The purpose of this multicenter, open-label, randomized controlled trial is to evaluate whether patient-centered support delivered through a large language model (LLM)-based artificial intelligence (AI) agent reduces anxiety in patients with newly diagnosed metastatic hormone-sensitive prostate cancer (mHSPC). Participants access the AI agent through a WeChat Mini Program-based platform. The study will also assess the effects of this intervention on illness perception, sleep quality, and patient satisfaction. Participants will be randomly assigned in a 1:1 ratio to either the intervention group or the control group. Participants in the intervention group will have access to the AI agent-enabled patient support platform throughout the 4-week study period. Participants in the control group will use the same platform without access to the AI agent during the first 2 weeks and will then receive access to the AI agent for the subsequent 2 weeks. Both groups will receive standard-of-care medical treatment throughout the study. The primary objective is to compare changes from baseline in anxiety at 2 weeks between the two groups. Anxiety will be assessed using the Generalized Anxiety Disorder-7 (GAD-7) scale. Secondary outcomes include illness perception, sleep quality, and patient satisfaction. Exploratory outcomes include the change from baseline in the GAD-7 total score at 4 weeks and the accuracy of responses generated by the AI agent to participants' questions.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
SUPPORTIVE_CARE
Masking
NONE
Enrollment
160
The basic platform supports study registration, assessments, and usage tracking but does not provide AI agent function during the first 2 weeks.
Participants access the AI agent through a WeChat Mini Program. It provides clinician-reviewed educational materials on prostate cancer and disease management. A large language model-based AI agent provides real-time, multi-turn, personalized responses to participants' questions. Retrieval-augmented generation based on a curated clinical knowledge base is used to improve the accuracy and clinical relevance of the responses. The AI agent will not replace physician assessment, diagnosis, or treatment decision-making.
Participants will receive access of AI agent after completing the 2-week assessments. The AI agent is accessible through a WeChat Mini Program. It provides clinician-reviewed educational materials on prostate cancer and disease management. A large language model-based AI agent provides real-time, multi-turn, personalized responses to participants' questions. Retrieval-augmented generation based on a curated clinical knowledge base is used to improve the accuracy and clinical relevance of the responses. The AI agent will not replace physician assessment, diagnosis, or treatment decision-making.
Participants will continue to receive standard-of-care medical treatment for mHSPC throughout the study. Treatment may include androgen deprivation therapy (ADT) in combination with an androgen receptor pathway inhibitor (ARPi), and bone-protective agents may also be administered, as determined by the treating physician according to clinical guidelines and individual patient needs. However, radiotherapy, surgery, or chemotherapy in any form is not permitted during the study period. Non-antineoplastic medications taken prior to enrollment may be continued during the study.
Fujian Cancer Hospital
Fuzhou, Fujian, China
Fudan University Shanghai Cancer Center
Shanghai, Shanghai Municipality, China
Yunnan Cancer Hospital
Kunming, Yunnan, China
The First Affiliated Hospital of Wenzhou Medical University
Wenzhou, Zhejiang, China
Between-Group Difference in Change from Baseline in GAD-7 Total Score at 2 Weeks
The Generalized Anxiety Disorder-7 (GAD-7) scale assesses anxiety symptoms using 7 items, each scored from 0 to 3. The total score ranges from 0 to 21, with higher scores indicating greater anxiety severity. Change from baseline is calculated as the score at 2 weeks minus the baseline score, with a negative change indicating improvement. The mean change from baseline will be compared between the two groups.
Time frame: At baseline and 2 weeks after randomization.
Between-Group Difference in Disease Knowledge Test Total Score at 2 Weeks
The study-specific Disease Knowledge Test consists of 10 objective questions on mHSPC. Each correct answer is scored as 1, and each incorrect or unknown answer is scored as 0. The total score ranges from 0 to 10, with higher scores indicating greater disease knowledge. The mean total score at 2 weeks will be compared between the two groups.
Time frame: At 2 weeks after randomization.
Between-Group Difference in Change from Baseline in the Brief Illness Perception Questionnaire (B-IPQ) Total Score at 2 Weeks
The Brief Illness Perception Questionnaire (B-IPQ) assesses cognitive and emotional representations of illness. Eight scored items are rated from 0 to 10. After appropriate reverse scoring, the total score ranges from 0 to 80, with higher scores indicating a more threatening perception of the illness. Change from baseline is calculated as the score at 2 weeks minus the baseline score, with negative values indicating improvement. The mean change from baseline will be compared between the two groups.
Time frame: At baseline and 2 weeks after randomization.
Between-Group Difference in Change from Baseline in the Insomnia Severity Index (ISI) Total Score at 2 Weeks
The Insomnia Severity Index (ISI) assesses insomnia severity using 7 items, each scored from 0 to 4. The total score ranges from 0 to 28, with higher scores indicating greater insomnia severity. Change from baseline is calculated as the score at 2 weeks minus the baseline score, with negative values indicating improvement. The mean change from baseline will be compared between the two groups.
Time frame: At baseline and 2 weeks after randomization.
Between-Group Difference in Change from Baseline in the Patient Satisfaction Questionnaire-18 (PSQ-18) Score at 2 Weeks
The Patient Satisfaction Questionnaire-18 (PSQ-18) consists of 18 items assessing satisfaction with medical care across seven domains. Each item is scored from 1 to 5. After appropriate reverse scoring, the item scores are summed to produce a total score ranging from 18 to 90, with higher scores indicating greater patient satisfaction. Change from baseline is calculated as the score at 2 weeks minus the baseline score, with positive values indicating improvement. The mean change from baseline will be compared between the two groups.
Time frame: At baseline and 2 weeks after randomization.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.