A Machine-Learning Approach to Predicting Smoking Cessation Treatment Outcomes

Nursing leadership in tobacco dependence treatment to advance health equity: An American Academy of Nursing policy manuscript

BACKGROUND

Tobacco use remains the leading cause of preventable disease, disability, and death in the United States and is a significant cause of health disparities.

PURPOSE

The purpose of this paper is to update the Tobacco Control policy paper published over a decade ago by the American Academy of Nursing's Health Behavior Expert Panel Tobacco Control subcommittee.

METHODS

Members reviewed and synthesized published literature from 2012 to 2024 to identify the current state of the science related to nurse-led tobacco dependence treatment and implications for nursing practice, education, and research.

FINDINGS

The results confirmed that nurse-led tobacco dependence treatment interventions are successful in enhancing cessation outcomes across settings.

DISCUSSION

Recommendations for nursing leaders include: promote tobacco dependence treatment as standard care, accelerate research on implementation of evidence-based treatment guidelines, reduce health disparities by extending access to evidence-based treatment, increase nursing competency in providing tobacco treatment, and drive equity-focused tobacco control policies.

Modelling the nicotine pharmacokinetic profile for e-cigarettes using real time monitoring of consumers' physiological measurements and mouth level exposure

Pharmacokinetic (PK) studies can provide essential information on abuse liability of nicotine and tobacco products but are intrusive and must be conducted in a clinical environment. The objective of the study was to explore whether changes in plasma nicotine levels following use of an e-cigarette can be predicted from real time monitoring of physiological parameters and mouth level exposure (MLE) to nicotine before, during, and after e-cigarette vaping, using wearable devices. Such an approach would allow an -effective pre-screening process, reducing the number of clinical studies, reducing the number of products to be tested and the number of blood draws required in a clinical PK study Establishing such a prediction model might facilitate the longitudinal collection of data on product use and nicotine expression among consumers using nicotine products in their normal environments, thereby reducing the need for intrusive clinical studies while generating PK data related to product use in the real world.An exploratory machine learning model was developed to predict changes in plasma nicotine levels following the use of an e-cigarette; from real time monitoring of physiological parameters and MLE to nicotine before, during, and after e-cigarette vaping. This preliminary study identified key parameters, such as heart rate (HR), heart rate variability (HRV), and physiological stress (PS) that may act as predictors for an individual's plasma nicotine response (PK curve). Relative to baseline measurements (per participant), HR showed a significant increase for nicotine containing e-liquids and was consistent across sessions (intra-participant). Imputing missing values and training the model on all data resulted in 57% improvement from the original'learning' data and achieved a median validation R2 of 0.70.The study is in its exploratory phase, with limitations including a small and non-diverse sample size and reliance on data from a single e-cigarette product. These findings necessitate further research for validation and to enhance the model's generalisability and applicability in real-world settings. This study serves as a foundational step towards developing non-intrusive PK models for nicotine product use.

Individual Predictors of Response to A Behavioral Activation-Based Digital Smoking Cessation Intervention: A Machine Learning Approach

Background: Depression is prevalent among individuals who smoke cigarettes and increases risk for relapse. A previous clinical trial suggests that Goal2Quit, a behavioral activation-based smoking cessation mobile app, effectively increases smoking abstinence and reduces depressive symptoms. Objective: Secondary analyses were conducted on these trial data to identify predictors of success in depression-specific digitalized cessation interventions. Methods: Adult who smoked cigarettes (age = 38.4 ± 10.3, 53% women) were randomized to either use Goal2Quit for 12 weeks (N = 103), paired with a 2-week sample of nicotine replacement therapy (patch and lozenge) or to a Treatment-As-Usual (TAU) control (N = 47). The least absolute shrinkage and selection operator was utilized to identify a subset of baseline variables predicting either smoking or depression intervention outcomes. The retained predictors were then fitted via linear regression models to determine relations to each intervention outcome. Results: Relative to TAU, only individuals who spent significant time using Goal2Quit (56 ± 46 min) were more likely to reduce cigarette use by at least 50% after 12 weeks, whereas those who spent minimal time using Goal2Quit (10 ± 2 min) did not exhibit significant changes. An interaction between educational attainment and treatment group revealed that, as compared to TAU, only app users with an educational degree beyond high school exhibited significant reductions in depression. Conclusions: The findings highlight the importance of tailoring depression-specific digital cessation interventions to individuals' unique engagement needs and educational level. This study provides a potential methodological template for future research aimed at personalizing technology-based treatments for cigarette users with depressive symptoms.

Dietary supplementation with a wild green oat extract (Avena sativa L.) to improve wellness and wellbeing during smoking reduction or cessation: a randomized double-blind controlled study

Objective

Smoking reduction or cessation are critical public health goals, given the well-documented risks of tobacco use to health. Reducing smoking frequency and cessation entirely are challenging due to nicotine addiction and withdrawal symptoms, which can significantly affect mental wellness and overall wellbeing. Previous research has suggested that certain dietary supplements may support smoking cessation and reduction efforts by mitigating these adverse effects. The objective of this study was to assess the effect of supplementation with 900 mg/day of Neuravena®, a green oat extract (GOE) of Avena sativa L., in enhancing wellness and wellbeing during a smoking reduction or cessation experience.

Methods

This was an 8-week randomized, double-blind, placebo-controlled study, ClinicalTrials Identifier: NCT04749017 (https://classic.clinicaltrials.gov/ct2/show/NCT04749017). Participants were assigned to one of the study groups, 72 participants were assigned to GOE and 73 to placebo. The subjects were followed for 8-weeks intervention period as well as an additional 4-week follow-up period. At subsequent visits, they underwent clinical assessments including assessments of quality of life, perceived stress, depression, nicotine dependence, anxiety, cognitive performance, and specific assessments of craving intensity.

Results

GOE was associated with greater improvements in elements of the abbreviated World Health Organization Quality of Life (WHOQOL-BREF) questionnaire as compared with placebo. Similar results were obtained from the SF-36 questionnaire and a visual QoL analogue scale (VAS). Perceived stress levels showed greater decline from baseline among the GOE supplemented participants as compared to placebo. Sleep quality parameters improved with GOE supplementation and worsened in the placebo group. At the end of the intervention period, the percentage of successful reducers (defined as >20% reduction in daily cigarettes) was higher in the GOE group as compared to placebo (66.7% vs. 49.3%, p = 0.034). The improvements from baseline in QoL measures in the GOE group persisted at 4 weeks after termination of the intervention.

Conclusion

GOE supplementation demonstrated greater improvements in quality of life measures, stress and sleep related parameters during a smoking reduction or cessation experience and the product was shown to be safe and well tolerated.

