Prevention Science最新文献

{"title":"A Guide to Constructing Indigenous Statistical Spaces for Prevention Science Research.","authors":"Valentín Quiroz de la Sierra","doi":"10.1007/s11121-026-01911-5","DOIUrl":"10.1007/s11121-026-01911-5","url":null,"abstract":"<p><p>Artificial intelligence (AI)-powered computational methods, such as machine learning and natural language processing, are increasingly applied in deaths of despair research among Indigenous populations. However, their application in Indigenous contexts is often constrained by epistemological misalignment, technical limitations, and ethical concerns. Integrating Indigenous Research Methodologies into AI-powered prevention science research is necessary to support Indigenous Data Sovereignty and address deaths of despair. The Indigenous Computational Approach (ICA) provides a structured reflexive protocol for constructing Indigenous Statistical Spaces that operationalize Indigenous Research Methodologies within computational workflows. ICA aligns four interdependent components: Researcher Standpoint, Indigenous Theoretical Frameworks, AI Data Analysis Technique, and Dissemination and Indigenous Governance. This protocol is supported by operational steps and an accompanying ICA Checklist. A previously published case study on the Indigenous Wholistic Factors Project illustrates the ICA in practice in the context of suicide risk modeling. The case study applied a lasso logistic regression model to structure feature selection on an Indigenous subsample of the 2019-2020 California Healthy Kids Survey (n = 2609). Ten of 17 candidate features were retained, and the model demonstrated strong discrimination (AUC = 0.87) and acceptable calibration (Brier score = 0.10). The ICA does not guarantee different empirical findings or superior model accuracy, but rather it restructures how AI models are designed, validated, and deployed for prevention science research. The ICA provides a replicable protocol for AI-powered prevention science research to support Indigenous self-determination and community-defined well-being.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting Patterns of Intimate Partner Violence Using Qualitative Analyses and Machine Learning Algorithms.","authors":"Ying Zhang, Jun Fang, Ambika Krishnakumar","doi":"10.1007/s11121-026-01923-1","DOIUrl":"https://doi.org/10.1007/s11121-026-01923-1","url":null,"abstract":"<p><p>Intimate partner violence (IPV) survivors increasingly use social media platforms to share their experiences and to seek help and support for their IPV-related concerns. IPV evidence extracted from social media platforms can provide valuable information and complement data obtained from conventional data sources (e.g., self-reports and interviews) thereby enhancing our understanding of IPV victimization. This study addressed three research questions: (1) What range of IPV behaviors emerge through qualitative coding? (2) To what extent do machine learning (ML) based text classifications yield results comparable to qualitative coding of IPV behaviors? and (3) Do the conceptualizations that emerge from unsupervised ML capture additional behaviors or contextual information not identified through qualitative analyses? We analyzed 400 posts from women on IPV-related online forums using qualitative content analysis and two ML approaches: supervised text classification and unsupervised topic modeling (Latent Dirichlet Allocation). Supervised learning approaches, notably Random Forest and Neural Networks, proved effective in classifying IPV violence subtypes with high accuracy (F1 scores .62 - .85). A comparison of findings from the qualitative and topic modeling approaches supported the presence of distinct characteristics of IPV: physical and sexual violence, psychological/emotional abuse, and coercive control. The ML model revealed vocabulary patterns consistent with relational and child-related contexts, temporal and frequency indicators of violence, references to legal system engagement, and spatial contexts, elements that were less captured through thematic qualitative coding alone. The consistency of findings across qualitative and ML approaches points to the potential of leveraging ML techniques when analyzing qualitative data, thus enabling the development of timely and effective IPV interventions.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Use of Machine Learning to Predict Offline Adolescent e-Cigarette Use: a Proof-of-Concept.","authors":"Julie V Cristello, Krzysztof Bogusz, Elisa M Trucco","doi":"10.1007/s11121-026-01922-2","DOIUrl":"https://doi.org/10.1007/s11121-026-01922-2","url":null,"abstract":"<p><p>Identification of adolescent e-cigarette use could inform prevention and intervention programming and reduce associated consequences. One way to predict those engaging in use is by examining social media profiles and metrics. Most studies examining substance use content on social media employ self-report or human coding that have methodological limitations. Thus, the current study developed a supervised machine learning algorithm to classify participants into e-cigarette use categories based on