Hyunsil Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hyunsil Song has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chanmi Park
HCI Lab, Yonsei University, Seoul, Republic of Korea
5 shared publications - Jinwoo Kim
Yonsei University
5 shared publications - Jee Hang Lee
Department of Human-Centered AI, Sangmyung University, Seoul 03016, Republic of Korea
3 shared publications - Eunji Kim
Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
2 shared publications - Hanna Kim
HAII Corp, Seoul, Republic of Korea
2 shared publications - Hye-Jeong Jo
Institute of Behavioral Science in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 14, e88919
Integration of Ecological Momentary Assessment and Intervention With Wearable-Based Digital Phenotypes to Treat Anxiety in Young Adults: Mixed Methods Experimental Study
Background: Young adults report high levels of anxiety, yet their access to timely treatment remains limited. Mobile-based digital therapeutics, particularly ecological momentary assessment and intervention (EMA/EMI), offer a promising approach to deliver context-responsive care. The integration of wearable-derived digital phenotypes with digital therapeutics may enhance the personalization of feedback in such interventions, but empirical evidence from real-world settings remains scarce. Objective: This study examined the real-world applicability and effectiveness of an EMA/EMI-based digital therapeutic, ANZEILAX-Green (HAII Corp), for use in anxiety reduction in young adults and investigated how personalized feedback generated by combining EMA/EMI data with wearable-based digital phenotypes ameliorates symptoms and promotes self-management and user engagement. Methods: An 8-week exploratory experimental study was conducted with young adults aged 19-39 years. Participants used a smartphone app in which EMA/EMI modules had been integrated with a smartwatch that continuously collected digital phenotyping data, including heart rate, sleep, and activity. Psychological outcomes were assessed using the Generalized Anxiety Disorder 7-item scale (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) at baseline and weeks 2, 4, 6, and 8, and the Rosenberg Self-Esteem Scale (RSES) at baseline and week 8. Quantitative changes were analyzed using paired-samples t tests and repeated-measures ANOVA, and qualitative interviews were thematically analyzed to identify user experience mechanisms and design implications. Results: In all, 29 participants were included in the final analysis. Significant improvements were observed in their GAD-7 (mean difference –4.79, 95% CI –6.56 to –3.02; Cohen d=1.03; P<.001), PHQ-9 (mean difference –3.86, 95% CI –5.79 to –1.93; Cohen d=0.76; P<.001), and RSES scores (mean difference +5.21, 95% CI 3.47 to 6.95; Cohen d=1.14; P<.001). Consistent improvements in GAD-7 scores were observed across the assessment points, with statistically significant reductions from week 4 onward. Participants demonstrated high adherence, completing 80% of the EMA/EMI prompts. The digital phenotype showed trends of increased deep sleep and reduced mobility, and sleep indicators were significantly correlated with depressive symptoms. Analysis of the interview findings revealed 5 mechanisms: enhanced self-awareness, data-driven reflection, behavioral change, intrinsic motivation, and extension of treatment into daily life. Conclusions: EMA/EMI-based digital therapeutics integrated with wearable-derived digital phenotypes are feasible and acceptable for use by young adults and were associated with within-group reductions in anxiety, suggesting acceptable efficacy, though this warrants confirmation in a controlled trial. The combination of real-time self-reported assessments of emotional states and passive physiological monitoring enables personalized feedback suited to users’ emotional and physiological states. These findings offer empirical and design insights for automated, personalized mental health intervention systems.