Artificial intelligence in preventive cardiology

Artificial intelligence (AI) is a field of study that strives to replicate aspects of human intelligence into machines. Preventive cardiology, a subspeciality of cardiovascular (CV) medicine, aims to target and mitigate known risk factors for CV disease (CVD). AI's integration into preventive cardiology may introduce novel treatment interventions and AI-centered clinician assistive tools to reduce the risk of CVD. AI's role in nutrition, weight loss, physical activity, sleep hygiene, blood pressure, dyslipidemia, smoking, alcohol, recreational drugs, and mental health has been investigated. AI has immense potential to be used for the screening, detection, and monitoring of the mentioned risk factors. However, the current literature must be supplemented with future clinical trials to evaluate the capabilities of AI interventions for preventive cardiology. This review discusses present examples, potentials, and limitations of AI's role for the primary and secondary prevention of CVD.

Applicability of machine learning algorithm to predict the therapeutic intervention success in Brazilian smokers

Smoking cessation is an important public health policy worldwide. However, as far as we know, there is a lack of screening of variables related to the success of therapeutic intervention (STI) in Brazilian smokers by machine learning (ML) algorithms. To address this gap in the literature, we evaluated the ability of eight ML algorithms to correctly predict the STI in Brazilian smokers who were treated at a smoking cessation program in Brazil between 2006 and 2017. The dataset was composed of 12 variables and the efficacies of the algorithms were measured by accuracy, sensitivity, specificity, positive predictive value (PPV) and area under the receiver operating characteristic curve. We plotted a decision tree flowchart and also measured the odds ratio (OR) between each independent variable and the outcome, and the importance of the variable for the best model based on PPV. The mean global values for the metrics described above were, respectively, 0.675±0.028, 0.803±0.078, 0.485±0.146, 0.705±0.035 and 0.680±0.033. Supporting vector machines performed the best algorithm with a PPV of 0.726±0.031. Smoking cessation drug use was the roof of decision tree with OR of 4.42 and importance of variable of 100.00. Increase in the number of relapses also promoted a positive outcome, while higher consumption of cigarettes resulted in the opposite. In summary, the best model predicted 72.6% of positive outcomes correctly. Smoking cessation drug use and higher number of relapses contributed to quit smoking, while higher consumption of cigarettes showed the opposite effect. There are important strategies to reduce the number of smokers and increase STI by increasing services and drug treatment for smokers.

Latent profiles of regulatory flexibility in alcohol use disorder: Associations with delay discounting and symptoms of depression, anxiety, and stress

BACKGROUND

Regulatory flexibility (RF) involves three distinct components of self-regulation: context sensitivity, repertoire, and feedback responsiveness. Subgroups based on differences in RF have been identified in a general sample and are differentially associated with symptoms of anxiety and depression. However, potential RF profiles have not been examined in individuals with substance use disorders. This study examined RF subtypes in individuals with alcohol use disorder (AUD) and their associations with psychosocial outcomes (i.e., depression, anxiety, and stress) and delay discounting (a core feature of addiction).

METHODS

Individuals (n = 200) with an Alcohol Use Disorders Identification Test score of >16 (mean = 24.12 (±6.92)) were recruited from Amazon Mechanical Turk (mean = 37.26 years old (±11.41); 94 (47%) women). Participants completed the Context Sensitivity Index, the Flexible Regulation of Emotional Expression Scale, and the Coping Flexibility Scale to assess RF. Participants also completed an Adjusting Amount Delay Discounting Task and the Depression, Anxiety, and Stress Scale (DASS-21). Latent profile analyses (LPA) were used to identify patterns in RF deficits. Kruskal-Wallis and Dunn's tests were performed to examine differences in discounting rates and symptoms of depression, anxiety, and stress across RF profiles.

RESULTS

The LPA revealed a 2-profile characterization, including (1) context sensitive regulators (CSR; n = 39) and (2) moderate flexibility regulators (MFR; n = 161). CSR demonstrated significantly lower symptoms of depression (p = 0.004), anxiety (p < 0.001), and stress (p < 0.001) than MFR. CSR also displayed significantly lower AUDIT scores (p = 0.031).

CONCLUSIONS

Findings illustrate that among individuals with moderate-severe AUD, those high in context sensitivity coupled with moderate abilities in repertoire and feedback responsiveness have fewer symptoms of depression, anxiety, and stress. Together, context sensitivity may be an important and protective component of RF among individuals with AUD.

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.

Applicability of machine learning technique in the screening of patients with mild traumatic brain injury

Even though the demand of head computed tomography (CT) in patients with mild traumatic brain injury (TBI) has progressively increased worldwide, only a small number of individuals have intracranial lesions that require neurosurgical intervention. As such, this study aims to evaluate the applicability of a machine learning (ML) technique in the screening of patients with mild TBI in the Regional University Hospital of Maringá, Paraná state, Brazil. This is an observational, descriptive, cross-sectional, and retrospective study using ML technique to develop a protocol that predicts which patients with an initial diagnosis of mild TBI should be recommended for a head CT. Among the tested models, he linear extreme gradient boosting was the best algorithm, with the highest sensitivity (0.70 ± 0.06). Our predictive model can assist in the screening of mild TBI patients, assisting health professionals to manage the resource utilization, and improve the quality and safety of patient care.

Are the Relevant Risk Factors Being Adequately Captured in Empirical Studies of Smoking Initiation? A Machine Learning Analysis Based on the Population Assessment of Tobacco and Health Study

INTRODUCTION

Cigarette smoking continues to pose a threat to public health. Identifying individual risk factors for smoking initiation is essential to further mitigate this epidemic. To the best of our knowledge, no study today has used machine learning (ML) techniques to automatically uncover informative predictors of smoking onset among adults using the Population Assessment of Tobacco and Health (PATH) study.

AIMS AND METHODS

In this work, we employed random forest paired with Recursive Feature Elimination to identify relevant PATH variables that predict smoking initiation among adults who have never smoked at baseline between two consecutive PATH waves. We included all potentially informative baseline variables in wave 1 (wave 4) to predict past 30-day smoking status in wave 2 (wave 5). Using the first and most recent pairs of PATH waves was found sufficient to identify the key risk factors of smoking initiation and test their robustness over time. The eXtreme Gradient Boosting method was employed to test the quality of these selected variables.

RESULTS

As a result, classification models suggested about 60 informative PATH variables among many candidate variables in each baseline wave. With these selected predictors, the resulting models have a high discriminatory power with the area under the specificity-sensitivity curves of around 80%. We examined the chosen variables and discovered important features. Across the considered waves, two factors, (1) BMI, and (2) dental and oral health status, robustly appeared as important predictors of smoking initiation, besides other well-established predictors.

CONCLUSIONS

Our work demonstrates that ML methods are useful to predict smoking initiation with high accuracy, identifying novel smoking initiation predictors, and to enhance our understanding of tobacco use behaviors.

IMPLICATIONS

Understanding individual risk factors for smoking initiation is essential to prevent smoking initiation. With this methodology, a set of the most informative predictors of smoking onset in the PATH data were identified. Besides reconfirming well-known risk factors, the findings suggested additional predictors of smoking initiation that have been overlooked in previous work. More studies that focus on the newly discovered factors (BMI and dental and oral health status,) are needed to confirm their predictive power against the onset of smoking as well as determine the underlying mechanisms.

