Journal of Behavioral Addictions最新文献

{"title":"SHARP-G-R: A revised tool for assessing the addictive potential of video games.","authors":"Orsolya Király, Mustafa Yildirim, Silvia Garcia-Cabacés, Ádám Gráf, Kata Zsuzsanna Csapó, Sára Perédi, Dana Katz, Patrik Koncz","doi":"10.1556/2006.2025.00339","DOIUrl":"https://doi.org/10.1556/2006.2025.00339","url":null,"abstract":"<p><p>The Saini-Hodgins Addiction Risk Potential of Games (SHARP-G) is a recently developed instrument designed to assess the addictive potential of video games based on their structural characteristics. While the novel instrument is highly valuable, its applicability may pose several challenges. In this work, we introduce the SHARP-G-R, a revised version featuring modifications of selected items and an overall simplification of language to improve clarity and accessibility. This updated iteration enhances the interpretability of the items, removes those with limited empirical support, and introduces new items that capture additional relevant features that may contribute to the addictive potential of games. The commentary outlines all modifications made and provides a detailed rationale for each of them. By refining the instrument, the authors aim to contribute to the discourse on the role of game design in the development and maintenance of gaming-related harms, highlighting the ethical responsibilities of the gaming industry in fostering safer gaming environments.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":""},"PeriodicalIF":6.3,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148368527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic interplay between food addiction, psychological and behavioral factors, and weight-related measures: A longitudinal network analysis in developing youth.","authors":"Dan Wang, Hui Zhou, Xuechun Chen, Qi Long, Yuzheng Hu, Marc N Potenza, Junfen Fu","doi":"10.1556/2006.2025.00141","DOIUrl":"10.1556/2006.2025.00141","url":null,"abstract":"<p><strong>Background and aims: </strong>Food addiction (FA) likely contributes to obesity within a complex system of psychological, behavioral, and physiological factors. However, interactions among these factors remain incompletely understood. This study used a network approach to identify interrelationships among FA, eating motives, lifestyle habits, and weight indicators in a developmental youth cohort.</p><p><strong>Methods: </strong>A longitudinal panel study was conducted in Eastern China. Youth aged >8 years (mean ages 13-14 years) completed survey and anthropometric measurements. The Chinese version of the dimensional Yale Food Addiction Scale for Children 2.0 (dYFAS-C 2.0), Kids Palatable Food Eating Motive Scale (K-PEMS) and Mindful Eating Scale for Children (MEQ-C) were used to measure addictive eating motives and behaviors. Semi-quantitative food intake, physical activity and sleep duration were assessed, and height and weight were measured by trained researchers to calculate a Body Mass Index Z score (BMIZ). Body composition measurement utilized bioelectrical impedance for detecting subcutaneous fat content (FC) and a visceral fat level (VFL). Network analysis, including cross-sectional network estimation at each time point, longitudinal network comparison, and cross-lagged panel network (CLPN) modeling, was used to examine the centrality, connectivity, and temporal relationships among FA and key variables.</p><p><strong>Results: </strong>Among the 2680 participants enrolled, 2054 completed both waves of surveys (retention rate: 76.7%; 49.5% girls). In the baseline (T1) cross-sectional network, FA showed the highest closeness and betweenness and was linked to the weight-related subnetwork (BMIZ, FC, and VFL) primarily through VFL. The follow-up (T2) cross-sectional network showed a broadly similar overall pattern. Longitudinal comparison suggested generally stable centrality patterns across time, with lifestyle-related factors showing relatively greater prominence at T2. In the CLPN, the strongest directional paths primarily extended from FA to later eating motives, whereas direct longitudinal paths from FA to weight indicators were not observed. FA and mindful eating exhibited bidirectional relationships, and mindful eating was also negatively associated with subsequent reward-based eating motives.</p><p><strong>Conclusion: </strong>FA may represent an important intervention target within the broader obesity-related psychobehavioral system in youth, particularly in relation to eating motives and reward-driven eating processes. Interventions that address FA together with mindful eating and modifiable lifestyle factors may offer a more comprehensive approach to youth weight-related health.