- 8 October 2026
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
- Vol. 14, e88919
Open AccessIntegration of Ecological Momentary Assessment and Intervention With Wearable-Based Digital Phenotypes to Treat Anxiety in Young Adults: Mixed Methods Experimental Study
Background: Young adults report high levels of anxiety, yet their access to timely treatment remains limited. Mobile-based digital therapeutics, particularly ecological momentary assessment and intervention (EMA/EMI), offer a promising approach to deliver context-responsive care. The integration of wearable-derived digital phenotypes with digital therapeutics may enhance the personalization of feedback in such interventions, but empirical evidence from real-world settings remains scarce. Objective: This study examined the real-world applicability and effectiveness of an EMA/EMI-based digital therapeutic, ANZEILAX-Green (HAII Corp), for use in anxiety reduction in young adults and investigated how personalized feedback generated by combining EMA/EMI data with wearable-based digital phenotypes ameliorates symptoms and promotes self-management and user engagement. Methods: An 8-week exploratory experimental study was conducted with young adults aged 19-39 years. Participants used a smartphone app in which EMA/EMI modules had been integrated with a smartwatch that continuously collected digital phenotyping data, including heart rate, sleep, and activity. Psychological outcomes were assessed using the Generalized Anxiety Disorder 7-item scale (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) at baseline and weeks 2, 4, 6, and 8, and the Rosenberg Self-Esteem Scale (RSES) at baseline and week 8. Quantitative changes were analyzed using paired-samples t tests and repeated-measures ANOVA, and qualitative interviews were thematically analyzed to identify user experience mechanisms and design implications. Results: In all, 29 participants were included in the final analysis. Significant improvements were observed in their GAD-7 (mean difference –4.79, 95% CI –6.56 to –3.02; Cohen d=1.03; P<.001), PHQ-9 (mean difference –3.86, 95% CI –5.79 to –1.93; Cohen d=0.76; P<.001), and RSES scores (mean difference +5.21, 95% CI 3.47 to 6.95; Cohen d=1.14; P<.001). Consistent improvements in GAD-7 scores were observed across the assessment points, with statistically significant reductions from week 4 onward. Participants demonstrated high adherence, completing 80% of the EMA/EMI prompts. The digital phenotype showed trends of increased deep sleep and reduced mobility, and sleep indicators were significantly correlated with depressive symptoms. Analysis of the interview findings revealed 5 mechanisms: enhanced self-awareness, data-driven reflection, behavioral change, intrinsic motivation, and extension of treatment into daily life. Conclusions: EMA/EMI-based digital therapeutics integrated with wearable-derived digital phenotypes are feasible and acceptable for use by young adults and were associated with within-group reductions in anxiety, suggesting acceptable efficacy, though this warrants confirmation in a controlled trial. The combination of real-time self-reported assessments of emotional states and passive physiological monitoring enables personalized feedback suited to users’ emotional and physiological states. These findings offer empirical and design insights for automated, personalized mental health intervention systems.
- Open Access
- 6 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Integrating Ecological Momentary Assessment and Intervention With Wearable-Based Digital Phenotypes for Anxiety in Young Adults: A Mixed-Method Experimental Study (Preprint)
BACKGROUND Anxiety is highly prevalent among young adults, yet access to timely treatment remains limited. Mobile-based digital therapeutics, particularly Ecological Momentary Assessment and Intervention (EMA·EMI), offer a promising approach for delivering context-responsive care. Integrating wearable-derived digital phenotypes may enhance the precision and personalization of such interventions, but empirical evidence from real-world settings remains scarce. OBJECTIVE This study examined the real-world applicability and effectiveness of an EMA·EMI–based digital therapeutic, ANZEILAX-Green, for anxiety reduction in young adults. It further investigated how personalized feedback generated by combining EMA·EMI data with wearable-based digital phenotypes supports symptom improvement, self-management, and user engagement. METHODS An eight-week exploratory experimental study conducted with young adults aged 19–39 years. Participants used a smartphone app integrating EMA·EMI modules along with a smartwatch that continuously collected digital phenotyping data, including heart rate, sleep, and activity. Psychological outcomes were assessed using the Generalized Anxiety Disorder 7-item scale (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) at baseline, weeks 2, 4, 6, and 8, and Rosenberg Self Esteem Scale (RSES) at baseline and week 8. Quantitative changes were analyzed using paired t tests and repeated-measures analysis of variance, and qualitative interviews were thematically analyzed to identify user experience mechanisms and design implications. RESULTS Twenty-nine participants were included in the final analysis. Significant improvements were observed in GAD-7 scores (mean difference –4.79, 95% CI –6.56 to –3.02, P<.001, Cohen d=1.03), PHQ-9 (mean difference –3.86, 95% CI –5.79 to –1.93, P<.001, Cohen d=0.76), RSES (mean difference +5.21, 95% CI 3.47 to 6.85, P<.001, Cohen d=1.14). Consistent improvements in GAD-7 scores were observed across assessment points, with statistically significant reductions from week 4 onward. Participants demonstrated high adherence, completing 80% of EMA·EMI prompts. Digital phenotype trends showed increased deep sleep and reduced mobility, and sleep indicators significantly correlated with depressive symptoms. Interview findings revealed five mechanisms: enhanced self-awareness, data-driven reflection, behavioral change, intrinsic motivation, and extension of treatment into daily life. CONCLUSIONS EMA·EMI–based digital therapeutics integrated with wearable-derived digital phenotypes are feasible and effective for reducing anxiety in young adults. The combination of real-time emotional self-reporting and passive physiological monitoring enables more personalized, timely, and context-aware interventions. These findings provide empirical and design insights for future automated, personalized mental health intervention systems.