Machine learning application for predicting smoking cessation among US adults: An analysis of waves 1-3 of the PATH study

Identifying determinants of smoking cessation is critical for developing optimal cessation treatments and interventions. Machine learning (ML) is becoming more prevalent for smoking cessation success prediction in treatment programs. However, only individuals with an intention to quit smoking cigarettes participate in such programs, which limits the generalizability of the results. This study applies data from the Population Assessment of Tobacco and Health (PATH), a United States longitudinal nationally representative survey, to select primary determinants of smoking cessation and to train ML classification models for predicting smoking cessation among the general population. An analytical sample of 9,281 adult current established smokers from the PATH survey wave 1 was used to develop classification models to predict smoking cessation by wave 2. Random forest and gradient boosting machines were applied for variable selection, and the SHapley Additive explanation method was used to show the effect direction of the top-ranked variables. The final model predicted wave 2 smoking cessation for current established smokers in wave 1 with an accuracy of 72% in the test dataset. The validation results showed that a similar model could predict wave 3 smoking cessation of wave 2 smokers with an accuracy of 70%. Our analysis indicated that more past 30 days e-cigarette use at the time of quitting, fewer past 30 days cigarette use before quitting, ages older than 18 at smoking initiation, fewer years of smoking, poly tobacco past 30-days use before quitting, and higher BMI resulted in higher chances of cigarette cessation for adult smokers in the US.

Effects of short-term nicotine deprivation on delay discounting among young, experienced, exclusive ENDS users: An initial study

Delay discounting describes how rapidly delayed rewards lose value as a function of delay and serves as one measure of impulsive decision-making. Nicotine deprivation among combustible cigarette smokers can increase delay discounting. We aimed to explore changes in discounting following nicotine deprivation among electronic nicotine delivery systems (ENDS) users. Thirty young adults (aged 18-24 years) that exclusively used ENDS participated in two laboratory sessions: one with vaping as usual and another after 16 hr of nicotine deprivation (biochemically assessed). At each session, participants completed a craving measure and three hypothetical delay discounting tasks presenting choices between small, immediate rewards and large, delayed ones (money-money; e-liquid-e-liquid; e-liquid-money). Craving for ENDS significantly increased during short-term nicotine deprivation relative to normal vaping. Delay discounting rates in the e-liquid now versus money later task increased (indicating a shift in preference for smaller, immediate rewards) following short-term nicotine deprivation relative to vaping as usual, but no changes were observed in the other two discounting tasks. Short-term nicotine deprivation increased the preference for smaller amounts of e-liquid delivered immediately over larger, monetary awards available after a delay in this first study of its kind. As similar preference shifts for drug now versus money later have been shown to be indicative of increased desire to use drug as well as relapse risk, the findings support the utility of the current model as a platform to explore interventions that can mitigate these preference shifts. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Predictors of smoking cessation outcomes identified by machine learning: A systematic review

This systematic review aims to characterize the utility of machine learning to identify the predictors of smoking cessation outcomes and identify the machine learning methods applied in this area. In the current study, multiple searches occurred through December 9, 2022 in MEDLINE, Science Citation Index, Social Science Citation Index, EMBASE, CINAHL Plus, APA PsycINFO, PubMed, Cochrane Central Register of Controlled Trials, and the IEEE Xplore were performed. Inclusion criteria included various machine learning techniques, studies reporting cigarette smoking cessation outcomes (smoking status and the number of cigarettes), and various experimental designs (e.g., cross-sectional and longitudinal). Predictors of smoking cessation outcomes were assessed, including behavioral markers, biomarkers, and other predictors. Our systematic review identified 12 papers fitting our inclusion criteria. In this review, we identified gaps in knowledge and innovation opportunities for machine learning research in the field of smoking cessation.

The Associations between Remission Status, Discounting Rates, and Recovery from Substance Use Disorders

Background: Recovery from substance use disorders (SUDs) requires sustained and purposeful support to maintain long-term remission. Methods: This study investigated the association between assessment of recovery capital, household chaos, delay discounting (DD) and probability discounting (PD), and remission status among individuals in recovery from SUD. Data from 281 participants from the International Quit & Recovery Registry (IQRR), an ongoing online registry that aims to study the recovery process, were included in the analysis. Results: Lower DD rates and higher recovery capital were found among those in remission compared to those not in remission after controlling for demographics. In contrast, the association of household chaos and PD with remission status were insignificant. Overall, DD accounted for 20% of the total effect between the recovery capital and the remission status. Conclusion: This study contributes to the understanding of recovery as a multidimensional process, supports DD as a behavioral marker of addiction, and suggests areas for future research.

Machine learning applications in tobacco research: a scoping review

OBJECTIVE

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

DATA SOURCES

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

STUDY SELECTION

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

DATA EXTRACTION

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

DATA SYNTHESIS

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

CONCLUSIONS

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

Self-efficacy in predicting smoking cessation: A prospective study in Italy

INTRODUCTION

Predicting the success of smoking cessation might be crucial to guide towards the treatment of smoking dependence in a clinical setting. We analyzed the potential determinants of successful smoking cessation with a specific focus on self-efficacy in predicting quitting smoking.

METHODS

All consecutive smokers (n=478; 224 men and 254 women) attending the Careggi University Hospital Smoking Cessation Service in Florence (Italy) in 2018-2019 provided information on self-efficacy in predicting smoking cessation, using a 1-10 rating scale during their first visit. Patients were followed up for success in quitting smoking at 3, 6 and 12 months, validated through CO exhaled measurement. To evaluate the association between self-efficacy and the probability of success, we estimated multivariable relative risks (RRs) and corresponding 95% confidence intervals (CIs) through log-binomial models for longitudinal data.

RESULTS

Overall, 47.9% of smokers succeeded in their attempt to quit at 3 months, 40.2% at 6 months, and 33.9% at 12 months. Compared to low self-efficacy (rating scale 1-5), the RR of success in quitting smoking was 1.40 (95% CI: 1.06-1.85) for intermediate self-efficacy (scale 6-7) and 1.64 (95% CI: 1.28-2.12) for high self-efficacy (scale 8-10).

CONCLUSIONS

Self-efficacy is an independent determinant of smoking cessation. We recommend to systematically collect self-efficacy, together with other relevant variables, to predict successful smoking cessation. Moreover, strategies to develop and maintain high levels of self-efficacy are essential to increase quit success and improve treatment.

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

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

Transcranial Magnetic Stimulation for Long-Term Smoking Cessation: Preliminary Examination of Delay Discounting as a Therapeutic Target and the Effects of Intensity and Duration

Background

Repetitive transcranial magnetic stimulation (rTMS) is a novel treatment for smoking cessation and delay discounting rate is novel therapeutic target. Research to determine optimal therapeutic targets and dosing parameters for long-term smoking cessation is needed. Due to potential biases and confounds introduced by the COVID-19 pandemic, we report preliminary results from an ongoing study among participants who reached study end prior to the pandemic.