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"721-734"},"PeriodicalIF":6.3,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371735/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148360875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The good and the bad: A qualitative investigation of students' perspectives on their problematic smartphone use.","authors":"Shuang Su, Janna Cousijn, Reinout W Wiers, Hayley Murray, Tim M Schoenmakers, Helle Larsen","doi":"10.1556/2006.2025.00380","DOIUrl":"10.1556/2006.2025.00380","url":null,"abstract":"<p><strong>Background and aims: </strong>Problematic smartphone use (PSU) features remain debated. This study aimed to identify both parallels and distinctions between PSU and established addiction criteria (DSM-5 and ICD-11), to critically examine the appropriateness of applying these criteria to PSU, and to explore potential etiological factors.</p><p><strong>Methods: </strong>Semi-structured interviews were conducted with 28 university students from 17 European countries who scored above the established cut-off values for problematic smartphone use on the Smartphone Addiction Scale-Short Version (SAS-SV; >31 for males and >33 for females). Thematic analysis was applied to explore patterns of meaning across participants' accounts.</p><p><strong>Results: </strong>Participants reported addiction-like symptoms, including craving, salience and preoccupation, negative consequences, loss of control, coping, and tolerance- and withdrawal-like experiences. In addition, the smartphone's vital roles in daily life, habitual use, and its role as a disruptive distraction were highlighted. A substantial proportion of participants described experiences consistent with multiple DSM-5 or ICD-11 addiction criteria; however, all participants emphasized substantial positive consequences of smartphone use, often outweighing the negative. A central \"trade-off process\" between positive and negative consequences emerged, alongside motives and perceived social norms, as key elements in PSU etiology.</p><p><strong>Discussion and conclusions: </strong>Findings suggest that directly and uncritically applying existing DSM-5 or ICD-11 addiction criteria to PSU warrants careful empirical and conceptual scrutiny. Future research should move beyond existing addiction criteria to also address the dynamic balance between benefits and harms, and the roles of motives and social norms in shaping use patterns.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"684-703"},"PeriodicalIF":6.3,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371772/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148360923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-burden data-driven work addiction screening: Comparing demographic and psychosocial predictors using machine learning.","authors":"Natalia A Woropay-Hordziejewicz, Edyta Charzyńska, Aleksandra Buźniak, Stanisław K Czerwiński, Zuzanna Schneider, Paweł A Atroszko","doi":"10.1556/2006.2026.00060","DOIUrl":"10.1556/2006.2026.00060","url":null,"abstract":"<p><strong>Background and aims: </strong>Identifying employees at risk for work addiction is critical for early intervention, yet systematic screening approaches face practical challenges for organizations. This study compared two screening strategies: a demographic-only model that requires no additional data collection versus a psychosocial model that incorporates job satisfaction and job stress assessments.</p><p><strong>Methods: </strong>We analyzed data from employees across 85 countries or territories. Dataset 1 (psychosocial model, n = 22,136) included demographic, occupational, and psychosocial variables. Dataset 2 (demographic model, n = 23,219) used only readily available information. Work addiction risk was assessed using the International Work Addiction Scale. Five machine learning algorithms (Logistic Regression, Random Forest, XGBoost, Neural Networks, Ensemble Voting) were evaluated on both full and Elastic Net-selected feature sets using cross-validation.</p><p><strong>Results: </strong>The psychosocial model demonstrated superior performance. The best-balanced model (Logistic Regression with Elastic Net selection) achieved balanced accuracy of 0.72 ± 0.01, AUC-ROC of 0.80 ± 0.01, and Youden's J of 0.45 ± 0.02, correctly identifying 72.7% of at-risk individuals while maintaining 72.2% specificity. The demographic model demonstrated moderate performance (Ensemble Voting: balanced accuracy 0.61 ± 0.01, AUC-ROC 0.65 ± 0.01), yet retained practical utility, detecting 57.0% of at-risk cases. High-sensitivity configurations achieved detection rates of 71%, but with elevated false-positive rates, presenting important trade-offs for screening design.</p><p><strong>Discussion and conclusions: </strong>While psychosocial variables provide superior prediction, demographic-only models offer a practical screening alternative that can identify over half of at-risk individuals without an additional data-collection burden. This trade-off between predictive performance and implementation feasibility has important implications for organizational screening programs.