Yanick Xavier Lukic


Last Name

Lukic

First Name

Yanick Xavier

ORCID

0000-0002-2576-6569

Organisational unit

Filters

2021 - 202515
Reset filters

Search Results

Publications1 - 10 of 15
  • Development of a digital biomarker and intervention for subclinical depression: study protocol for a longitudinal waitlist control study
    Item type: Journal Article
    Teepe, Gisbert W.; Lukic, Yanick Xavier; Kleim, Birgit; et al. (2023)
    BMC Psychology
    Background Depression remains a global health problem, with its prevalence rising worldwide. Digital biomarkers are increasingly investigated to initiate and tailor scalable interventions targeting depression. Due to the steady influx of new cases, focusing on treatment alone will not suffice; academics and practitioners need to focus on the prevention of depression (i.e., addressing subclinical depression). Aim With our study, we aim to (i) develop digital biomarkers for subclinical symptoms of depression, (ii) develop digital biomarkers for severity of subclinical depression, and (iii) investigate the efficacy of a digital intervention in reducing symptoms and severity of subclinical depression. Method Participants will interact with the digital intervention BEDDA consisting of a scripted conversational agent, the slow-paced breathing training Breeze, and actionable advice for different symptoms. The intervention comprises 30 daily interactions to be completed in less than 45 days. We will collect self-reports regarding mood, agitation, anhedonia (proximal outcomes; first objective), self-reports regarding depression severity (primary distal outcome; second and third objective), anxiety severity (secondary distal outcome; second and third objective), stress (secondary distal outcome; second and third objective), voice, and breathing. A subsample of 25% of the participants will use smartwatches to record physiological data (e.g., heart-rate, heart-rate variability), which will be used in the analyses for all three objectives. Discussion Digital voice- and breathing-based biomarkers may improve diagnosis, prevention, and care by enabling an unobtrusive and either complementary or alternative assessment to self-reports. Furthermore, our results may advance our understanding of underlying psychophysiological changes in subclinical depression. Our study also provides further evidence regarding the efficacy of standalone digital health interventions to prevent depression.
  • Physiological Responses and User Feedback on a Gameful Breathing Training App: Within-Subject Experiment
    Item type: Journal Article
    Lukic, Yanick Xavier; Shih, Chen-Hsuan Iris; Hernández Reguera, Álvaro; et al. (2021)
    JMIR Serious Games
    Background: Slow-paced breathing training (6 breaths per minute [BPM]) improves physiological and psychological well-being by inducing relaxation characterized by increased heart rate variability (HRV). However, classic breathing training has a limited target group, and retention rates are very low. Although a gameful approach may help overcome these challenges, it is crucial to enable breathing training in a scalable context (eg, smartphone only) and ensure that they remain effective. However, despite the health benefits, no validated mobile gameful breathing training featuring a biofeedback component based on breathing seems to exist. Objective: This study aims to describe the design choices and their implementation in a concrete mobile gameful breathing training app. Furthermore, it aims to deliver an initial validation of the efficacy of the resulting app. Methods: Previous work was used to derive informed design choices, which, in turn, were applied to build the gameful breathing training app Breeze. In a pretest (n=3), design weaknesses in Breeze were identified, and Breeze was adjusted accordingly. The app was then evaluated in a pilot study (n=16). To ascertain that the effectiveness was maintained, recordings of breathing rates and HRV-derived measures (eg, root mean square of the successive differences [RMSSDs]) were collected. We compared 3 stages: baseline, standard breathing training deployed on a smartphone, and Breeze. Results: Overall, 5 design choices were made: use of cool colors, natural settings, tightly incorporated game elements, game mechanics reflecting physiological measures, and a light narrative and progression model. Breeze was effective, as it resulted in a slow-paced breathing rate of 6 BPM, which, in turn, resulted in significantly increased HRV measures compared with baseline (P<.001 for RMSSD). In general, the app was perceived positively by the participants. However, some criticized the somewhat weaker clarity of the breathing instructions when compared with a standard breathing training app. Conclusions: The implemented breathing training app Breeze maintained its efficacy despite the use of game elements. Moreover, the app was positively perceived by participants although there was room for improvement.