Methods

In a 3 × 2 randomized factorial design, participants (n = 23) received 900 pulses of 20 Hz rTMS to the left dorsolateral prefrontal cortex (PFC) in one of three Durations (8, 12, or 16 days of stimulation) and two Intensities (1 or 2 sessions per day). We examined direction and magnitude of the effect sizes on latency to relapse, 6-month point-prevalence abstinence rates, research burden, and delay discounting rates.

Results

A large effect size was found for Duration and a medium for Intensity for latency to relapse. Increasing Duration increased the odds of abstinence 7–8-fold while increasing Intensity doubled the odds of abstinence. A large effect size was found for Duration, a small for Intensity for delay discounting rate. Increasing Duration and Intensity had a small effect on participant burden.

Conclusion

Findings provide preliminary support for delay discounting as a therapeutic target and for increasing Duration and Intensity to achieve larger effect sizes for long-term smoking cessation and will provide a pre-pandemic comparison for data collected during the pandemic.

Clinical Trial Registration

[www.ClinicalTrials.gov], identifier [NCT03865472].

Delay Discounting in Gambling Disorder: Implications in Treatment Outcome

Impulsive choice, measured by delay discounting (DD) tasks, has been shown in patients with gambling disorders (GD). However, the impact of DD and treatment outcome has been scarcely explored in GD patients. The aims of this study were: (1) to examine the baseline association between DD and clinical variables in GD patients depending on their age and gambling preferences (strategic vs. non-strategic); and (2) to estimate the predictive role of DD on poorer outcomes of cognitive-behavioral therapy (CBT) when considering also the effect of other clinical variables. 133 treatment-seeking male GD patients were evaluated at baseline with a DD task and measures of GD severity, personality traits and psychopathology. Treatment outcome was measured in terms of dropout from CBT and relapses. Results showed baseline associations between DD and GD severity (correlation coefficient R = 0.408 among strategic gamblers and R = 0.279 among mixed gamblers) and between DD and positive/negative urgency (R = 0.330 for the youngest patients, R = 0.244 for middle age, and around R = 0.35 for gamblers who reported preferences for strategic games). Other personality traits such as high harm avoidance and low cooperativeness were also related to DD at baseline (R = 0.606 among strategic gamblers). Regarding treatment outcome, a steeper discount rate predicted a higher risk of relapses in strategic gamblers (odds ratio OR = 3.01) and middle-age ones (OR = 1.59), and a higher risk of dropout in younger gamblers (OR = 1.89), non-strategic gamblers (OR = 1.70) and mixed gamblers (R = 4.74). GD severity mediated the associations between age, DD, personality traits and poor CBT outcome. In conclusion, impulsive choice affects treatment response in individuals with GD and may interfere with it to a significant extent. Considering DD in GD, patients seeking treatment could help control its impact on treatment adherence and relapses.

Examination of social smoking classifications using a machine learning approach

INTRODUCTION

Idiosyncratic definitions of social smoking proliferate in the literature, making cross-study comparison challenging. This project investigated and differentiated four distinct classifications of social smoking using traditional modeling techniques as well as a multilayer perceptron artificial network, a novel machine learning approach suited for heterogeneous, multidimensional data.

METHODS

One hundred thirty-three adults recruited from a college in the Pacific Northwest and from Amazon Mechanical Turk, age 18 to 25 (48% men; 37% women; 8% nonbinary; 73% white; 24% Hispanic or Latinx), completed a set of self-report measures assessing common variables associated with cigarette use. Participants also completed a well-validated audio simulation (Smoking-Simulated Intoxication Digital Elicitation) depicting social smoking contexts and reported their willingness to use cigarettes or alcohol in these contexts.

RESULTS

Across three of the four social smoking definitions, social smokers consistently scored lower on measures of dependence, frequency, quantity, willingness to smoke, and all use motives than nonsocial smokers. The area under the curve for all four models ranged from excellent to outstanding discrimination within the training set. Frequency of days smoked in the past month was the most important predictor for three of the classification models with a relative importance of 100%.

CONCLUSION

The social smoking definitions demonstrated great variability across common cigarette use variables between groups, except for one. The machine learning approach successfully differentiated all four classifications. Recommendations are made for which social smoker classifications to use in subsequent research to maximize appropriate endorsement by the target population.

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

INTRODUCTION

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Loss aversion and risk for cigarette smoking and other substance use

BACKGROUND

Cigarette smoking is among the leading preventable causes of global morbidity and mortality. We aimed to determine whether individual differences in loss aversion, a bias in decision-making wherein losses are valued greater than gains, predicts smoking and other addiction risk.

METHODS

We recruited current daily cigarette smokers (n = 181; > 10 cigarettes per day) and never-smokers (n = 237; < 100 cigarettes lifetime) from the United States using Amazon Mechanical Turk. Groups were matched on gender, educational attainment, and age. All completed items related to current cigarette smoking, alcohol use, other drug use, sleep problems, and depressed mood, and task-based measures of loss aversion and delay discounting, a decision-making bias associated with cigarette smoking.

RESULTS

Smokers were less loss averse than never-smokers (F(1, 411) = 24.19, η² = 0.02, p < .0001) even after accounting for delay discounting (F(1, 410) = 20.53, η² = 0.02, p < .0001). Loss aversion was also a significant independent risk factor for alcohol (F(1, 410) = 21.47, η² = 0.02, p < .0001) and other drug use (F(1, 410) = 54.12, η² = 0.04, p < .0001), although not other behavioral-health conditions (i.e., sleep disturbance, depressed mood). Further analyses revealed that co-occurring low loss aversion and high delay discounting were independently associated with greater risk for all patterns of substance use.

CONCLUSIONS

Loss aversion was associated with current cigarette smoking and other substance use patterns independent of delay discounting. Loss aversion may warrant attention as a protective factor and potential target for preventive intervention for substance use and addiction.