Instagram metrics. Participants (n = 67, M_age = 18.27; 64.2% female, 82.1% Hispanic/Latino[a/x], 91% White) in the study provided their Instagram data downloaded through the app. Instagram metrics (i.e., number of followers, number following, number of liked comments, number of liked posts, number of posts, and number of messages) were extracted and included as input features in the model. Adolescents reported their e-cigarette use on a self-report measure. A classification tree method was used to classify participants as engaging in e-cigarette use or not. Data was partitioned into a training and test set using stratified sampling. All analyses were performed in Python. Three input features (number of followers, number of liked posts, and number of messages) were selected through hyperparameter-optimized feature selection. The final model accurately detected e-cigarette use 71% of the time. Findings indicate that supervised learning can predict adolescent e-cigarette use with accuracy consistent with other clinical populations. This study establishes that universal aspects of social media may be harbingers for policy makers and tech companies to provide targeted support and messaging.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of the ADAPT Military Parenting Program on Parenting Behaviors in a Subsample of Deployed Mothers.","authors":"Cheuk H Cheng, Susanne S Lee, Abigail H Gewirtz","doi":"10.1007/s11121-026-01927-x","DOIUrl":"https://doi.org/10.1007/s11121-026-01927-x","url":null,"abstract":"<p><p>The current study examined the effects of the After Deployment, Adaptive Parenting Tools (ADAPT program), a parenting program for military families, in a subsample of deployed mothers from a larger randomized control trial. Multiple regression was used to examine both observed and self-reported parenting outcomes between intervention and control groups at 1-year follow-up. Drawn from a randomized controlled trial with 336 military families with 5-12-year-old children, the current sample included 56 deployed mothers (Mean age = 34.57 years old; 64.3% were married; 87.5% Caucasians). Results indicated that deployed mothers showed improvement in observed positive parenting (β = .31, p = .01, SE = .32, d = .55) but no significant improvement in overall observed parenting, (β = .24, p = .08, SE = .13, d = .43), no significant reductions in observed harsh discipline (β = .19, p = .18, SE = .14, d = .08) and no significant increases in self-report of parental locus of control (β =  - .05, p = .49, SE = .08, d = .25). These findings present the first evidence for the effectiveness of a parenting program for deployed mothers with school-aged children. Improvements in positive parenting are consistent with prior findings from the GenPMTO intervention framework. The lack of intervention effects on harsh discipline suggests that future interventions should consider the cultural meanings and functions of discipline within military contexts and how they may spill over into the home.  CLINICAL TRIAL REGISTRATION: This study was registered at ClinicalTrials.gov, study NCT03522610 on 02/16/2018.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Mixed-Methods Study of Policymakers' Adoption of AI to Support Use of Research Evidence: Implications for Artificial Intelligence in Prevention Policy.","authors":"D Max Crowley, Jonathan Wright, Alex Winters, Damon Jones, Jessica Pugel, Patrick O'Neill, Bethany Shaw, Sarah Hamel, Elizabeth Long, Michael Donovan, Taylor Scott","doi":"10.1007/s11121-026-01925-z","DOIUrl":"https://doi.org/10.1007/s11121-026-01925-z","url":null,"abstract":"<p><p>Policymakers are increasingly adopting artificial intelligence (AI) tools to support legislative decision-making, yet there is limited empirical understanding of how these technologies are used and the implications for evidence-based policymaking. General-purpose AI tools, such as large language models (LLMs), present both opportunities for improved efficiency and risks related to misinformation and lack of transparency. This study examines state legislators' use of AI in policymaking and introduces the AIRE Protocol (AI for Informed and Responsible Evidence-use), a structured framework for developing specialized AI tools grounded in validated evidence. We demonstrate the application of the AIRE Protocol through the development of the Results First AI Assistant, designed to enhance policymakers' access to the Results First Clearinghouse. A mixed-methods approach was used. Forty-five US state legislators participated in live interviews to assess AI adoption patterns, perceived benefits, and concerns. The AIRE Protocol guided the rapid prototyping and iterative development of the AI assistant, with input from policymakers, national policy organizations, and technical experts, resulting in tailored evidence based recommendations. While policymakers expressed interest in AI tools for improving access to information under time constraints, they also raised concerns regarding transparency, reliability, and appropriate use. Our findings suggest that AI tools tailored to policymakers' needs-developed using frameworks like AIRE-will facilitate the integration of validated evidence into legislative decision-making while addressing ethical and practical concerns associated with generalized AI solutions.