  • Long-Term Usage of Breeze, a Gamified Breathing Training App, and Its Effect on Momentary Relaxation in People With Cancer: Cohort Study
    Item type: Journal Article
    Bischof, Anja Yvonne; Budig, Tobias; Schläpfer, Sonja; et al. (2025)
    JMIR Serious Games
    Background: People with cancer often experience stress. Digital health interventions can help individuals increase momentary relaxation. Breeze is a gamified breathing training that can be embedded into digital health interventions. Its effectiveness in controlled cross-sectional studies has been demonstrated. However, adherence to Breeze and its effect on momentary relaxation in longitudinal interventional studies has yet to be investigated. Objective: This study aimed to assess Breeze across 3 key dimensions: (1) its usage over time compared to other intervention components; (2) the accuracy with which users adhered to the guiding breathing pattern provided by Breeze; and (3) its effect on momentary relaxation, including the impact of the duration of the breathing session delivered by Breeze. Methods: Breeze was 1 of 7 relaxation techniques included in the CanRelax 2.0 app, designed specifically for individuals diagnosed with cancer. Participants could select any of the 7 techniques to promote momentary relaxation. The intervention was designed to last 10 weeks. However, participants were allowed to use the CanRelax 2.0 app after that period. Participants were adults diagnosed with cancer in the last 5 years recruited across Switzerland, Germany, and Austria. Adherence to the intended breathing pattern was measured using a Pearson correlation coefficient. Momentary relaxation was measured pre- and post-exercise using an 11-point visual analog scale. Statistical analyses included linear mixed effects models and calculations of effect sizes. We further analyzed the relationship between session duration and the magnitude of momentary relaxation and compared Breeze’s efficacy and time efficiency to the other available techniques. Results: Of 279 participants, 118 (42.3%) used Breeze at least once. The 118 participants engaged in 754 breathing sessions with Breeze. Momentary relaxation was assessed and calculated for 249 (33.0%) Breeze sessions. The use of Breeze declined initially but remained stable even after 10 weeks. Participants followed the predefined breathing rates of Breeze (r=0.9). On average, a small effect (−0.42; P<.001; d=0.19) on momentary relaxation was observed, with 2-minute breathing sessions (−0.30; P=.02; d=0.13) showing a small effect, whereas a large effect (−1.53; P=.03; d=0.74) was observed for breathing sessions of 4 minutes or longer. Conclusions: This study demonstrates the potential of Breeze to alleviate acute stress in individuals with chronic conditions, such as cancer. By combining gamification with evidence-based breathing techniques, Breeze fosters sustained user engagement and momentary relaxation. Participants adhered well to the guided breathing. While even short breathing sessions of 2 minutes provided modest momentary relaxation, longer durations (≥4 min) were considerably more effective. Future research aims to assess the impact of Breeze on other populations and chronic conditions.
  • Breathing as an Input Modality in a Gameful Breathing Training App (Breeze 2): Development and Evaluation Study
    Item type: Journal Article
    Lukic, Yanick Xavier; Teepe, Gisbert Wilhelm; Fleisch, Elgar; et al. (2022)
    JMIR Serious Games
    Background: Slow-paced breathing training can have positive effects on physiological and psychological well-being. Unfortunately, use statistics indicate that adherence to breathing training apps is low. Recent work suggests that gameful breathing training may help overcome this challenge. Objective: This study aimed to introduce and evaluate the gameful breathing training app Breeze 2 and its novel real-time breathing detection algorithm that enables the interactive components of the app. Methods: We developed the breathing detection algorithm by using deep transfer learning to detect inhalation, exhalation, and nonbreathing sounds (including silence). An additional heuristic prolongs detected exhalations to stabilize the algorithm’s predictions. We evaluated Breeze 2 with 30 participants (women: n=14, 47%; age: mean 29.77, SD 7.33 years). Participants performed breathing training with Breeze 2 in 2 sessions with and without headphones. They answered questions regarding user engagement (User Engagement Scale Short Form [UES-SF]), perceived effectiveness (PE), perceived relaxation effectiveness, and perceived breathing detection accuracy. We used Wilcoxon signed-rank tests to compare the UES-SF, PE, and perceived relaxation effectiveness scores with neutral scores. Furthermore, we correlated perceived breathing detection accuracy with actual multi-class balanced accuracy to determine whether participants could perceive the actual breathing