The phenotype of recovery II: The association between delay discounting, self-reported quality of life, and remission status among individuals in recovery from substance use disorders

Quality of life (QOL) and delay discounting (preference for smaller, immediate rewards) are significantly associated with substance use status, severity, and treatment outcomes. Associations between delay discounting and QOL among individuals in recovery from substance use have not been investigated. In this 2-study investigation, using data collected from The International Quit & Recovery Registry, we examined the association between QOL, discounting rates, and remission status among individuals in recovery from SUD. Study 1 (N = 166) investigated the relationship between delay discounting and QOL among individuals in recovery from SUD. Study 2 (N = 282) aimed to validate and extend the results of Study 1 by assessing the association between the remission status, delay discounting, and QOL among individuals in recovery from alcohol use disorder (AUD). In both studies, delay discounting was a significant predictor of QOL domains of physical health, psychological, and environment even after controlling for age, gender, race, ethnicity, education, and days since last use. In Study 2, a mediation analysis using Hayes's methods revealed that the association between the remission status and QOL domains of physical health, psychological and environment were partially mediated by the discounting rates. The current study expands the generality of delay discounting and indicates that discounting rates predict QOL and remission status among individuals in recovery from substance use disorders. This finding corroborates the recent characterizations of delay discounting as a candidate behavioral marker of addiction and may help identify subgroups that require special treatment or unique interventions to overcome their addiction. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

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

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

The Predictive Utility of Valuing the Future for Smoking Cessation: Findings from the ITC 4 Country Surveys

Background: Delay discounting (DD) and time perspective (TP) are conceptually related constructs that are theorized as important determinants of the pursuit of future outcomes over present inclinations. This study explores their predictive relationships for smoking cessation. Methods: 5006 daily smokers at a baseline wave provided 6710 paired observations of quitting activity between two waves. Data are from the International Tobacco Control (ITC) smoking and vaping surveys with samples from the USA, Canada, England, and Australia, across three waves conducted in 2016, 2018 and 2020. Smokers were assessed for TP and DD, plus smoking-specific predictors at one wave of cessation outcomes defined as either making a quit attempt and/or success among those who tried to quit which was ascertained at the subsequent survey wave. Results: TP and DD were essentially uncorrelated. TP predicted making quit attempts, both on its own and controlling for other potential predictors but was negatively associated with quit success. By contrast, DD was not related to making quit attempts, but high DD predicted relapse. The presence of financial stress at baseline resulted in some moderation of effects. Conclusions: Understanding the mechanisms of action of TP and DD can advance our understanding of, and ability to enhance, goal-directed behavioural change. TP appears to contribute to future intention formation, but not necessarily practical thought of how to achieve goals. DD is more likely an index of capacity to effectively generate competing future possibilities in response to immediate gratification.

Covariate adjustment of spirometric and smoking phenotypes: The potential of neural network models

To increase power and minimize bias in statistical analyses, quantitative outcomes are often adjusted for precision and confounding variables using standard regression approaches. The outcome is modeled as a linear function of the precision variables and confounders; however, for many complex phenotypes, the assumptions of the linear regression models are not always met. As an alternative, we used neural networks for the modeling of complex phenotypes and covariate adjustments. We compared the prediction accuracy of the neural network models to that of classical approaches based on linear regression. Using data from the UK Biobank, COPDGene study, and Childhood Asthma Management Program (CAMP), we examined the features of neural networks in this context and compared them with traditional regression approaches for prediction of three outcomes: forced expiratory volume in one second (FEV1), age at smoking cessation, and log transformation of age at smoking cessation (due to age at smoking cessation being right-skewed). We used mean squared error to compare neural network and regression models, and found the models performed similarly unless the observed distribution of the phenotype was skewed, in which case the neural network had smaller mean squared error. Our results suggest neural network models have an advantage over standard regression approaches when the phenotypic distribution is skewed. However, when the distribution is not skewed, the approaches performed similarly. Our findings are relevant to studies that analyze phenotypes that are skewed by nature or where the phenotype of interest is skewed as a result of the ascertainment condition.

Internal Validity of Two Promising Methods of Altering Temporal Orientation among Cigarette Smokers

Relapse to smoking continues to be among the most urgent global health concerns. Novel, accessible, and minimally invasive treatments to aid in smoking cessation are likely to improve the reach and efficacy of smoking cessation treatment. Encouraging prospection by decreasing delay discounting (DD) is a new therapeutic target in the treatment of smoking cessation. Two early-stage interventions, delivered remotely and intended to increase prospection, decrease DD and promote cessation are Episodic Future Thinking (EFT) and Future Thinking Priming (FTP). EFT and FTP have demonstrated at least modest reductions in delay discounting, but understanding whether these interventions are internally valid (i.e., are accomplishing the stated intention) is key. This study examined the internal validity of EFT and FTP. Participants (n = 20) seeking to quit smoking were randomly assigned to active or control conditions of EFT and FTP. Linguistic Inquiry Word Count (LIWC2015) was used to examine the language participants used while engaged in the tasks. Results revealed significant differences in the language participants used in the active and control conditions. Women employed more words than men, but no other demographic differences were found in language. The active conditions for both tasks showed a greater emphasis on future orientation. Risk-avoidance was significantly higher in the active vs. control condition for EFT. Remote delivery of both EFT and FTP was valid and feasible as participants adhered to instructions in the remote prompts, and trends in DD were in the expected directions.

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.

Delayed Reward Discounting as a Prognostic Factor for Smoking Cessation Treatment Outcome: A Systematic Review

INTRODUCTION

While large proportions of smokers attempt to quit, rates of relapse remain high and identification of valid prognostic markers is of high priority. Delayed reward discounting (DRD) is a behavioral economic index of impulsivity that has been associated with smoking cessation, albeit inconsistently. This systematic review sought to synthesize the empirical findings on DRD as a predictor of smoking cessation treatment outcome, to critically appraise the quality of the literature, and to propose directions for future research.

AIMS AND METHODS

A total of 734 articles were identified, yielding k = 14 studies that met the eligibility criteria. The Quality in Prognosis Studies (QUIPS) tool was used to assess methodological quality of the included studies.

RESULTS

Individual study methods were highly heterogeneous, including substantial variation in research design, DRD task, clinical subpopulation, and treatment format. The predominant finding was that steeper DRD (higher impulsivity) was associated with significantly worse smoking cessation outcomes (10/14 studies). Negative results tended to be in pregnant and adolescent subpopulations. The QUIPS results suggested low risk of bias across studies; 11/14 studies were rated as low risk of bias for 5/6 QUIPS domains.

CONCLUSIONS

This review revealed consistent low-bias evidence for impulsive DRD as a negative prognostic predictor of smoking cessation treatment outcome in adults. However, methodological heterogeneity was high, precluding meta-analysis and formal tests of small study bias. The prospects of targeting impulsive DRD as a potentially modifiable risk factor or providing targeted treatment for smokers exhibiting high levels of discounting are discussed.

IMPLICATIONS

These findings indicate consistent evidence for DRD as a negative prognostic factor for smoking cessation outcome in adults. As such, DRD may be a useful as a novel treatment target or for identifying high-risk populations requiring more intensive treatment.

Contingency management for smoking cessation among individuals with substance use disorders: In-treatment and post-treatment effects

INTRODUCTION

Smokers with substance use disorders (SUDs) show elevated tobacco prevalence, and smoking abstinence rates are considerably low. This randomized controlled trial sought to compare the effect of a cognitive behavioral treatment (CBT) that includes an episodic future thinking (EFT) component with the same treatment protocol plus contingency management (CM). This study aims to examine the effect of CM on smoking outcomes and in-treatment behaviors (i.e., retention, session attendance and adherence to nicotine use reduction guidelines), and to analyze whether these in-treatment variables predicted days of continuous abstinence at end-of-treatment.

