ARAna Radovic

Ana Radovic

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ana Radovic has a total of 87 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Brief Report: Mental Health Literacy Among a Sample of Black Adolescents

    by Dashawna J. Fussell-Ware, Heather A. Jones, Jasmin Perrier, Jaime M. Booth, Ana Radovic, Christina E. Newhill, James P. Huguley

  • Open Access

    Provider Perspectives on Implementing an Enhanced Digital Screening for Adolescent Depression and Suicidality: Qualitative Study

    by Morgan A Coren, Oliver Lindhiem, Abby R Angus, Emma K Toevs, Ana Radovic

    Background: With a growing adolescent mental health crisis, pediatric societies are increasingly recommending that primary care providers (PCPs) engage in mental health screening. While symptom-level screens identify symptoms, novel technology interventions can assist PCPs with providing additional point-of-care guidance to increase uptake for behavioral health services. Objective: In this study, we sought community PCP feedback on a web-based, digitally enhanced mental health screening tool for adolescents in primary care previously only evaluated in research studies to inform implementation in community settings. Methods: A total of 10 adolescent providers were recruited to trial the new screening tool and participate in structured interviews based on the Consolidated Framework for Implementation Research domains. Interviews were audio recorded, transcribed, and coded according to a prespecified codebook using a template analysis approach. Results: Providers identified improving mental health screening and treatment in pediatric primary care as a priority and agreed that a web-based digitally enhanced screening tool could help facilitate identification of and management of adolescent depression. Salient barriers identified were lack of electronic health record integration, time to administer screening, implications on clinic workflow, accessibility, and lack of transparency within health care organizations about the process of approving new technologies for clinical use. Providers made multiple suggestions to enhance implementation in community settings, such as incorporating customization options. Conclusions: Technology interventions can help address the need for improved behavioral health support in primary care settings. However, numerous barriers exist, complicating implementation of new technologies in real-world settings.


  • Open Access

    A Mixed Method Investigation of Parent-Adolescent Communication About Mental Health

    by Sophie Wecht, Morgann Hendrixson, Ana Radović


  • Open Access

    Framework for Ranking Machine Learning Predictions of Limited, Multimodal, and Longitudinal Behavioral Passive Sensing Data: Combining User-Agnostic and Personalized Modeling

    by Tahsin Mullick, Sam Shaaban, Ana Radovic, Afsaneh Doryab

    Background: Passive mobile sensing provides opportunities for measuring and monitoring health status in the wild and outside of clinics. However, longitudinal, multimodal mobile sensor data can be small, noisy, and incomplete. This makes processing, modeling, and prediction of these data challenging. The small size of the data set restricts it from being modeled using complex deep learning networks. The current state of the art (SOTA) tackles small sensor data sets following a singular modeling paradigm based on traditional machine learning (ML) algorithms. These opt for either a user-agnostic modeling approach, making the model susceptible to a larger degree of noise, or a personalized approach, where training on individual data alludes to a more limited data set, giving rise to overfitting, therefore, ultimately, having to seek a trade-off by choosing 1 of the 2 modeling approaches to reach predictions. Objective: The objective of this study was to filter, rank, and output the best predictions for small, multimodal, longitudinal sensor data using a framework that is designed to tackle data sets that are limited in size (particularly targeting health studies that use passive multimodal sensors) and that combines both user agnostic and personalized approaches, along with a combination of ranking strategies to filter predictions. Methods: In this paper, we introduced a novel ranking framework for longitudinal multimodal sensors (FLMS) to address challenges encountered in health studies involving passive multimodal sensors. Using the FLMS, we (1) built a tensor-based aggregation and ranking strategy for final interpretation, (2) processed various combinations of sensor fusions, and (3) balanced user-agnostic and personalized modeling approaches with appropriate cross-validation strategies. The performance of the FLMS was validated with the help of a real data set of adolescents diagnosed with major depressive disorder for the prediction of change in depression in the adolescent participants. Results: Predictions output by the proposed FLMS achieved a 7% increase in accuracy and a 13% increase in recall for the real data set. Experiments with existing SOTA ML algorithms showed an 11% increase in accuracy for the depression data set and how overfitting and sparsity were handled. Conclusions: The FLMS aims to fill the gap that currently exists when modeling passive sensor data with a small number of data points. It achieves this through leveraging both user-agnostic and personalized modeling techniques in tandem with an effective ranking strategy to filter predictions.


