 French hospitals. The study endpoint was unplanned 30-day all-cause rehospitalization. Logistic regression (LR), classification and regression trees (CART), random forest (RF), gradient boosting (GB), and neural networks (NN) were applied to the collected data. The predictive performance of the models was evaluated using the H-measure and the area under the ROC curve (AUC).Our analysis included 118,650 hospitalizations, of which 4127 (3.5%) led to rehospitalizations via emergency departments. The RF model was the most performant model according to the H-measure (0.29) and the AUC (0.79). The performances of the RF, GB and NN models (H-measures ranged from 0.18 to 0. 29, AUC ranged from 0.74 to 0.79) were better than those of the LR model (H-measure = 0.18, AUC = 0.74); all P values <.001. In contrast, LR was superior to CART (H-measure = 0.16, AUC = 0.70), P < .0001.The use of ML may be an alternative to regression models to predict health outcomes. The integration of ML, particularly the RF algorithm, in the prediction of unplanned rehospitalization may help health service providers target patients at high risk of rehospitalizations and propose effective interventions at the hospital level.

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.

Can Hyperparameter Tuning Improve the Performance of a Super Learner?: A Case Study

BACKGROUND

Super learning is an ensemble machine learning approach used increasingly as an alternative to classical prediction techniques. When implementing super learning, however, not tuning the hyperparameters of the algorithms in it may adversely affect the performance of the super learner.

METHODS

In this case study, we used data from a Canadian electronic prescribing system to predict when primary care physicians prescribed antidepressants for indications other than depression. The analysis included 73,576 antidepressant prescriptions and 373 candidate predictors. We derived two super learners: one using tuned hyperparameter values for each machine learning algorithm identified through an iterative grid search procedure and the other using the default values. We compared the performance of the tuned super learner to that of the super learner using default values ("untuned") and a carefully constructed logistic regression model from a previous analysis.

RESULTS

The tuned super learner had a scaled Brier score (R) of 0.322 (95% [confidence interval] CI = 0.267, 0.362). In comparison, the untuned super learner had a scaled Brier score of 0.309 (95% CI = 0.256, 0.353), corresponding to an efficiency loss of 4% (relative efficiency 0.96; 95% CI = 0.93, 0.99). The previously-derived logistic regression model had a scaled Brier score of 0.307 (95% CI = 0.245, 0.360), corresponding to an efficiency loss of 5% relative to the tuned super learner (relative efficiency 0.95; 95% CI = 0.88, 1.01).

CONCLUSIONS

In this case study, hyperparameter tuning produced a super learner that performed slightly better than an untuned super learner. Tuning the hyperparameters of individual algorithms in a super learner may help optimize performance.

Osteoporotic hip fracture prediction from risk factors available in administrative claims data - A machine learning approach

Objective

Hip fractures are among the most frequently occurring fragility fractures in older adults, associated with a loss of quality of life, high mortality, and high use of healthcare resources. The aim was to apply the superlearner method to predict osteoporotic hip fractures using administrative claims data and to compare its performance to established methods.

Methods

We devided claims data of 288,086 individuals aged 65 years and older without care level into a training (80%) and a validation set (20%). Subsequently, we trained a superlearner algorithm that considered both regression and machine learning algorithms (e.g., support vector machines, RUSBoost) on a large set of clinical risk factors. Mean squared error and measures of discrimination and calibration were employed to assess prediction performance.

Results

All algorithms used in the analysis showed similar performance with an AUC ranging from 0.66 to 0.72 in the training and 0.65 to 0.70 in the validation set. Superlearner showed good discrimination in the training set but poorer discrimination and calibration in the validation set.

Conclusions

The superlearner achieved similar predictive performance compared to the individual algorithms included. Nevertheless, in the presence of non-linearity and complex interactions, this method might be a flexible alternative to be considered for risk prediction in large datasets.

Prediction of attempted suicide in men and women with crack-cocaine use disorder in Brazil

Background

Suicide is a severe health problem, with high rates in individuals with addiction. Considering the lack of studies exploring suicide predictors in this population, we aimed to investigate factors associated with attempted suicide in inpatients diagnosed with cocaine use disorder using two analytical approaches.

Methods

This is a cross-sectional study using a secondary database with 247 men and 442 women hospitalized for cocaine use disorder. Clinical assessment included the Addiction Severity Index, the Childhood Trauma Questionnaire, and the Structured Clinical Interview for the Diagnostic and Statistical Manual of Mental Disorders, totalling 58 variables. Descriptive Poisson regression and predictive Random Forest algorithm were used complementarily to estimate prevalence ratios and to build prediction models, respectively. All analyses were stratified by gender.

Results

The prevalence of attempted suicide was 34% for men and 50% for women. In both genders, depression (PR_M = 1.56, PR_W = 1.27) and hallucinations (PR_M = 1.80, PR_W = 1.39) were factors associated with attempted suicide. Other specific factors were found for men and women, such as childhood trauma, aggression, and drug use severity. The men's predictive model had prediction statistics of AUC = 0.68, Acc. = 0.66, Sens. = 0.82, Spec. = 0.50, PPV = 0.47 and NPV = 0.84. This model identified several variables as important predictors, mainly related to drug use severity. The women's model had higher predictive power (AUC = 0.73 and all other statistics were equal to 0.71) and was parsimonious.

