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.
Adults aged 20 to 65 years.
Currently employed as clinical nursing staff in the participating institution, including inpatient wards or intensive care units.
Able to read Traditional Chinese and receive daily messages via LINE or Email.
Willing to participate and able to provide written informed consent.
Refusal or inability to provide informed consent.
Unable to receive daily messages through LINE or Email (e.g., no smartphone or internet access).
Currently undergoing psychiatric treatment or in the acute phase of major physical/mental illness, where participation may interfere with clinical care.
Cognitive or communication impairments that prevent understanding of study material or completion of questionnaires.
Parallel
Interactive LINE GPT Emotional Support
BehavioralParticipants 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.
Static Supportive Messages
BehavioralParticipants 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.
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.
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.
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.
AI Engagement Metrics (Message Frequency and Interaction Patterns)
AI engagement will be assessed using system-generated usage data from the LINE platform, including message frequency, interaction patterns, and response behaviors. These metrics are used to evaluate intervention feasibility and participant engagement and are not considered clinical or psychological outcome measures.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