  • Open Access

    Evaluating the Feasibility of a Multiplayer Role-Playing Game as a Behavioral Health Intervention in Adolescent Patients With Chronic Physical or Mental Conditions: Protocol for a Cohort Study

    by Dmitriy Babichenko, Ana Radovic, Ravi Patel, Alexis Hester, Koehler Powell, Nicholas Eggers, David Happe

    Background: Numerous studies have revealed that adolescents with chronic physical or mental conditions (CPMCs) are at an increased risk for depression and anxiety, with serious direct and indirect negative effects on treatment adherence, family functioning, and health-related quality of life. As game-based approaches are effective interventions in treating anxiety and depression, we propose to explore the use of a multiplayer role-playing game (RPG) as a potential intervention for social isolation, anxiety, and depression. Objective: The objectives of this study were to (1) determine the feasibility of using Masks, a multiplayer RPG, as an intervention for social isolation, anxiety, and depression in adolescents with CPMCs; (2) evaluate the viability of the research process; and (3) gauge participation in and engagement with RPG-based interventions. Methods: This study is a remote synchronous game-based intervention for adolescents with CPMCs aged 14-19 years. Eligible participants completed a web-based baseline survey to assess anxiety, depression, and social isolation and to identify their gaming habits. After completing the baseline survey, they participated in 5 moderated Masks game sessions. In Masks, players assume the roles of young superheroes; select their character types, superpowers; and perform actions determined by the game’s rule system and dice rolls. All game sessions were played using Discord, a communication platform commonly used by gaming communities. Games were led and moderated by game masters (GMs). After each game session, participants completed surveys to assess changes in anxiety, depression, and social isolation, and their attitude toward the game and the user experience. The participants also completed an exit survey after all 5 game sessions (modified version of the Patient Health Questionnaire and the Generalized Anxiety Disorder Questionnaire, and 17 open-ended questions). The GMs rated each game session and reported on gameplay, player behavior, comfort, and engagement levels of the players. Results: As of March 2020, six participants were recruited for the pilot study to participate in moderated web-based game sessions of Masks; 3 completed all game sessions and all required assessments. Although the number of participants was too low to draw generalizable conclusions, self-reported clinical outcomes did seem to indicate a positive change in depression, anxiety, and social isolation symptoms. Qualitative analysis of postgame survey data from participants and GMs indicated high levels of engagement and enjoyment. Furthermore, the participants provided feedback about improved mood and engagement related to weekly participation in Masks. Lastly, responses to the exit survey showed interest in future RPG-related studies. Conclusions: We established a workflow for gameplay and evaluated a research protocol for evaluating the impact of RPG participation on isolation, anxiety, and depression symptoms in adolescents with CPMCs. Preliminary data collected from the pilot study support the validity of the research protocol and the use of RPG-based interventions in larger clinical studies. International Registered Report Identifier (IRRID): RR1-10.2196/43987


  • Open Access

    Framework for Ranking Machine Learning Predictions of Limited, Multimodal, and Longitudinal Behavioral Passive Sensing Data: Combining User-Agnostic and Personalized Modeling (Preprint)

    by Tahsin Mullick, Sam Shaaban, Ana Radovic, Afsaneh Doryab

    BACKGROUND Passive mobile sensing provides opportunities for measuring and monitoring health status in the wild and outside of clinics. However, longitudinal, multimodal mobile sensor data can be small, noisy, and incomplete. This makes processing, modeling, and prediction of these data challenging. The small size of the data set restricts it from being modeled using complex deep learning networks. The current state of the art (SOTA) tackles small sensor data sets following a singular modeling paradigm based on traditional machine learning (ML) algorithms. These opt for either a user-agnostic modeling approach, making the model susceptible to a larger degree of noise, or a personalized approach, where training on individual data alludes to a more limited data set, giving rise to overfitting, therefore, ultimately, having to seek a trade-off by choosing 1 of the 2 modeling approaches to reach predictions. OBJECTIVE The objective of this study was to filter, rank, and output the best predictions for small, multimodal, longitudinal sensor data using a framework that is designed to tackle data sets that are limited in size (particularly targeting health studies that use passive multimodal sensors) and that combines both user agnostic and personalized approaches, along with a combination of ranking strategies to filter predictions. METHODS In this paper, we introduced a novel ranking framework for longitudinal multimodal sensors (FLMS) to address challenges encountered in health studies involving passive multimodal sensors. Using the FLMS, we (1) built a tensor-based aggregation and ranking strategy for final interpretation, (2) processed various combinations of sensor fusions, and (3) balanced user-agnostic and personalized modeling approaches with appropriate cross-validation strategies. The performance of the FLMS was validated with the help of a real data set of adolescents diagnosed with major depressive disorder for the prediction of change in depression in the adolescent participants. RESULTS Predictions output by the proposed FLMS achieved a 7% increase in accuracy and a 13% increase in recall for the real data set. Experiments with existing SOTA ML algorithms showed an 11% increase in accuracy for the depression data set and how overfitting and sparsity were handled. CONCLUSIONS The FLMS aims to fill the gap that currently exists when modeling passive sensor data with a small number of data points. It achieves this through leveraging both user-agnostic and personalized modeling techniques in tandem with an effective ranking strategy to filter predictions.