METHOD

A total of 54 treatment-seeking participants (75.9% males, M = 46.19 years old) were allocated to CBT + EFT (n = 30) or CBT + EFT + CM (n = 24). Intervention consisted of eight weeks of group-based sessions. Tobacco abstinence was verified biochemically by testing levels of carbon monoxide (≤4ppm) and urine cotinine (≤80 ng/ml).

RESULTS

CM intervention increased 24-hour tobacco abstinence (50% vs. 20%, χ²(1) = 5.4; p = .021) and days of continuous abstinence (M = 5.92 ± 7.67 vs. 5.53 ± 12.42; t(52) = -0.132; p = 0.89) at end-of-treatment in comparison with CBT + EFT intervention. Although not statistically significant, CBT + EFT + CM enhanced in-treatment behaviors, in terms of retention (83.3% vs. 70%; χ²(1) = 0.255; p = .208), sessions attended (12.29 ± 3.22 vs. 10.93 ± 3.26; t(52) = -1.527; p = .133) and adherence to weekly nicotine use reduction targets (41.07% ± 31.96 vs. 35% ±2 6.28; t(52) = -0.766; p = .447). A higher percentage of samples meeting reduction guidelines (β = 0.609; p<.001) predicted days of continuous abstinence at end-of-treatment.

CONCLUSION

Combining CM with CBT + EFT improves short-term quitting rates. Findings suggest the need to incorporate strategies for improving adherence to nicotine reduction guidelines.

Are Machine Learning Methods the Future for Smoking Cessation Apps?

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

Modeling motivation for alcohol in humans using traditional and machine learning approaches

Given the significant cost of alcohol use disorder (AUD), identifying risk factors for alcohol seeking represents a research priority. Prominent addiction theories emphasize the role of motivation in the alcohol seeking process, which has largely been studied using preclinical models. In order to bridge the gap between preclinical and clinical studies, this study examined predictors of motivation for alcohol self-administration using a novel paradigm. Heavy drinkers (n = 67) completed an alcohol infusion consisting of an alcohol challenge (target breath alcohol = 60 mg%) and a progressive-ratio alcohol self-administration paradigm (maximum breath alcohol 120 mg%; ratio requirements range = 20-3 139 response). Growth curve modeling was used to predict breath alcohol trajectories during alcohol self-administration. K-means clustering was used to identify motivated (n = 41) and unmotivated (n = 26) self-administration trajectories. The data were analyzed using two approaches: a theory-driven test of a-priori predictors and a data-driven, machine learning model. In both approaches, steeper delay discounting, indicating a preference for smaller, sooner rewards, predicted motivated alcohol seeking. The data-driven approach further identified phasic alcohol craving as a predictor of motivated alcohol self-administration. Additional application of this model to AUD translational science and treatment development appear warranted.

Development of Machine Learning Models for Prediction of Smoking Cessation Outcome

Predictors for success in smoking cessation have been studied, but a prediction model capable of providing a success rate for each patient attempting to quit smoking is still lacking. The aim of this study is to develop prediction models using machine learning algorithms to predict the outcome of smoking cessation. Data was acquired from patients underwent smoking cessation program at one medical center in Northern Taiwan. A total of 4875 enrollments fulfilled our inclusion criteria. Models with artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LoR), k-nearest neighbor (KNN), classification and regression tree (CART), and naïve Bayes (NB) were trained to predict the final smoking status of the patients in a six-month period. Sensitivity, specificity, accuracy, and area under receiver operating characteristic (ROC) curve (AUC or ROC value) were used to determine the performance of the models. We adopted the ANN model which reached a slightly better performance, with a sensitivity of 0.704, a specificity of 0.567, an accuracy of 0.640, and an ROC value of 0.660 (95% confidence interval (CI): 0.617–0.702) for prediction in smoking cessation outcome. A predictive model for smoking cessation was constructed. The model could aid in providing the predicted success rate for all smokers. It also had the potential to achieve personalized and precision medicine for treatment of smoking cessation.

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

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

Digital Health in Cardiac Rehabilitation and Secondary Prevention: A Search for the Ideal Tool

Digital health is becoming more integrated in daily medical practice. In cardiology, patient care is already moving from the hospital to the patients' homes, with large trials showing positive results in the field of telemonitoring via cardiac implantable electronic devices (CIEDs), monitoring of pulmonary artery pressure via implantable devices, telemonitoring via home-based non-invasive sensors, and screening for atrial fibrillation via smartphone and smartwatch technology. Cardiac rehabilitation and secondary prevention are modalities that could greatly benefit from digital health integration, as current compliance and cardiac rehabilitation participation rates are low and optimisation is urgently required. This viewpoint offers a perspective on current use of digital health technologies in cardiac rehabilitation, heart failure and secondary prevention. Important barriers which need to be addressed for implementation in medical practice are discussed. To conclude, a future ideal digital tool and integrated healthcare system are envisioned. To overcome personal, technological, and legal barriers, technological development should happen in dialog with patients and caregivers. Aided by digital technology, a future could be realised in which we are able to offer high-quality, affordable, personalised healthcare in a patient-centred way.

Predicting Response to Group Cognitive Behavioral Therapy in Asthma by a Small Number of Abnormal Resting-State Functional Connections

Group cognitive behavioral therapy (GCBT) is a successful psychotherapy for asthma. However, response varies considerably among individuals, and identifying biomarkers of GCBT has been challenging. Thus, the aim of this study was to predict an individual's potential response by using machine learning algorithms and functional connectivity (FC) and to improve the personalized treatment of GCBT. We use the lasso method to make the feature selection in the functional connections between brain regions, and we utilize t-test method to test the significant difference of these selected features. The feature selections are performed between controls (size = 20) and pre-GCBT patients (size = 20), pre-GCBT patients (size = 10) and post-GCBT patients (size = 10), and post-GCBT patients (size = 10) and controls (size = 10). Depending on these features, support vector classification was used to classify controls and pre- and post-GCBT patients. Pearson correlation analysis was employed to analyze the associations between clinical symptoms and the selected discriminated FCs in post-GCBT patients. At last, linear support vector regression was applied to predict the therapeutic effect of GCBT. After feature selection and significant analysis, five discriminated FC regarding neuroimaging biomarkers of GCBT were discovered, which are also correlated with clinical symptoms. Using these discriminated functional connections, we could accurately classify the patients before and after GCBT (classification accuracy, 80%) and predict the therapeutic effect of GCBT in asthma (predicted accuracy, 67.8%). The findings in this study would provide a novel sight toward GCBT response prediction and further confirm neural underpinnings of asthma. Moreover, our findings had clinical implications for personalized treatment by identifying asthmatic patients who will be appropriate for GCBT.