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Measuring Exposure to Gun Violence and Risky Behavior: Psychometric Validation and Analysis of the Gun Violence Exposure (Gun-X) Scale.","authors":"Kimberly J Mitchell, Victoria Banyard, Patrick J Guziewicz, Bruce G Taylor","doi":"10.1007/s11121-026-01916-0","DOIUrl":"https://doi.org/10.1007/s11121-026-01916-0","url":null,"abstract":"<p><p>Gun violence is a critical public health problem in the United States, requiring improved strategies for early identification and prevention. This study introduces and validates the Gun Violence Exposure (Gun-X) Scale, designed to assess awareness of gun violence, threats, and risky firearm behaviors within social networks, including in-person and digital contexts. Data were drawn from a nationally representative sample of 5,311 youth and young adults (ages 10-34) and collected from September 2023 to January 2024. Using a multi-method psychometric approach, findings supported a unidimensional structure with good reliability and consistent model fit across training and validation samples. Item Response Theory analyses indicated high discrimination across items and strongest measurement precision at moderate levels of exposure. Convergent validity was supported through associations with violence exposure, peer gun carrying, and neighborhood risk, while discriminant validity was demonstrated with mental health and social support measures. The 10-item Gun-X Scale provides a reliable and generalizable measure of bystander exposure to gun violence. It has applications in research, clinical screening, and prevention efforts, particularly for characterizing exposure patterns and informing tailored, context-sensitive responses. The scale is intended to assess exposure and should not be used as a standalone tool for selecting individuals for intervention roles.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Role of an Intermediary Organization and State Government Partnership to Advance Practice and Policy in Children's Behavioral Health.","authors":"Jason M Lang, Kellie Randall, Aleece Kelly, Jeana Bracey, Jenny Bridges-Hightower, Katie Newkirk, Jack Lu, Francis Gregory, Tracy Duran, Catherine Foley Geib, Stephanie Bozak, Jocelyn Mackey, Jeffrey J Vanderploeg","doi":"10.1007/s11121-026-01926-y","DOIUrl":"https://doi.org/10.1007/s11121-026-01926-y","url":null,"abstract":"<p><p>Policymakers navigating an increasingly complex and evolving landscape can benefit from establishing intersectoral partnerships with researchers, providers, schools, family advocates, and other stakeholders in children's behavioral health. Intermediary organizations, which serve as neutral conveners to bridge cross-system improvements to systems, policy, and practice, are relatively new but are increasing in number and offer an efficient way to support government with strengthening partnerships and systems. We describe an evolving 25-year-long partnership between an independent non-profit intermediary organization, the Child Health and Development Institute (CHDI), and state government that has contributed to systems, policy, and practice improvements as well as research on children's behavioral health. Key components of the partnership include the number and diversity of partners, ongoing involvement of family members with lived experience, use of research and data to inform policy and system development, translational communication of research for policymakers, and the agility, efficiency, and strength as a convener of an independent intermediary organization. Case examples of the partnership's efforts to improve practice, policy, and research through dissemination of evidence-based practices, development of a statewide children's behavioral health plan, implementation of a school-based diversion model, and creation of a strategic plan for the behavioral health workforce are provided. Recommendations are made for states to develop and strengthen partnerships to improve the integration of research, policy, and system development.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Run It Up Intervention: Addressing the Effects of Structural Determinants on Adolescent Identity, Beliefs, and Involvement in Firearm Violence-Formative Research and Intervention Development.","authors":"Mark C Edberg, W Douglas Evans, Yan Wang, Elizabeth L Andrade, Nisha Sachdev, Michael W Long, Leslie Manso, Madelene Sciortino, Michael Wallace, Julia Tutt, Victor Battle, Kenneth Rioland, Dolores Bryant, Amy Mack","doi":"10.1007/s11121-026-01910-6","DOIUrl":"https://doi.org/10.1007/s11121-026-01910-6","url":null,"abstract":"<p><p>Firearm violence in Washington, DC, rose from 2020 to 2022, especially in neighborhoods most affected by long-term socioeconomic marginalization as discussed by Josephson (2022). The Run It Up project is a research-based effort to reduce the role of community structural factors in prioritizing adolescent beliefs about potential life trajectories (\"possible