- 6 December 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessIntegrating Ecological Momentary Assessment and Intervention With Wearable-Based Digital Phenotypes for Anxiety in Young Adults: A Mixed-Method Experimental Study (Preprint)
BACKGROUND Anxiety is highly prevalent among young adults, yet access to timely treatment remains limited. Mobile-based digital therapeutics, particularly Ecological Momentary Assessment and Intervention (EMA·EMI), offer a promising approach for delivering context-responsive care. Integrating wearable-derived digital phenotypes may enhance the precision and personalization of such interventions, but empirical evidence from real-world settings remains scarce. OBJECTIVE This study examined the real-world applicability and effectiveness of an EMA·EMI–based digital therapeutic, ANZEILAX-Green, for anxiety reduction in young adults. It further investigated how personalized feedback generated by combining EMA·EMI data with wearable-based digital phenotypes supports symptom improvement, self-management, and user engagement. METHODS An eight-week exploratory experimental study conducted with young adults aged 19–39 years. Participants used a smartphone app integrating EMA·EMI modules along with a smartwatch that continuously collected digital phenotyping data, including heart rate, sleep, and activity. Psychological outcomes were assessed using the Generalized Anxiety Disorder 7-item scale (GAD-7) and Patient Health Questionnaire-9 (PHQ-9) at baseline, weeks 2, 4, 6, and 8, and Rosenberg Self Esteem Scale (RSES) at baseline and week 8. Quantitative changes were analyzed using paired t tests and repeated-measures analysis of variance, and qualitative interviews were thematically analyzed to identify user experience mechanisms and design implications. RESULTS Twenty-nine participants were included in the final analysis. Significant improvements were observed in GAD-7 scores (mean difference –4.79, 95% CI –6.56 to –3.02, P<.001, Cohen d=1.03), PHQ-9 (mean difference –3.86, 95% CI –5.79 to –1.93, P<.001, Cohen d=0.76), RSES (mean difference +5.21, 95% CI 3.47 to 6.85, P<.001, Cohen d=1.14). Consistent improvements in GAD-7 scores were observed across assessment points, with statistically significant reductions from week 4 onward. Participants demonstrated high adherence, completing 80% of EMA·EMI prompts. Digital phenotype trends showed increased deep sleep and reduced mobility, and sleep indicators significantly correlated with depressive symptoms. Interview findings revealed five mechanisms: enhanced self-awareness, data-driven reflection, behavioral change, intrinsic motivation, and extension of treatment into daily life. CONCLUSIONS EMA·EMI–based digital therapeutics integrated with wearable-derived digital phenotypes are feasible and effective for reducing anxiety in young adults. The combination of real-time emotional self-reporting and passive physiological monitoring enables more personalized, timely, and context-aware interventions. These findings provide empirical and design insights for future automated, personalized mental health intervention systems.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Talk to You More, Listen to You More, and Feel Better in Your Mind: Utilizing Self-talk as a Mechanism of Action for Alleviating Anxiety
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessTalk to You More, Listen to You More, and Feel Better in Your Mind: Utilizing Self-talk as a Mechanism of Action for Alleviating Anxiety
- Open Access
- 12 December 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e69981
Anzeilax, a Smartphone-based Digital Therapeutic for Generalized Anxiety Disorder: A Randomized Controlled Trial (Preprint)