CLINICAL TRIAL REGISTRATION

The brain mechanisms of group cognitive behavioral therapy to improve the symptoms of asthma (Registration number: Chi-CTR-15007442, http://www.chictr.org.cn/index.aspx).

Machine-learning approaches to substance-abuse research: emerging trends and their implications

PURPOSE OF REVIEW

To provide an accessible overview of some of the most recent trends in the application of machine learning to the field of substance use disorders and their implications for future research and practice.

RECENT FINDINGS

Machine-learning (ML) techniques have recently been applied to substance use disorder (SUD) data for multiple predictive applications including detecting current abuse, assessing future risk and predicting treatment success. These models cover a wide range of machine-learning techniques and data types including physiological measures, longitudinal surveys, treatment outcomes, national surveys, medical records and social media.

SUMMARY

The application of machine-learning models to substance use disorder data shows significant promise, with some use cases and data types showing high predictive accuracy, particularly for models of physiological and behavioral measures for predicting current substance use, portending potential clinical diagnostic applications; however, these results are uneven, with some models performing poorly or at chance, a limitation likely reflecting insufficient data and/or weak validation methods. The field will likely benefit from larger and more multimodal datasets, greater standardization of data recording and rigorous testing protocols as well as greater use of modern deep neural network models applied to multimodal unstructured datasets.

Tobacco Dependence Treatment in Oncology: Initial Patient Clinical Characteristics and Outcomes from Roswell Park Comprehensive Cancer Center

Despite the importance of smoking cessation to cancer care treatment, historically, few cancer centers have provided treatment for tobacco dependence. To address this gap, the National Cancer Institute (NCI) launched the Cancer Center Cessation Initiative (C3i). As part of this effort, this study examined implementation outcomes in a cohort of cancer survivors (CSs) who smoked cigarettes in the first year of an ongoing process to develop and implement a robust Tobacco Treatment Service at Roswell Park Comprehensive Cancer Center. We provide a comprehensive description of the new tobacco use assessment and referral process, and of the characteristics of cancer survivors who agreed to treatment including traditional tobacco-related psychosocial and cancer treatment-related characteristics and novel characteristics such as delay discounting rates. We also examine characteristic differences among those who agreed to treatment between those who attended and those who did not attend treatment. As the new tobacco assessment was implemented, the number of referrals increased dramatically. The mean number of treatment sessions attended was 4.45 (SD = 2.98) and the six-month point prevalence intention to treat abstinence rate among those who attended was 22.7%. However, only 6.4% agreed to treatment and 4% attended at least one treatment session. A large proportion of cancer survivors who agreed to treatment were women, of older age, of lower socioeconomic status (SES), and who had high levels of depressive symptomology. The findings demonstrate that the implementation of system changes can significantly improve the identification of cancer survivors who use tobacco and are referred to tobacco use treatment. Among those who attend, treatment is effective. However, the findings also suggest that a systematic assessment of barriers to engagement is needed and that cancer survivors may benefit from additional treatment tailoring. We present plans to address these implementation challenges. Systematic electronic medical record (EMR)-sourced referral to tobacco treatment is a powerful tool for reaching cancer survivors who smoke, but more research is needed to determine how to enhance engagement and tailor treatment processes.

A Comparative Analysis of Machine Learning Methods for Class Imbalance in a Smoking Cessation Intervention

Smoking is one of the major public health issues, which has a significant impact on premature death. In recent years, numerous decision support systems have been developed to deal with smoking cessation based on machine learning methods. However, the inevitable class imbalance is considered a major challenge in deploying such systems. In this paper, we study an empirical comparison of machine learning techniques to deal with the class imbalance problem in the prediction of smoking cessation intervention among the Korean population. For the class imbalance problem, the objective of this paper is to improve the prediction performance based on the utilization of synthetic oversampling techniques, which we called the synthetic minority over-sampling technique (SMOTE) and an adaptive synthetic (ADASYN). This has been achieved by the experimental design, which comprises three components. First, the selection of the best representative features is performed in two phases: the lasso method and multicollinearity analysis. Second, generate the newly balanced data utilizing SMOTE and ADASYN technique. Third, machine learning classifiers are applied to construct the prediction models among all subjects and each gender. In order to justify the effectiveness of the prediction models, the f-score, type I error, type II error, balanced accuracy and geometric mean indices are used. Comprehensive analysis demonstrates that Gradient Boosting Trees (GBT), Random Forest (RF) and multilayer perceptron neural network (MLP) classifiers achieved the best performances in all subjects and each gender when SMOTE and ADASYN were utilized. The SMOTE with GBT and RF models also provide feature importance scores that enhance the interpretability of the decision-support system. In addition, it is proven that the presented synthetic oversampling techniques with machine learning models outperformed baseline models in smoking cessation prediction.

Identifying smoker subgroups with high versus low smoking cessation attempt probability: A decision tree analysis approach

BACKGROUND

Regression-based research has successfully identified independent predictors of smoking cessation, both its initiation and maintenance. However, it is unclear how these various independent predictors interact with each other and conjointly influence smoking behaviour. As a proof-of-concept, this study used decision tree analysis (DTA) to identify the characteristics of smoker subgroups with high versus low smoking cessation initiation probability based on the conjoint effects of four predictor variables, and determine any variations by socio-economic status (SES).

METHODS

Data come from the Australian arm of the ITC project, a longitudinal cohort study of adult smokers followed up approximately annually. Reported wanting to quit smoking, worries about smoking negative health impact, quitting self-efficacy and quit intentions assessed in 2005 were used as predictors and reported quit attempts at the 2006 follow-up survey were used as the outcome for the initial model calibration and validation analyses (n = 1475), and further cross-validated using the 2012-2013 data (n = 787).

RESULTS

DTA revealed that while all four predictor variables conjointly contributed to the identification of subgroups with high versus low smoking cessation initiation probability, quit intention was the most important predictor common across all SES strata. The relative importance of the other predictors showed differences by SES.

CONCLUSIONS

Modifiable characteristics of smoker subgroups associated with making a quit attempt and any variations by SES can be successfully identified using a decision tree analysis approach, to provide insights as to who might benefit from targeted intervention, thus, underscoring the value of this approach to complement the conventional regression-based approach.