  • Middle School Students’ Experiences with Cyberbullying and Perspectives Toward Prevention and Bystander Intervention in Schools

    by Candice Biernesser, Mary Ohmer, Lisa Nelson, Elizabeth Mann, Rosta Farzan, Beth Schwanke, Ana Radovic

    Cyberbullying is a growing problem for middle school students. Bystander interventions that train witnesses to positively intervene can prevent cyberbullying. Through six focus groups, we explored forty-six middle school students’ experiences with cyberbullying and opportunities for school-based prevention programs to encourage positive bystander behavior. Focus groups were recorded, transcribed, and analyzed using content analysis. Students viewed cyberbullying as an important problem with significant consequences. They noted hesitancy in reporting to parents and school personnel and felt more comfortable discussing cyberbullying with a near-peer (e.g. older sibling or friend). Students desired combining school-based and online programming with near-peer mentorship. This study suggests need for targeted prevention programs that center middle school students’ lived experiences with cyberbullying and their preferences for learning and utilizing positive bystander strategies.


  • Open Access

    Support over Social Media among Socially Isolated Sexual and Gender Minority Youth in Rural U.S. during the COVID-19 Pandemic: Opportunities for Intervention Research

    by Sana Karim, Sophia Choukas-Bradley, Ana Radovic, Savannah R. Roberts, Anne J. Maheux, César G. Escobar-Viera

    Sexual and gender minority (SGM) rural adolescents are at risk for higher levels of social isolation, a well-known risk factor for depression and other negative health outcomes. We qualitatively examined how rural SGM youth seek emotional and informational support, which are protective factors for social isolation on social media (SM) regarding their SGM identity, and determined which SM platforms and tools are most effective in providing support. We conducted semistructured online interviews with rural SGM teens who screened positive for social isolation in spring 2020 and used a thematic analysis approach to analyze the data. Sixteen youths participated in interviews. Themes included seeking emotional support through SM groups and communities, seeking emotional support in designated online SGM spaces, using SM feeds for informational support, and disclosing SGM identity differentially across platforms. SM-based interventions could be leveraged to provide emotional and informational support for rural SGM youth across specific SM platforms and consider whether they are providing emotional or information support. Interventions focused on informational support may best be used on content-based platforms. Those designed to combat social isolation and connect marginalized SGM youths to similar others might benefit from community and forum-based platforms.


  • Open Access

    Evaluating the Feasibility of a Multiplayer Role-Playing Game as a Behavioral Health Intervention in Adolescent Patients With Chronic Physical or Mental Conditions: Protocol for a Cohort Study (Preprint)

    by Dmitriy Babichenko, Ana Radovic, Ravi Patel, Alexis Hester, Koehler Powell, Nicholas Eggers, David Happe