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: Individuals with generalized anxiety disorder (GAD) often face challenges with self-regulation and limited access to traditional therapy. While Acceptance and Commitment Therapy (ACT) has demonstrated both efficacy and effectiveness in promoting psychological flexibility, scalable solutions are necessary to address these barriers. This study introduces Anzeilax, an ACT-based digital therapeutic (DTx) that incorporates self-talk as a novel mechanism of action (MoA) to enhance psychological flexibility in the treatment of GAD. Objective: This study aimed to evaluate the efficacy of Anzeilax in reducing anxiety symptoms in individuals with GAD. Methods: A 10-week, parallel-group, superiority randomized controlled trial was conducted with 96 participants diagnosed with GAD (GAD-7 scores ≥10, age ≥19 years). The participants were randomly assigned (1:1) to receive either Anzeilax, a self-guided ACT-based DTx incorporating self-talk content alongside treatment-as-usual (n=48), or treatment-as-usual alone (n=48). Only the outcome evaluators were blinded to the group assignment. The primary outcome was the change in GAD-7 score from baseline to week 10. The secondary outcomes included the Beck Anxiety Inventory (BAI) for anxiety symptoms, the Penn State Worrying Questionnaire (PSWQ) for pathological worry, and the Hospital Anxiety and Depression Scale (HADS) for anxiety and depression symptoms. All self-report outcomes were assessed at baseline and at weeks 5, 10 (post-intervention), and 15 (follow-up). Results: During the trial, 34 (71%) and 31 (65%) participants in the treatment group maintained at least 80% of the prescribed usage frequency at weeks 5 and 10, respectively. Based on the Full Analysis Set (FAS), participants using Anzeilax demonstrated significant improvement in anxiety symptoms compared to the control group. Analysis of the primary outcome at 10 weeks post-intervention compared to baseline exhibited a significant reduction in GAD-7 scores (adjusted mean difference: -2.26; 95% CI: -3.78 to -0.74, P=.002). Secondary outcomes at the same time point indicated consistent improvements, with significant group-by-time interactions observed in the GAD-7 (P=.008, Cohen d=0.60), BAI (P=.008, Cohen d=0.50), PSWQ (P=.002, Cohen d=0.62), and HADS-A (P=.014, Cohen d=0.50). These improvements were sustained throughout the 15-week follow-up period. While the differences in depressive symptoms between the two groups did not present statistical significance, notable improvements were observed in the treatment group. Conclusions: Anzeilax demonstrated clinically meaningful efficacy in reducing anxiety symptoms when combined with treatment-as-usual. The results showed consistent improvements across multiple anxiety measures, with effects sustained through follow-up. The incorporation of context-sensitive self-talk within an ACT-based DTx framework offers a promising and accessible solution for treating individuals with GAD. Clinical Trial: ClinicalTrials.gov NCT06010654
- 12 December 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 27, e69981
Open AccessAnzeilax, a Smartphone-based Digital Therapeutic for Generalized Anxiety Disorder: A Randomized Controlled Trial (Preprint)
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: Individuals with generalized anxiety disorder (GAD) often face challenges with self-regulation and limited access to traditional therapy. While Acceptance and Commitment Therapy (ACT) has demonstrated both efficacy and effectiveness in promoting psychological flexibility, scalable solutions are necessary to address these barriers. This study introduces Anzeilax, an ACT-based digital therapeutic (DTx) that incorporates self-talk as a novel mechanism of action (MoA) to enhance psychological flexibility in the treatment of GAD. Objective: This study aimed to evaluate the efficacy of Anzeilax in reducing anxiety symptoms in individuals with GAD. Methods: A 10-week, parallel-group, superiority randomized controlled trial was conducted with 96 participants diagnosed with GAD (GAD-7 scores ≥10, age ≥19 years). The participants were randomly assigned (1:1) to receive either Anzeilax, a self-guided ACT-based DTx incorporating self-talk content alongside treatment-as-usual (n=48), or treatment-as-usual alone (n=48). Only the outcome evaluators were blinded to the group assignment. The primary outcome was the change in GAD-7 score from baseline to week 10. The secondary outcomes