detection performance. We also conducted a repeated-measure ANOVA to investigate breathing detection differences in balanced accuracy with and without the heuristic and when classifying data captured from headphones and smartphone microphones. The analysis controlled for potential between-subject effects of the participants’ sex. Results: Our results show scores that were significantly higher than neutral scores for the UES-SF (W=459; P<.001), PE (W=465; P<.001), and perceived relaxation effectiveness (W=358; P<.001). Perceived breathing detection accuracy correlated significantly with the actual multi-class balanced accuracy (r=0.51; P<.001). Furthermore, we found that the heuristic significantly improved the breathing detection balanced accuracy (F1,25=6.23; P=.02) and that detection performed better on data captured from smartphone microphones than than on data from headphones (F1,25=17.61; P<.001). We did not observe any significant between-subject effects of sex. Breathing detection without the heuristic reached a multi-class balanced accuracy of 74% on the collected audio recordings. Conclusions: Most participants (28/30, 93%) perceived Breeze 2 as engaging and effective. Furthermore, breathing detection worked well for most participants, as indicated by the perceived detection accuracy and actual detection accuracy. In future work, we aim to use the collected breathing sounds to improve breathing detection with regard to its stability and performance. We also plan to use Breeze 2 as an intervention tool in various studies targeting the prevention and management of noncommunicable diseases.
  • Leveraging Influencers to Reach and Engage Vulnerable Individuals With a Digital Health Intervention: Quasi-Experimental Field Study
    Item type: Journal Article
    Nißen, Marcia; Harperink, Samira; Joshi, Priyam; et al. (2025)
    Journal of Medical Internet Research
    Background: Noncommunicable diseases are the leading cause of death, present economic challenges to health care systems worldwide, and disproportionally affect vulnerable individuals with low socioeconomic status (SES). While digital health interventions (DHIs) offer scalable and cost-effective solutions to promote health literacy and encourage behavior change, key challenges concern how to effectively reach and engage vulnerable individuals. To this end, social media influencers provide a unique opportunity to reach millions, and lasting engagement can be ensured through the design of DHIs in a manner that specifically appeals to low-SES individuals through alignment with their social background. Objective: The objectives of this study were 2-fold: to assess the effectiveness of leveraging influencers to reach vulnerable individuals (as measured via app downloads per stream viewers) and evaluate how the design of a DHI can improve engagement among this group (as measured via completion of the intervention). Methods: This study used a cross-sectional, quasi-experimental field design to assess both (1) the effectiveness of influencers in reaching vulnerable individuals and (2) the impact of specific design elements—such as gamification and storytelling—on user engagement using a stress management DHI featuring a slow-paced breathing exercise. In total, 3 differently designed versions of this DHI were developed following a fractional factorial design (StressLess, Breeze, and TragicKingdom). Reach was calculated as the number of downloads per viewers per stream and influencer. Engagement with the DHI was measured via number of conversational turns and milestone and intervention completion rates. Participants’ SES and technology acceptance were evaluated through a postintervention survey. Descriptive statistics, chi-square tests, and ANOVAs were used to examine the effects of the DHI design on reach and engagement metrics. Results: The recruitment via 8 influencers (total streams=25; total viewers=12,667) generated 220 downloads. The average reach ratio across streams amounted to 16.2% (SD 15.5%), with significant differences between conditions (ꭓ22=8.0, P=.02; StressLess: 8.1%, SD 9.3%; Breeze: 14%, SD 10.5%; TragicKingdom: 28.4%, SD 17.6%). The intervention completion rate across all DHI versions amounted to 7.7% (17/220), with no significant differences between conditions (P=.48). Conclusions: This work provides the first evidence that recruitment via influencers yields high reach ratios, moving far beyond the reach of traditional social media platforms. Nonetheless, based on the data collected, the ability to leverage such platforms to recruit vulnerable individuals remains unclear. In addition, while engagement with the promoted interventions was initially high, the completion rate of the full breathing exercise was comparably low, indicating that the influencer promotion strategy cannot fully overcome the well-documented adherence barriers in digital health.