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"900-914"},"PeriodicalIF":6.3,"publicationDate":"2026-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371748/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148360891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-scale, circuit-to-gene signature of approach-bias modification in internet gaming disorder.","authors":"Min Wang, Jiejie Fu, Shuang Li, Meiting Wei, Guang-Heng Dong","doi":"10.1556/2006.2025.00434","DOIUrl":"10.1556/2006.2025.00434","url":null,"abstract":"<p><strong>Background: </strong>Approach-bias modification (ApBM) is a cognitive training intervention with potential therapeutic value for internet gaming disorder (IGD). However, its clinical efficacy and the underlying neural mechanisms remain to be systematically investigated. This study aimed to evaluate the effectiveness of ApBM for IGD and to identify the associated multi-scale neurobiological signatures, from brain connectivity to gene expression.</p><p><strong>Methods: </strong>We conducted a randomized controlled trial involving individuals with IGD assigned to either an ApBM (N = 30) or a control group (N = 27). Resting-state functional magnetic resonance imaging data were collected pre- and post-intervention. We applied non-negative matrix factorization and a machine learning framework to identify intervention-related functional connectivity patterns. Imaging-transcriptomic analysis was then used to explore the molecular foundations of the identified neural signature.</p><p><strong>Results: </strong>The ApBM intervention led to a reduction in IGD symptoms and craving. A specific functional connectivity pattern, characterized by anti-connectivity between the visual and ventral attention network (VAN), was identified via machine learning as a potential neural marker of the intervention. This pattern's statistical significance under conservative permutation test was (p = 0.06-0.08). It was spatially coupled to genes enriched in neurodevelopmental and synaptic transmission processes.</p><p><strong>Conclusions: </strong>This study provides multi-scale evidence supporting ApBM as an intervention for IGD. The remodeling between vision and the VAN may reflect a mechanism that interrupts the automatic capture of attention by gaming cues, a process regulated by genes associated with neuroplasticity. We propose a circuit-to-gene framework for understanding ApBM in IGD, though the identified neural signature warrants further independent validation.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"787-797"},"PeriodicalIF":6.3,"publicationDate":"2026-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371734/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148329661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Problematic social media use and cognitive performance in young adults: Associations with selective attention and inhibitory control.","authors":"Conchita Sisí, Ståle Pallesen, M P Fernández-Martín","doi":"10.1556/2006.2025.00576","DOIUrl":"10.1556/2006.2025.00576","url":null,"abstract":"<p><strong>Background and aims: </strong>Problematic social media use (PSMU) has been associated with emotional and behavioral difficulties, yet its relationship with cognitive performance remains insufficiently understood. This study examined whether PSMU is associated with deficits in selective attention and inhibitory control, and whether sex moderates these associations.</p><p><strong>Methods: </strong>A total of 943 Spanish young adults (18-35 years) completed the Bergen Social Media Addiction Scale (BSMAS) and two computerized tasks: the Stroop task, assessing selective attention, and the Simon task, assessing inhibitory control. Correlational and multiple regression analyses examined associations between PSMU severity, cognitive performance, age, and daily social media time of use. Moderation analyses examined sex differences.</p><p><strong>Results: </strong>PSMU showed a positive correlation with Stroop reaction times (r = .65, p < .05), indicating a positive relationship between attentional interference and PSMU scores. However, in regression models, greater daily social media time of use, rather than PSMU severity, was the only significant correlate of slower Stroop performance (β = .28, p < .001). No significant associations were found between PSMU and Simon task performance. A significant Sex × PSMU interaction (β = .14, p = .018) indicated that the association between PSMU and slower Stroop performance was stronger among women than among men.</p><p><strong>Discussion and conclusions: </strong>Selective attention appeared to be more closely associated with daily social media time of use than inhibitory control. Our findings underscore the need to distinguish between problematic use and overall time of use when assessing cognitive correlates.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"672-683"},"PeriodicalIF":6.3,"publicationDate":"2026-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371731/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148329679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neuronal inhibitory mechanisms in overweight/obesity and food/eating addiction: The role of frontal brain coherence, dysregulated eating, and depressive symptoms.","authors":"Roni Aviram-Friedman, Guy Baz, Lior Kafri, Uri Alyagon, Abraham Zangen","doi":"10.1556/2006.2025.00344","DOIUrl":"10.1556/2006.2025.00344","url":null,"abstract":"<p><strong>Background and aims: </strong>Obesity and food/eating addiction are associated with deficits in inhibitory control mechanisms manifested in the lateral prefrontal cortex (LPFC) bilaterally. We explored abnormalities in the functional coherence between the hemispheres and within each of them.