Conclusions

Our findings indicate that attempted suicide is associated with depression, hallucinations and childhood trauma in both genders. Also, it suggests that severity of drug use may be a moderator between predictors and suicide among men, while psychiatric issues shown to be more important for women.

Understanding Opioid Use Disorder (OUD) using tree-based classifiers

BACKGROUND

Opioid Use Disorder (OUD), defined as a physical or psychological reliance on opioids, is a public health epidemic. Identifying adults likely to develop OUD can help public health officials in planning effective intervention strategies. The aim of this paper is to develop a machine learning approach to predict adults at risk for OUD and to identify interactions between various characteristics that increase this risk.

METHODS

In this approach, a data set was curated using the responses from the 2016 edition of the National Survey on Drug Use and Health (NSDUH). Using this data set, tree-based classifiers (decision tree and random forest) were trained, while employing downsampling to handle class imbalance. Predictions from the tree-based classifiers were also compared to the results from a logistic regression model. The results from the three classifiers were then interpreted synergistically to highlight individual characteristics and their interplay that pose a risk for OUD.

RESULTS

Random forest predicted adults at risk for OUD with remarkable accuracy, with the average area under the Receiver-Operating-Characteristics curve (AUC) over 0.89, even though the prevalence of OUD was only about 1 %. It showed a slight improvement over logistic regression. Logistic regression identified statistically significant characteristics, while random forest ranked the predictors in order of their contribution to OUD prediction. Early initiation of marijuana (before 18 years) emerged as the dominant predictor. Decision trees revealed that early marijuana initiation especially increased the risk if individuals: (i) were between 18-34 years of age, or (ii) had incomes less than $49,000, or (iii) were of Hispanic and White heritage, or (iv) were on probation, or (v) lived in neighborhoods with easy access to drugs.

CONCLUSIONS

Machine learning can accurately predict adults at risk for OUD, and identify interactions among the factors that pronounce this risk. Curbing early initiation of marijuana may be an effective prevention strategy against opioid addiction, especially in high risk groups.

Treatment resistant opioid use disorder (TROUD): Definition, rationale, and recommendations

The opioid overdose epidemic kills about 130 people a day in the United States and it is estimated that there are about 2.1 million people who suffer from an opioid use disorder (OUD). Academic neuroscientists, psychiatrists and the National Institute of Drug Abuse have spent the last forty-years establishing the foundation of addiction as a brain disorder. It is now clear that extended opioid use causes multiple important and at times, irreversible changes to the brain, especially to its dopamine and opioid systems. With our recognized criteria for diagnosis and the accepted multifaceted treatment approach of both professional psychotherapy and medications that assist treatments, treatment failures should be limited. Unfortunately, this is not the case. Slips, relapses, overdose and multiple failures are all too common. Similar to treatment resistant depression there is a subpopulation who do not respond to standard OUD treatments. However, the field has suggested that if a treatment does not work, it is either the patients fault, they have not hit bottom or simply we need to try the same treatment again. There is a rational to consider this a new category of OUD, treatment resistant opioid use disorder (TROUD). This paper explores past treatment attempts data from OUD patients entering traditional outpatient treatment and makes recommendations how TROUD can be defined. It challenges the addiction research and treatment providers to change its focus from individuals being resistant to the unique conditions associated with this brain disorder as being resistant to treatment as usual.

Analysis of substance use and its outcomes by machine learning I. Childhood evaluation of liability to substance use disorder

BACKGROUND

Substance use disorder (SUD) exacts enormous societal costs in the United States, and it is important to detect high-risk youths for prevention. Machine learning (ML) is the method to find patterns and make prediction from data. We hypothesized that ML identifies the health, psychological, psychiatric, and contextual features to predict SUD, and the identified features predict high-risk individuals to develop SUD.

METHOD

Male (N = 494) and female (N = 206) participants and their informant parents were administered a battery of questionnaires across five waves of assessment conducted at 10-12, 12-14, 16, 19, and 22 years of age. Characteristics most strongly associated with SUD were identified using the random forest (RF)algorithm from approximately 1000 variables measured at each assessment. Next, the complement of features was validated, and the best models were selected for predicting SUD using seven ML algorithms. Lastly, area under the receiver operating characteristic curve (AUROC) evaluated accuracy of detecting individuals who develop SUD+/- up to thirty years of age.

RESULTS

Approximately thirty variables strongly predict SUD. The predictors shift from psychological dysregulation and poor health behavior in late childhood to non-normative socialization in mid to late adolescence. In 10-12-year-old youths, the features predict SUD+/- with 74% accuracy, increasing to 86% at 22 years of age. The RF algorithm optimally detects individuals between 10-22 years of age who develop SUD compared to other ML algorithms.

CONCLUSION

These findings inform the items required for inclusion in instruments to accurately identify high risk youths and young adults requiring SUD prevention.