included the Beck Anxiety Inventory (BAI) for anxiety symptoms, the Penn State Worrying Questionnaire (PSWQ) for pathological worry, and the Hospital Anxiety and Depression Scale (HADS) for anxiety and depression symptoms. All self-report outcomes were assessed at baseline and at weeks 5, 10 (post-intervention), and 15 (follow-up). Results: During the trial, 34 (71%) and 31 (65%) participants in the treatment group maintained at least 80% of the prescribed usage frequency at weeks 5 and 10, respectively. Based on the Full Analysis Set (FAS), participants using Anzeilax demonstrated significant improvement in anxiety symptoms compared to the control group. Analysis of the primary outcome at 10 weeks post-intervention compared to baseline exhibited a significant reduction in GAD-7 scores (adjusted mean difference: -2.26; 95% CI: -3.78 to -0.74, P=.002). Secondary outcomes at the same time point indicated consistent improvements, with significant group-by-time interactions observed in the GAD-7 (P=.008, Cohen d=0.60), BAI (P=.008, Cohen d=0.50), PSWQ (P=.002, Cohen d=0.62), and HADS-A (P=.014, Cohen d=0.50). These improvements were sustained throughout the 15-week follow-up period. While the differences in depressive symptoms between the two groups did not present statistical significance, notable improvements were observed in the treatment group. Conclusions: Anzeilax demonstrated clinically meaningful efficacy in reducing anxiety symptoms when combined with treatment-as-usual. The results showed consistent improvements across multiple anxiety measures, with effects sustained through follow-up. The incorporation of context-sensitive self-talk within an ACT-based DTx framework offers a promising and accessible solution for treating individuals with GAD. Clinical Trial: ClinicalTrials.gov NCT06010654
- Open Access
- 12 December 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Anzeilax, a Smartphone-based Digital Therapeutic for Generalized Anxiety Disorder: A Randomized Controlled Trial (Preprint)
BACKGROUND Individuals with generalized anxiety disorder (GAD) often face challenges with self-regulation and limited access to traditional therapy. While Acceptance and Commitment Therapy (ACT) has demonstrated both efficacy and effectiveness in promoting psychological flexibility, scalable solutions are necessary to address these barriers. This study introduces Anzeilax, an ACT-based digital therapeutic (DTx) that incorporates self-talk as a novel mechanism of action (MoA) to enhance psychological flexibility in the treatment of GAD. OBJECTIVE This study aimed to evaluate the efficacy of Anzeilax in reducing anxiety symptoms in individuals with GAD. METHODS A 10-week, parallel-group, superiority randomized controlled trial was conducted with 96 participants diagnosed with GAD (GAD-7 scores ≥10, age ≥19 years). The participants were randomly assigned (1:1) to receive either Anzeilax, a self-guided ACT-based DTx incorporating self-talk content alongside treatment-as-usual (n=48), or treatment-as-usual alone (n=48). Only the outcome evaluators were blinded to the group assignment. The primary outcome was the change in GAD-7 score from baseline to week 10. The secondary outcomes included the Beck Anxiety Inventory (BAI) for anxiety symptoms, the Penn State Worrying Questionnaire (PSWQ) for pathological worry, and the Hospital Anxiety and Depression Scale (HADS) for anxiety and depression symptoms. All self-report outcomes were assessed at baseline and at weeks 5, 10 (post-intervention), and 15 (follow-up). RESULTS During the trial, 34 (71%) and 31 (65%) participants in the treatment group maintained at least 80% of the prescribed usage frequency at weeks 5 and 10, respectively. Based on the Full Analysis Set (FAS), participants using Anzeilax demonstrated significant improvement in anxiety symptoms compared to the control group. Analysis of the primary outcome at 10 weeks post-intervention compared to baseline exhibited a significant reduction in GAD-7 scores (adjusted mean difference: -2.26; 95% CI: -3.78 to -0.74, P=.002). Secondary outcomes at the same time