</p><p><strong>Methods: </strong>Resting-state electroencephalography (EEG) was utilized to examine intra- and inter-hemispheric frontal brain coherence in individuals with obesity and food/eating addiction (FAOB, n = 27), those with obesity without addiction (Non-FAOB, n = 11), and healthy controls (HC, n = 15). Participants were included in this study following assessment of their BMI and Yale Food Addiction Scale (YFAS) scores. In addition, depressive symptoms were measured with the Beck Depression Inventory (BDI).</p><p><strong>Results: </strong>Individuals with obesity (FAOB and Non-FAOB combined) exhibited higher interhemispheric frontal (IF) and right frontal (RF) coherence compared to healthy controls. Within the obesity group, Non-FAOB participants showed higher IF and RF coherence than the FAOB group. These results remained significant after controlling for BDI scores. Depressive symptoms in the FAOB group were higher than those of the HC group.</p><p><strong>Discussion: </strong>Elevated frontal coherence, both between the frontal hemispheres and within the right frontal hemisphere, may be associated with effortful cognitive control and possibly a compensatory neurocognitive correlate associated with differential susceptibility to developing addictive-like overeating.</p><p><strong>Conclusions: </strong>Frontal brain coherence patterns represent candidate neurophysiological correlates of differential vulnerability to addictive-like overeating in individuals with overweight/obesity and warrant longitudinal investigation to establish their prognostic value.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"915-920"},"PeriodicalIF":6.3,"publicationDate":"2026-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371773/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148329675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From social media to body image distress: Problematic internet use, exercise addiction, and enhancement drugs use across countries.","authors":"Artemisa R Dores, Julius Burkaukas, Agne Stanyte, Aiste Pranckeviciene, Irene P Carvalho, Thomas Zandonai, Pierluigi Simonato, Ilaria De Luca, Alessandro Carollo, Krisztina Edina Ábel, Attila Szabo, Rita Kovácsik, Hironobu Fujiwara, Mami Shibata, Andreea Girleanu, Alejandra Rebeca Melero Ventola, Ricardo M Santos-Labrador, Nelson Bruno de Almeida Cunha, Gabriele Penazzi, Sofia Venturini, Fabio Castro, Lambros Lazuras, Gianluca Esposito, Zsolt Demetrovics, Ornella Corazza","doi":"10.1556/2006.2025.00317","DOIUrl":"10.1556/2006.2025.00317","url":null,"abstract":"<p><strong>Background and aims: </strong>Social media increasingly shapes body image by promoting often unattainable beauty ideals. Concurrently, targeted online marketing of image- and performance-enhancing drugs (IPEDs) exploits these vulnerabilities, intensifying anxiety and fostering maladaptive behaviours such as problematic usage of the internet (PUI), compulsive exercise, and IPEDs consumption. This study explores these behaviours across nine countries and examines how PUI, excessive exercise, and IPEDs use predict appearance anxiety, aiming to inform targeted prevention strategies for at-risk populations.</p><p><strong>Methods: </strong>A total of 3,514 participants from nine countries completed a web-based survey assessing sociodemographic data, appearance anxiety (AAI), problematic internet use (PIUQ-9), excessive exercise (EAI-R), and IPEDs intake.</p><p><strong>Results: </strong>Appearance-related anxiety was observed in 12% of the participants, with the highest prevalence in Mexico (20.7%), Japan (13.8%) and Italy (13.6%). Median PUI scores were highest in Mexico (22.57) and Singapore (21.59). Excessive exercise was reported by 3.6% with no significant country differences. IPEDs use was reported by 28.3% of the sample, with the highest rates in Japan (60.6%). Logistic regression analyses revealed that PUI, excessive exercise and IPEDs use were significant predictors of appearance-related anxiety.</p><p><strong>Discussion and conclusions: </strong>The strong associations between PUI, excessive exercise, IPEDs use, and appearance anxiety underscore the complex interplay between online exposure, body image concerns and mental health. Cross-country differences suggest that socio-cultural factors influence appearance-related anxiety. These findings highlight the need for culturally sensitive interventions and policy measures that address the impact of digital media on body image, particularly to protect vulnerable populations.