selves\") that foreground violence. The project is a partnership between the George Washington University Milken Institute School of Public Health and the Washington Highlands community in DC. This paper presents results of formative research, including 10 adolescent focus groups (n = 80) and 17 key informant interviews conducted over 12 months, to inform intervention development. The resulting intervention seeks to change the calculation of possible selves for adolescents by implementing desirable, tangible trajectories that do not involve violence or pro-violence norms, and in turn reduce youth involvement in firearm violence. These alternative trajectories are implemented through community-based training/mentoring in six career pathways (tracks) that offer attributes and gains meaningful to youth (from the formative research). The intervention includes an intervention branding campaign implemented primarily through social media featuring narratives about the tracks and their attributes. Run It Up is being evaluated using a quasi-experimental design with baseline and follow-up surveys in the intervention and comparison communities. The purpose of the research project is to determine whether and how a university-community partnership can develop and promote alternative life trajectories for youth in communities with high levels of violence, and whether these alternatives increase youth resilience and decrease involvement in violence.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785346","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How Adherence to an Evidence-Based Targeted Intervention Procedure is Related to Intervention Effectiveness?","authors":"Eerika Johander, Lydia Laninga-Wijnen, Daniel Graf, Daniela V Chávez, Christina Salmivalli","doi":"10.1007/s11121-026-01917-z","DOIUrl":"https://doi.org/10.1007/s11121-026-01917-z","url":null,"abstract":"<p><p>Research suggests that although teachers' targeted interventions can stop bullying, they still fail in about one-fourth of cases. Yet, most studies to date have not considered how targeted interventions were implemented, leaving open the possibility that improper implementation contributed to these failures. To address this gap, we examined the extent to which school personnel implementing the KiVa® antibullying program in Finland adhered to the program-recommended targeted intervention procedure when addressing bullying cases, and whether modifications to the procedure, influenced intervention effectiveness. We further tested the specific effects of two types of modifications - adaptations and omissions - on effectiveness. Data were collected using ecological momentary assessment, with school personnel documenting in a mobile application the steps they took when addressing bullying cases. The sample included 341 cases involving 396 victimized students (53% female, Mage = 12.39 SD = 2.08) and 733 bullying students (13% female, Mage = 12.52 SD = 1.96) from 22 primary and secondary schools. The results indicated that adherence to procedure varied considerably across intervention steps, and adherence to the full procedure was low. Interventions were, however, more effective when school personnel adhered to the procedure than when they made modifications. Moreover, interventions were least effective, when steps were omitted, whereas adaptations did not significantly reduce effectiveness compared to full adherence, though the trend was in the same direction as with omissions. These findings suggest that closer adherence to evidence-based procedures tends to lead to better outcomes in targeted bullying interventions.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147786055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging State-Level Partnerships to Scale-Up Positive Behavioral Interventions and Supports in U.S. Schools.","authors":"Angus Kittelman, Timothy J Lewis, Steve Goodman, Lisa Powers","doi":"10.1007/s11121-026-01915-1","DOIUrl":"https://doi.org/10.1007/s11121-026-01915-1","url":null,"abstract":"<p><p>Positive Behavioral Interventions and Supports (PBIS) is widely implemented in districts and schools across the United States. State leadership teams play critical roles in facilitating the successful scale up of PBIS in partnership with the National Technical Assistance Center on PBIS. The purpose of this paper is to highlight exemplary partnerships between state leadership teams and the Center on PBIS that have resulted in meaningful and socially significant improvements in school and student outcomes. In addition, given the current climate and shifting federal priorities, we also offer recommendations for state leadership teams focused on continuing to scale and sustain PBIS in schools. These recommendations come from structured interviews with 12 state leadership team members as well as our collective experience supporting state leadership teams for over 25 years.</p>","PeriodicalId":48268,"journal":{"name":"Prevention Science","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2026-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147730425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}