point indicated consistent improvements, with significant group-by-time interactions observed in the GAD-7 (P=.008, Cohen d=0.60), BAI (P=.008, Cohen d=0.50), PSWQ (P=.002, Cohen d=0.62), and HADS-A (P=.014, Cohen d=0.50). These improvements were sustained throughout the 15-week follow-up period. While the differences in depressive symptoms between the two groups did not present statistical significance, notable improvements were observed in the treatment group. CONCLUSIONS Anzeilax demonstrated clinically meaningful efficacy in reducing anxiety symptoms when combined with treatment-as-usual. The results showed consistent improvements across multiple anxiety measures, with effects sustained through follow-up. The incorporation of context-sensitive self-talk within an ACT-based DTx framework offers a promising and accessible solution for treating individuals with GAD. CLINICALTRIAL ClinicalTrials.gov NCT06010654
- 12 December 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAnzeilax, a Smartphone-based Digital Therapeutic for Generalized Anxiety Disorder: A Randomized Controlled Trial (Preprint)
BACKGROUND Individuals with generalized anxiety disorder (GAD) often face challenges with self-regulation and limited access to traditional therapy. While Acceptance and Commitment Therapy (ACT) has demonstrated both efficacy and effectiveness in promoting psychological flexibility, scalable solutions are necessary to address these barriers. This study introduces Anzeilax, an ACT-based digital therapeutic (DTx) that incorporates self-talk as a novel mechanism of action (MoA) to enhance psychological flexibility in the treatment of GAD. OBJECTIVE This study aimed to evaluate the efficacy of Anzeilax in reducing anxiety symptoms in individuals with GAD. METHODS A 10-week, parallel-group, superiority randomized controlled trial was conducted with 96 participants diagnosed with GAD (GAD-7 scores ≥10, age ≥19 years). The participants were randomly assigned (1:1) to receive either Anzeilax, a self-guided ACT-based DTx incorporating self-talk content alongside treatment-as-usual (n=48), or treatment-as-usual alone (n=48). Only the outcome evaluators were blinded to the group assignment. The primary outcome was the change in GAD-7 score from baseline to week 10. The secondary outcomes included the Beck Anxiety Inventory (BAI) for anxiety symptoms, the Penn State Worrying Questionnaire (PSWQ) for pathological worry, and the Hospital Anxiety and Depression Scale (HADS) for anxiety and depression symptoms. All self-report outcomes were assessed at baseline and at weeks 5, 10 (post-intervention), and 15 (follow-up). RESULTS During the trial, 34 (71%) and 31 (65%) participants in the treatment group maintained at least 80% of the prescribed usage frequency at weeks 5 and 10, respectively. Based on the Full Analysis Set (FAS), participants using Anzeilax demonstrated significant improvement in anxiety symptoms compared to the control group. Analysis of the primary outcome at 10 weeks post-intervention compared to baseline exhibited a significant reduction in GAD-7 scores (adjusted mean difference: -2.26; 95% CI: -3.78 to -0.74, P=.002). Secondary outcomes at the same time point indicated consistent improvements, with significant group-by-time interactions observed in the GAD-7 (P=.008, Cohen d=0.60), BAI (P=.008, Cohen d=0.50), PSWQ (P=.002, Cohen d=0.62), and HADS-A (P=.014, Cohen d=0.50). These improvements were sustained throughout the 15-week follow-up period. While the differences in depressive symptoms between the two groups did not present statistical significance, notable improvements were observed in the treatment group. CONCLUSIONS Anzeilax demonstrated clinically meaningful efficacy in reducing anxiety symptoms when combined with treatment-as-usual. The results showed consistent improvements across multiple anxiety measures, with effects sustained through follow-up. The incorporation of context-sensitive self-talk within an ACT-based DTx framework offers a promising and accessible solution for treating individuals with GAD. CLINICALTRIAL ClinicalTrials.gov NCT06010654