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"704-720"},"PeriodicalIF":6.3,"publicationDate":"2026-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148239348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Problematic internet use and borderline personality features: A systematic review informed by the alternative model of personality disorders.","authors":"Eve Chesivoir, Elizabeth Hernandez, Sara Dolan","doi":"10.1556/2006.2025.00590","DOIUrl":"10.1556/2006.2025.00590","url":null,"abstract":"<p><strong>Background and aims: </strong>Associations between problematic internet use (PIU) and borderline personality disorder (BPD) have been reported, but the literature is highly heterogeneous, with some studies assessing overall BPD severity and others examining individual traits (e.g., emotional lability, impulsivity, dissociation). This review synthesizes these approaches using the Alternative Model of Personality Disorders (AMPD), examining how BPD-relevant pathological personality traits (Criterion B) and impairments in self and interpersonal functioning (Criterion A) relate to PIU.</p><p><strong>Methods: </strong>Following PRISMA 2020 guidelines, we searched PsycINFO, Web of Science, PubMed, Embase, and Scopus for studies examining associations between PIU (e.g., general use, social media, gaming, smartphone use) and personality traits or functioning in adults. Study quality was assessed using the NIH Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies.</p><p><strong>Results: </strong>Thirty studies (N = 21,358) met inclusion criteria. Emotional lability and impulsivity showed the most consistent associations with PIU across outcome types. Few studies examined impairments in personality functioning, but available evidence suggests that identity disturbance may predict PIU over time and that interpersonal dysfunction is associated with greater use of online environments for reassurance and emotion regulation. Associations involving dissociation and detachment were relatively weak and less consistent.</p><p><strong>Discussion and conclusions: </strong>Studies varied widely in design, measures, and theoretical approach, limiting direct comparison across studies. Despite this heterogeneity, findings indicate that emotional lability, impulsivity, and identity disturbance appear to represent transdiagnostic vulnerabilities that increase risk for PIU and shape patterns of online engagement.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":"597-621"},"PeriodicalIF":6.3,"publicationDate":"2026-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371729/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148175906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting problem gambling among online sports and race bettors: Assessing the value of machine learning using behavioural and self-reported data.","authors":"Robert M Heirene, Eden Zhang, Darya Vanichkina, Charles T de Leau, Eunice L Y Huynh, Sally M Gainsbury","doi":"10.1556/2006.2025.00525","DOIUrl":"10.1556/2006.2025.00525","url":null,"abstract":"<p><strong>Background and aims: </strong>Online gambling operators collect detailed behavioural data that can identify customers at risk of harmful gambling. However, there is limited clarity on how to optimally achieve this in practice, including which variables are most useful and whether short-term data windows are sufficient for risk detection. These details are increasingly important as regulatory frameworks emphasise timely intervention. We examined the value of machine learning in this context by comparing models trained on 30 days versus six months of behavioural data and exploring whether incorporating survey responses enhanced performance.</p><p><strong>Methods: </strong>Customers from two Australian sports and race betting sites (N = 1,470) completed a survey including the Problem Gambling Severity Index (PGSI) and measures of employment, income, gambling satisfaction, and number of gambling accounts. We built machine learning models to classify participants into risk groups (PGSI 1-7 [no-to-moderate-risk] vs. PGSI≥8 [high-risk]), comparing performance across data windows (30 days vs. six months), and with or without survey variables.</p><p><strong>Results: </strong>Models using only behavioural data achieved adequate classification accuracy (AUROC = 0.74-0.75), with similar performance across 30-day and six-month windows. The most predictive account-based variables were age, deposits per active day, average stake, and days since betting. Combining behavioural data with self-reported variables enhanced performance (AUROC = 0.76-0.85). Two self-reported variables-number of gambling accounts held and gambling satisfaction-were primarily responsible for these improvements.</p><p><strong>Conclusions: </strong>Machine learning models can detect at-risk customers on online sports and race betting sites using only 30 days of behavioural data. Performance can be improved by adding minimal, non-intrusive self-report measures.</p>","PeriodicalId":15049,"journal":{"name":"Journal of Behavioral Addictions","volume":" ","pages":""},"PeriodicalIF":6.3,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13371738/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148156757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}