Clinical nurses are frequently exposed to high emotional demands due to heavy workloads, time pressure, patient suffering, and the interpersonal complexity of clinical care. These stressors may contribute to compassion fatigue, burnout, reduced resilience, and decreased occupational well-being. However, timely and accessible psychological support is often limited in busy clinical environments, and many nurses may hesitate to seek help due to stigma, time constraints, or limited resources. This study is a prospective, randomized, controlled, parallel-group interventional trial designed to evaluate the feasibility and effectiveness of an on-demand, human-centered emotional support intervention delivered through a LINE-based GPT assistant. The AI assistant provides real-time supportive conversations, reflective prompts, stress-coping guidance, and resilience-enhancing strategies tailored specifically for clinical nurses, offering a private and easily accessible support resource. Eligible clinical nurses (target sample size: 100-120) are randomly assigned to either an Intervention Group, which interacts with the AI assistant, or a Control Group, which receives non-interactive static messages, over a four-week intervention period. Primary outcomes include changes in compassion fatigue, burnout, and compassion satisfaction, as measured by the Professional Quality of Life Scale (ProQOL). Secondary outcomes include changes in resilience (Brief Resilience Scale), general self-efficacy (General Self-Efficacy Scale), and perceived stress (Perceived Stress Scale-10). The results of this study are expected to provide evidence on the feasibility and potential effectiveness of AI-based emotional support as a scalable and accessible tool to promote psychological well-being among clinical nurses, thereby informing future digital mental health interventions in healthcare settings.
1\. Study Design and Randomization MechanismThis study utilizes a Pre-Post Parallel Intervention Design. To enhance internal validity, minimize selection bias, and account for unit-level characteristics, a Stratified Cluster Randomization approach is employed. Clinical units are stratified into three tiers based on assessed work intensity: High Intensity (e.g., ICUs and ED), Medium Intensity (e.g., medical and surgical wards), and Low Intensity (e.g., psychiatric and rehabilitation wards). Within each stratum, the nursing unit or ward serves as the cluster. Clusters are then randomly assigned (1:1 ratio) to either the Intervention Group or the Control Group, ensuring that all nurses within a single unit belong to the same study arm. The planned total sample size is N=120, distributed across approximately 18 clusters.2. Intervention Protocol (4-Week Period)The intervention period spans four weeks (28 days). The core tool is a customized GPT dialogue model integrated with the LINE Official Account (LINE OA) platform, widely used by the target population.Intervention Group (Interactive AI Support)Participants receive a two-part daily intervention: a daily push message and access to a two-way AI interaction. They are encouraged to actively engage in free-form psychological support dialogue with the LINE GPT assistant. The AI's response logic is rigorously defined via Prompt Engineering to focus on clinical work stress, emotional coping, and resilience-promoting strategies. Crucially, the AI is programmed with ethical guardrails to gently redirect users back to the clinical stress axis if they deviate to non-work related or sensitive topics, and strictly prohibit the provision of any medical, diagnostic, or therapeutic advice.Control Group (Static Message Control)Participants in the control group receive daily static text messages. The content themes are identical to the push messages received by the intervention group, but the channel lacks any interactive AI response capability.3. Study Procedures and Data Collection TimelineThe entire study spans a minimum of six weeks, structured into three distinct phases.The process begins in Weeks 1-2 with recruitment and baseline assessment. Following informed consent, participants are oriented to the study platform (LINE OA) and complete the Pre-Test Questionnaire. This baseline assessment, which takes approximately 25-30 minutes, captures all demographic/occupational variables and the initial scores for all primary and secondary outcome scales (ProQOL, GSE, PSS-10, BRS).Immediately following baseline assessment, the 4-week intervention period commences, spanning from approximately Week 3 through Week 6. Throughout this period, both the intervention and control groups receive their respective daily messages. To track subjective engagement and experience, all participants are required to complete a brief "AI Use Feedback Simple Form" weekly, which takes approximately 5 minutes.Upon completion of the four weeks, the study enters the Post-Test phase at the end of Week 6. All participants complete the same battery of outcome scales (re-measurement of ProQOL, GSE, PSS-10, BRS) and the AI Use Satisfaction Questionnaire. The Intervention Group is additionally requested to complete an Open-ended Feedback Questionnaire to provide rich qualitative data on their experience with the GPT assistant.4. Statistical Analysis PlanData will be anonymized using unique study IDs prior to analysis. Due to the stratified cluster randomization, the analysis will employ methods suitable for clustered data structures to account for Intracluster Correlation (ICC). The Primary Analysis will utilize Generalized Estimating Equations (GEE) to model the change in outcomes over time, specifically testing the "Time $\\times$ Group" interaction to assess the intervention effect. The nursing unit/ward will be specified as the cluster variable in the GEE model. Linear Mixed-Effects Models (LMM) may be used for supplementary or sensitivity analysis. Covariates such as nursing tenure and baseline stress levels will be included in the models for adjustment and exploratory analysis. Qualitative data from the open-ended feedback will be analyzed using Content Analysis to categorize emerging themes.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
SUPPORTIVE_CARE
Masking
NONE
Enrollment
120
Participants receive daily interactive emotional support messages delivered through a LINE-based GPT assistant. The AI system provides two-way conversations, reflective prompts, and coping suggestions related to work stress and emotional well-being. The intervention is available on demand throughout the 4-week study period.
Participants receive daily non-interactive supportive messages via LINE. Message themes match those in the intervention arm (e.g., stress awareness, emotional well-being) but contain no AI-generated responses or interactive components. Participants receive one static message per day for 4 weeks.
Change in Compassion Fatigue, Burnout, and Compassion Satisfaction (ProQOL)
Compassion fatigue, burnout, and compassion satisfaction will be assessed using the Professional Quality of Life Scale (ProQOL), a validated self-report instrument consisting of three subscales: Compassion Fatigue, Burnout, and Compassion Satisfaction. Each subscale score ranges from 10 to 50. Higher scores on the Compassion Fatigue and Burnout subscales indicate worse outcomes. Higher scores on the Compassion Satisfaction subscale indicate better outcomes. Scores will be collected at baseline and at the end of the 4-week intervention period to evaluate changes associated with the AI emotional support intervention compared with the control condition.
Time frame: Baseline and Week 4
Change in Resilience (Brief Resilience Scale, BRS)
Resilience will be measured using the Brief Resilience Scale (BRS), a 6-item self-report scale assessing the ability to recover from stress. Total scores range from 1 to 5, calculated as the mean of item responses. Higher scores indicate greater resilience and better outcomes. BRS scores will be collected at baseline and at Week 4 to assess changes in resilience between the intervention and control groups.
Time frame: Baseline and Week 4
Change in General Self-Efficacy (GSE)
General self-efficacy will be assessed using the General Self-Efficacy Scale (GSE), a 10-item self-report measure evaluating perceived ability to cope with challenging situations. Total scores range from 10 to 40. Higher scores indicate greater self-efficacy and better outcomes. Scores will be measured at baseline and at Week 4 to determine the effect of the AI emotional support intervention on self-efficacy.
Time frame: Baseline and Week 4
Change in Perceived Stress (PSS-10)
Perceived stress will be evaluated using the 10-item Perceived Stress Scale (PSS-10), which measures the degree to which situations in life are appraised as stressful. Total scores range from 0 to 40. Higher scores indicate higher perceived stress and worse outcomes. PSS-10 scores will be collected at baseline and at Week 4 to compare changes in perceived stress between study groups.
Time frame: Baseline and Week 4
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.