  • Leveraging Influencers to Reach and Engage Vulnerable Individuals: A Quasi-Experimental Field Study with a Digital Health Intervention (Preprint)
    Item type: Working Paper
    Nißen, Marcia; Harperink, Samira; Joshi, Priyam; et al. (2025)
    JMIR Preprints
    Background: Non-communicable diseases (NCDs) are the leading cause of death, present economic challenges to healthcare systems worldwide, and disproportionally affect vulnerable individuals of low socioeconomic status (SES). While digital health interventions (DHIs) offer scalable and cost-effective solutions to promote health literacy and encourage behavior change, key challenges concern how to effectively (a) REACH and (b) ENGAGE vulnerable individuals. To this end, (a) social media influencers provide a unique opportunity to reach millions; and (b), ensure lasting engagement by designing DHIs in a manner that specifically appeals to low SES individuals through alignment with their social background. Objective: The objectives of this study are twofold: To assess the effectiveness of leveraging influencers to reach vulnerable individuals (as measured via app downloads per stream viewers) and to evaluate how the design of a DHI can improve engagement among this group (as measured via completion of intervention). Methods: This study utilized a cross-sectional, quasi-experimental field design to assess both (a) the effectiveness of influencers reaching vulnerable individuals and (b) the impact of specific design elements—such as gamification and storytelling—on user engagement with a stress-management DHI featuring a slow-paced breathing exercise. Three differently designed versions of this DHI were developed following a fractional factorial design (i.e., STRESSLESS, BREEZE, and TRAGICKINGDOM). Reach was calculated as the number of downloads per viewers per stream and influencer. Engagement with the DHI was measured via number of conversational turns, and milestone and intervention completion rates. Participants' SES and technology acceptance were evaluated through a post-intervention survey. Descriptive statistics, ꭓ2-tests, and ANOVAs were used to examine effects of the DHI design on reach and engagement metrics. Results: The recruitment via eight influencers (Total Streams = 25; Total Viewers = 12,667) generated 220 downloads. The average reach ratio across streams amounted to 16.2%, with significant differences between conditions, ꭓ2(2) = 8.04, p = .018: STRESSLESS: 8.1%; BREEZE: 14.0%; TRAGICKINGDOM: 28.4%. The intervention completion rate across all DHI versions amounted to 7.7% (17 out of 220), with no significant differences between conditions. Conclusions: This work provides first evidence that recruitment via influencers yields high reach ratios, moving far beyond the reach of traditional social media platforms. Nonetheless, based on the data collected, the ability to leverage such platforms to recruit and engage vulnerable individuals with DHIs remains unclear. Additionally, while engagement with the promoted interventions was initially high, completion rate of the full breathing exercise was comparably low, indicating that influencer promotion strategy cannot fully overcome the well-documented adherence barriers in digital health.
  • The Impact of a Gameful Breathing Training Visualization on Intrinsic Experiential Value, Perceived Effectiveness, and Engagement Intentions: Between-Subject Online Experiment
    Item type: Journal Article
    Lukic, Yanick Xavier; Klein, Shari Shirin; Brügger, Victoria; et al. (2021)
    JMIR Serious Games
    Background: Slow-paced breathing has been shown to be positively associated with psychological and physiological health. In practice, however, there is little long-term engagement with breathing training, as shown by the usage statistics of breathing training apps. New research suggests that gameful smartphone-delivered breathing training may address this challenge. Objective: This study assesses the impact of breathing training, guided by a gameful visualization, on perceived experiential and instrumental values and the intention to engage in such training. Methods: A between-subject online experiment with 170 participants was conducted, and one-way multiple analysis of variance and two-tailed t test analyses were used to test for any difference in intrinsic experiential value, perceived effectiveness, and the intention to engage in either a breathing training with a gameful or a nongameful guidance visualization. Moreover, prior experience in gaming and meditation practices were assessed as moderator variables for a preliminary analysis. Results: The intrinsic experiential value for the gameful visualization was found to be significantly higher compared to the nongameful visualization (P=.001), but there was no difference in either perceived effectiveness (P=.50) or the intention to engage (P=.44). The preliminary analysis of the influence of meditation and gaming experience on the outcomes indicates that people with more meditation