    BACKGROUND Numerous studies have revealed that adolescents with chronic physical or mental conditions (CPMCs) are at an increased risk for depression and anxiety, with serious direct and indirect negative effects on treatment adherence, family functioning, and health-related quality of life. As game-based approaches are effective interventions in treating anxiety and depression, we propose to explore the use of a multiplayer role-playing game (RPG) as a potential intervention for social isolation, anxiety, and depression. OBJECTIVE The objectives of this study were to (1) determine the feasibility of using Masks, a multiplayer RPG, as an intervention for social isolation, anxiety, and depression in adolescents with CPMCs; (2) evaluate the viability of the research process; and (3) gauge participation in and engagement with RPG-based interventions. METHODS This study is a remote synchronous game-based intervention for adolescents with CPMCs aged 14-19 years. Eligible participants completed a web-based baseline survey to assess anxiety, depression, and social isolation and to identify their gaming habits. After completing the baseline survey, they participated in 5 moderated Masks game sessions. In Masks, players assume the roles of young superheroes; select their character types, superpowers; and perform actions determined by the game’s rule system and dice rolls. All game sessions were played using Discord, a communication platform commonly used by gaming communities. Games were led and moderated by game masters (GMs). After each game session, participants completed surveys to assess changes in anxiety, depression, and social isolation, and their attitude toward the game and the user experience. The participants also completed an exit survey after all 5 game sessions (modified version of the Patient Health Questionnaire and the Generalized Anxiety Disorder Questionnaire, and 17 open-ended questions). The GMs rated each game session and reported on gameplay, player behavior, comfort, and engagement levels of the players. RESULTS As of March 2020, six participants were recruited for the pilot study to participate in moderated web-based game sessions of Masks; 3 completed all game sessions and all required assessments. Although the number of participants was too low to draw generalizable conclusions, self-reported clinical outcomes did seem to indicate a positive change in depression, anxiety, and social isolation symptoms. Qualitative analysis of postgame survey data from participants and GMs indicated high levels of engagement and enjoyment. Furthermore, the participants provided feedback about improved mood and engagement related to weekly participation in Masks. Lastly, responses to the exit survey showed interest in future RPG-related studies. CONCLUSIONS We established a workflow for gameplay and evaluated a research protocol for evaluating the impact of RPG participation on isolation, anxiety, and depression symptoms in adolescents with CPMCs. Preliminary data collected from the pilot study support the validity of the research protocol and the use of RPG-based interventions in larger clinical studies. CLINICALTRIAL INTERNATIONAL REGISTERED REPORT RR1-10.2196/43987

  • Open Access

    A Social Media Website (Supporting Our Valued Adolescents) to Support Treatment Uptake for Adolescents with Depression or Anxiety: Outcomes From a Pilot Randomized Controlled Trial (Preprint)

    by Ana Radovic, Yaming Li, Doug Landsittel, Kayla R Odenthal, Bradley D Stein, Elizabeth Miller

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Adolescents with depression or anxiety initiate mental health treatment in low numbers due to multiple factors, with a top reason being negative attitudes towards treatment. We developed a peer-support website intervention, Supporting Our Valued Adolescents (SOVA), for adolescents seen in primary care settings and their parents with the goal of increasing treatment uptake through changing negative health beliefs, enhancing knowledge, offering peer emotional support, and increasing parent-adolescent communication about mental health. Objective: The aim of this pilot study was to refine recruitment and retention strategies, document intervention fidelity, and explore change in study outcomes (primary outcome being treatment uptake). Methods: We conducted a two-group, single blind, pilot randomized controlled trial in a single adolescent medicine clinic. Participants were aged 12 to 19 with clinician-identified symptoms of depression or anxiety for which a health care provider recommends treatment. The patient and parent, if interested, were randomized to receive the SOVA websites and Enhanced Usual Care (EUC) compared to EUC alone. Baseline, 6-week, and 3-month measures were collected by web-based self-report survey and blinded electronic health record review. Main pilot outcomes assessed were feasibility of recruitment and retention strategies. Implementation outcomes, intervention fidelity, missingness, and adequacy of safety protocols were documented. Descriptive statistics were used to summarize mental health service use, and target measures (examine change in health beliefs and knowledge, emotional support, and parent-adolescent communication) using 2-sample t tests to compare differences between arms. Results: A little under half of adolescents offered patient education material (195/461; 42%) were referred by their clinician to the study. Of 146 adolescents meeting inclusion criteria, 38 completed the baseline survey, qualifying them for randomization, and 25 (66%; 95% CI 51 - 81%) completed 6-week measures. There was limited engagement in the treatment arm with (5/11) 45% of adolescents who completed 6-week measures reporting accessing SOVA, mostly citing forgetting. Changes were found in target factors at 6-weeks, but not in per protocol analyses. Despite this, at 12 weeks, 15/18 (83%) adolescents randomized to SOVA received mental health treatment as compared to 10/20 (50%) adolescents randomized to EUC (P=.03), where receipt of treatment was measured by combined adolescent or parent self-report and a blinded manual EHR extraction. Conclusions: In this pilot trial of a peer-support website intervention for adolescents with depression or anxiety we found lower than expected study enrollment post recruitment. While generalizability may be enhanced by not requiring parental permission for adolescent participation in trials of mental health interventions, this may limit study recruitment and retention. We found implementing patient education introducing the study into provider workflow was feasible and acceptable, resulting in almost 500 study referrals. Lastly, we found preliminary evidence that the SOVA intervention may increase uptake of mental health treatment as compared to usual care. Clinical Trial: ClinicalTrials.gov NCT03318666; https://clinicaltrials.gov/ct2/show/NCT03318666