Intertemporal decision-making-related brain states predict adolescent drug abuse intervention responses

Adolescent drug misuse represents a major risk factor for long-term drug use disorders. However, wide individual differences in responses to first-line behavioral therapies targeting adolescent drug misuse limit critical early intervention. Identifying the neural signatures of those adolescents most likely to respond to an intervention would potentially guide personalized strategies for reducing drug misuse. Prior to a 14-week evidence-based intervention involving combinations of contingency management, motivational enhancement, and cognitive behavioral therapy, thirty adolescent alcohol and/or cannabis users underwent fMRI while performing a reward delay discounting (DD) task tapping an addiction-related cognition. Intervention responses were longitudinally characterized by both urinalysis and self-report measures of the percentage of days used during treatment and in post-treatment follow-up. Group independent component analysis (ICA) of task fMRI data identified neural processing networks related to DD task performance. Separate measures of wholesale recruitment during immediate reward choices and within-network functional connectivity among selective networks significantly predicted intervention-related changes in drug misuse frequency. Specifically, heightened pre-intervention engagement of a temporal lobe "reward motivation" network for impulsive choices on the DD task predicted poorer intervention outcomes, while modes of functional connectivity within the reward motivation network, a prospection network, and a posterior insula network demonstrated robust associations with intervention outcomes. Finally, the pre-intervention functional organization of the prospection network also predicted post-intervention drug use behaviors for up to 6 months of follow-up. Multiple functional variations in the neural processing networks supporting preference for immediate and future rewards signal individual differences in readiness to benefit from an effective behavioral therapy for reducing adolescent drug misuse. The implications for efforts to boost therapy responses are discussed.

Reducing impulsive choice: VI. Delay-exposure training reduces aversion to delay-signaling stimuli

Delay-exposure (DE) training consistently and robustly reduces impulsive choice in rats, but the behavioral mechanisms behind this effect are not yet understood. The present study evaluated if DE training works by mitigating aversion to delay-signaling stimuli-those encountered when rats chose the larger-later reward in impulsive choice assessments. Fifty-seven rats were randomly assigned to 120 days of training with delayed reinforcement, training with immediate reinforcement (IE), or to a no-training Control group. Consistent with prior experiments, DE rats made significantly fewer impulsive choices than IE or Control rats. Subsequently, in a separate assessment of delay aversion, rats were given the opportunity to press a lever to temporarily escape from stimuli correlated with long or short time-intervals to food. When these escape opportunities terminated delay-signaling stimuli in the impulsive-choice task, DE rats escaped significantly less than IE and Control rats. When escapes terminated FI-signaling stimuli (a procedure in which there is no response-reinforcer delay), the difference only approached significance. These results support the hypothesis that DE training reduces impulsive choice, in part, by reducing aversion to delay-signaling stimuli. (PsycINFO Database Record (c) 2020 APA, all rights reserved).

Primed for Health: Future Thinking Priming Decreases Delay Discounting

OBJECTIVE

Delay discounting, the propensity to devalue delayed rewards, has robust predictive validity for multiple health behaviors and is a new therapeutic target for health behavior change. Priming can influence behaviors in a predictable manner. We aimed to use the Future Thinking Priming task, administered remotely, to reliably decrease delay discounting rates.

METHODS

In this pre-post randomized control group design, participants completed multiple delay discounting measures at baseline; then, 2 weeks later, they were randomized to Future Thinking Priming or Neutral Priming conditions. We hypothesized that Future Thinking Priming would significantly decrease delay discounting rates accounting for baseline delay discounting rates and time in repeated measures analyses.

RESULTS

Participants randomized to Future Thinking Priming (N = 783) demonstrated significantly lower delay discounting rates post-intervention than those randomized to Neutral Priming (N = 747) on multiple delay discounting measures and magnitudes.

CONCLUSIONS

A single administration of Future Thinking Priming produces statistically reliable reductions in delay discounting rates. The task is brief, can be administered remotely, and is highly scalable. If found to support behavior change, the task might be disseminated broadly to enhance evidence-based behavior change interventions. Future research must determine optimal exposure patterns to support durable health behavior change.

Changing Delay Discounting and Impulsive Choice: Implications for Addictions, Prevention, and Human Health

Delay discounting describes the tendency to devalue delayed consequences or future prospects. The degree to which an individual discounts delayed events appears trait-like in that it is stable over time and across functionally similar situations. Steeply discounting delayed rewards is correlated with most substance-use disorders, the severity of these disorders, rates of relapse to drug use, and a host of other maladaptive decisions impacting human health. Longitudinal data suggest steep delay discounting and high levels of impulsive choice are predictive of subsequent drug taking, which suggests (though does not establish) that reducing delay discounting could have a preventive health-promoting effect. Experimental manipulations that produce momentary or long-lasting reductions in delay discounting or impulsive choice are reviewed, and behavioral mechanisms that may underlie these effects are discussed. Shortcomings of each manipulation technique are discussed and areas for future research are identified. While much work remains, it is clear that impulsive decision-making can be reduced, despite its otherwise trait-like qualities. Such findings invite technique refinement, translational research, and hope.

Applications of machine learning in addiction studies: A systematic review

This study aims to provide a systematic review of the applications of machine learning methods in addiction research. In this study, multiple searches on MEDLINE, Embase and the Cochrane Database of Systematic Reviews were performed. 23 full-text articles were assessed and 17 articles met the inclusion criteria for the final review. The selected studies covered mainly substance addiction (N = 14, 82.4%), including smoking (N = 4), alcohol drinking (N = 3), as well as uses of cocaine (N = 4), opioids (N = 1), and multiple substances (N = 2). Other studies were non-substance addiction (N = 3, 17.6%), including gambling (N = 2) and internet gaming (N = 1). There were eight cross-sectional, seven cohort, one non-randomized controlled, and one crossover trial studies. Majority of the studies employed supervised learning (N = 13), and others employed unsupervised learning (N = 2) and reinforcement learning (N = 2). Among the supervised learning studies, five studies used ensemble learning methods or multiple algorithm comparisons, six used regression, and two used classification. The two included reinforcement learning studies used the direct methods. These results suggest that machine learning methods, particularly supervised learning are increasingly used in addiction psychiatry for informing medical decisions.

The phenotype of recovery III: Delay discounting predicts abstinence self-efficacy among individuals in recovery from substance use disorders

Abstinence self-efficacy (ASE) and delay discounting predict treatment outcomes and risk of relapse. Associations between delay discounting and ASE among individuals in recovery from substance use have not been investigated. Data from 216 individuals in recovery from substance abuse recruited from The International Quit & Recovery Registry, an ongoing online data collection program used to understand addiction and how people succeed in recovery, were included in the analysis. Discounting rates were assessed using an adjusting-delay task, and ASE was assessed using the Relapse Situation Efficacy Questionnaire (RSEQ). Delay discounting was a significant predictor of ASE, even after controlling for age, gender, race, ethnicity, annual income, education level, marital status, and primary addiction. Context-specific factors of relapse included Negative Affect, Positive Affect, Restrictive Situations (to drug use), Idle Time, Social-Food Situations, Low Arousal, and Craving. A principal component analysis of RSEQ factors in the current sample revealed that self-efficacy scores were primarily unidimensional and not situation specific. The current study expands the generality of delay discounting and indicates that discounting rates predict ASE among individuals in recovery from substance use disorders. This finding supports the recent characterizations of delay discounting as a candidate behavioral marker of addiction and may serve as a basis to better identify and target subgroups that need unique or more intensive interventions to address higher risks of relapse and increase their likelihood of abstinence. (PsycINFO Database Record (c) 2019 APA, all rights reserved).