experience yielded higher intrinsic experiential values from using the gameful visualization than people with no or little meditation experience (P=.03). This analysis did not find any additional evidence of gaming time or meditation experience impacting the outcomes. Conclusions: The gameful visualization was found to increase the intrinsic experiential value of the breathing training without decreasing the perceived effectiveness. However, there were no differences in intentions to engage in both breathing training conditions. Furthermore, gaming and meditation experiences seem to have no or only a small positive moderating effect on the relationship between the gameful visualization and the intrinsic experiential value. Future longitudinal field studies are required to assess the impact of gameful breathing training on actual behavior, that is, long-term engagement and outcomes.
  • Breeze, ein spielerisches Biofeedback Atemtraining für das Smartphone: Physiologische Reaktionen und subjektive Einschätzungen aus einem Labor- und Online-Experiment
    Item type: Other Conference Item
    Lukic, Yanick Xavier; Klein, Shari; Shih, Iris; et al. (2021)
    Hintergrund: Langsames Atmen hat eine positive Wirkung auf die Herzfunktion und auf das psychische Wohlbefinden. Daher werden entsprechende Atemübungen oft bei chronischen Krankheiten empfohlen; sie werden allerdings aus verschiedenen Gründen nur von bestimmten Personengruppen ausgeübt und haben somit eine eingeschränkte Reichweite und Wirkung. Ziel: Die Breeze App verfolgt das Ziel, die Reichweite von Atemübungen mit einem spielerischen und skalierbaren Biofeedback-Ansatz zu erhöhen. Methode: Grundlage der Atemübung Breeze ist die Erkennung der Atmung mit dem Mikrofon des Smartphones, um damit beim Ausatmen «Rückenwind» für ein virtuelles Segelboot zu erzeugen und es somit zu beschleunigen. Entspricht der Atmungs-Zyklus einem validierten Muster (z.B. 4s Einatmung, 2s Ausatmung und 4s Pause), kann mit dem Segelboot, welches in Echtzeit auf dem Bildschirm des Smartphones dargestellt wird, die grösste Reisedistanz zurückgelegt werden. Es wurden Labor- und Online-Experimente durchgeführt, um Breeze hinsichtlich physiologischer Effekte und subjektiver Einschätzungen bei erwachsenen Personen zu evaluieren. Ergebnisse: Im Labor (N=16) konnte gezeigt werden, dass Breeze nicht nur zu einer Steigerung der Herzfrequenzvariabilität geführt hat (p<.001), sondern auch gegenüber einer validierten Atemübung ohne spielerischen Ansatz von 14 (87.5%) Personen präferiert wurde. Ein Online-Experiment mit Teilnehmenden, welche im Schnitt nur wenig bis gar keine Erfahrung mit Atemübungen hatten, zeigte darüber hinaus, dass die wahrgenommene Entspannung durch Breeze (N=88) mit der einer validierten Atemübung (N=82) vergleichbar ist und 51 (58.0%) Personen Breeze im Alltag nutzen würden. Zusammenfassung: Breeze hat mit seinem spielerischen Ansatz das Potential, die Reichweite von Atemübungen zu erhöhen, was insbesondere für das Selbstmanagement bei chronischen Krankheiten relevant sein kann.
  • Just Breathe: Harnessing Pretrained Audio Models for Mood Awareness in a Gamified Breathing Training App
    Item type: Conference Paper
    Shenoi, Akshaye; Teepe, Gisbert W.; Lukic, Yanick Xavier; et al. (2025)
    Proceedings of CHI '25 Workshop on Envisioning the Future of Interactive Health
    Mood disorders can significantly impair an individual’s ability to function in daily life. One common symptom observed in early stages of several mood disorders is Agitation. Early detection and regulation of agitation can thus help prevent the progression of severe mood disorders. Digital Health Interventions such as guided slow-paced breathing apps have demonstrated their efficacy in reducing agitation. How-ever, such interventions are often hindered by poor adherence in the long term. We hypothesize that an awareness of the individual’s current mood states would allow for a more personalized intervention (e.g., adaptive session duration), thereby improving adherence. In this paper, we explore the feasibility of predicting real-time agitation in an individual as they engage with a gamified biofeedback-based breath-ing training app Breeze. In a controlled lab experiment (𝑛 = 30), we collect voice and breathing samples from Breeze alongside self-reports of perceived agitation. Two pretrained audio models, VGGish and OPERA, are used to extract feature embeddings from raw audio signals, and downstream classifiers are subsequently trained to predict agitation levels. Initial results show that (1) respiratory audio is indeed a reliable predictor of agitation, and (2) pretrained models are capable of extracting meaningful features from respiratory audio. Our findings lay the technical groundwork to further investigate and evaluate the effect of mood-aware personalization strategies to improve user adherence, and ultimately, lead to better mental health outcomes.
Publications1 - 10 of 15