Efficacy of a large language model-driven application for emotion management in breast cancer patients (EMBRACE): protocol for a multicentre randomised controlled trial
8 affiliations
- 1Nanfang Hospital, Southern Medical University, Guangzhou, China
- 2School of Nursing, Southern Medical University, Guangzhou, China
- 3State Key Laboratory of Multi-Organ Injury Prevention and Treatment, Department of Biostatistics, School of Public Health, Southern Medical University, Guangzhou, China
- 4The First Affiliated Hospital of Army Medical University, Chongqing, China
- 5Affiliated Hospital of Guangdong Medical University, Zhanjiang, China
- 6The Second Nanning People’s Hospital, Nanning, Guangxi, China
- 7Zigong First People's Hospital, Zigong, Sichuan, China
- 8The Affiliated Huizhou Hospital, Guangzhou Medical University, Huizhou, China
Abstract
Introduction: In breast cancer, psychological distress predicts poorer quality of life, adherence and clinical outcomes. Most digital psychosocial interventions rely on static content and infrequent monitoring, missing patients’ evolving emotional states. Therefore, a key clinical challenge is the timely identification of these emotional fluctuations and the tailoring of interventions accordingly. We have developed a large language model (LLM)-enabled emotion management system, whose core methodological innovation lies in leveraging patient-generated text from social media platforms as the primary analytical source to deliver guideline-aligned personalised supportive interventions for patients. The study aims to establish whether this intervention improves health-related quality of life (HRQoL), psychological outcomes, symptom burden while reducing unplanned hospitalisations in patients with breast cancer.
Methods and analysis: This prospective stratified block randomised controlled trial targets a total sample of 440 eligible patients with breast cancer with 1:1 allocation, recruited from six tertiary hospitals stratified by regional economic levels. Eligibility criteria include histologically confirmed primary breast cancer, smartphone access and regular social media use; those with cognitive impairment, concurrent malignancies or active suicidal ideation are excluded. The intervention group receives usual care plus an LLM-based emotion management system that analyses patient text to generate personalised emotion labels and match symptom keywords, then provides tailored evidence-based interventions. The control group receives usual care. Assessments are conducted at baseline, 1, 3 and 6 months. The primary outcome is HRQoL assessed using the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire-Core 30 (EORTC QLQ-C30) summary score, with the primary endpoint defined as the 6-month assessment after randomisation; secondary outcomes cover individual HRQoL domains of the EORTC QLQ-C30 to examine effects on function and symptom status, anxiety (Generalised Anxiety Disorder-7), depression (Patient Health Questionnaire-9), symptom burden (Memorial Symptom Assessment Scale), rate of unplanned hospitalisation and time to first unplanned hospitalisation.
Ethics and dissemination: This trial is conducted in accordance with the principles of the Declaration of Helsinki and the International Council for Harmonisation Guidelines for Good Clinical Practice. Ethical approval was obtained from the ethics committees of 6 hospitals. Written informed consent was collected from all participants before enrolment. Participants can withdraw freely at any time without prejudice to routine clinical care. Trial results will be submitted for publication in peer-reviewed journals.
Trial registration number: NCT07452055.
Related
- A randomised, double-blind, multicentre, placebo-controlled phase 3 efficacy, safety, and immunogenicity study of an Ad26.RSV.preF/RSV prefusion F-protein vaccine for the prevention of respiratory syncytial virus-mediated lower respiratory tract disease in adults aged 60 years and older
- Evaluation of percutaneous cryoneurotomy compared with surgical open neurotomy for the management of post-stroke spastic equinovarus foot in France: protocol for a multicentre, randomised controlled, open-label, non-inferiority trial
- AI-Powered CURA Application for Identifying At-Risk Pregnancies in Obstetrics Management (CURAte): protocol for a randomised controlled trial.
- Multicentre randomised controlled trial to evaluate the efficacy of DIALIVE 2.0, a liver dialysis device, for the treatment of acute-on-chronic liver failure: study protocol
- Efficacy and safety of double plasma cytokine adsorption system with sequential low-volume plasma exchange in treating acute-on-chronic liver failure complicated by sepsis: protocol for a multicentre randomised controlled clinical trial
BibTeX
@article{luo2026efficacy,
title = {{Efficacy of a large language model-driven application for emotion management in breast cancer patients (EMBRACE): protocol for a multicentre randomised controlled trial}},
author = {Meiqin Luo and Chongyang Duan and Wenji Li and Ying Yang and Hongpo Xie and Hua Lin and Changju Liao and Linzhi Li and Huihui Zhao and Chaixiu Li and Xiaoting Tan and Xiaoxue Wei and Xiaorong Bian and Huan Liu and Yinghua Zeng and Hui Yang and Yinhuan Wang and Di Lin and Xin Liu and Xiaoli Gan and Yu Sun and Qiuyan Ren and Yan He and Jiale Sun and Yanni Wu},
journal = {BMJ Open},
year = {2026},
month = oct,
doi = {10.1136/bmjopen-2026-126107},
url = {https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2026-126107},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Efficacy of a large language model-driven application for emotion management in breast cancer patients (EMBRACE): protocol for a multicentre randomised controlled trial
AU - Meiqin Luo
AU - Chongyang Duan
AU - Wenji Li
AU - Ying Yang
AU - Hongpo Xie
AU - Hua Lin
AU - Changju Liao
AU - Linzhi Li
AU - Huihui Zhao
AU - Chaixiu Li
AU - Xiaoting Tan
AU - Xiaoxue Wei
AU - Xiaorong Bian
AU - Huan Liu
AU - Yinghua Zeng
AU - Hui Yang
AU - Yinhuan Wang
AU - Di Lin
AU - Xin Liu
AU - Xiaoli Gan
AU - Yu Sun
AU - Qiuyan Ren
AU - Yan He
AU - Jiale Sun
AU - Yanni Wu
PY - 2026
DA - 2026/10/28
JO - BMJ Open
DO - 10.1136/bmjopen-2026-126107
UR - https://bmjopen.bmj.com/lookup/doi/10.1136/bmjopen-2026-126107
AB - Introduction: In breast cancer, psychological distress predicts poorer quality of life, adherence and clinical outcomes. Most digital psychosocial interventions rely on static content and infrequent monitoring, missing patients’ evolving emotional states. Therefore, a key clinical challenge is the timely identification of these emotional fluctuations and the tailoring of interventions accordingly. We have developed a large language model (LLM)-enabled emotion management system, whose core methodological innovation lies in leveraging patient-generated text from social media platforms as the primary analytical source to deliver guideline-aligned personalised supportive interventions for patients. The study aims to establish whether this intervention improves health-related quality of life (HRQoL), psychological outcomes, symptom burden while reducing unplanned hospitalisations in patients with breast cancer. Methods and analysis: This prospective stratified block randomised controlled trial targets a total sample of 440 eligible patients with breast cancer with 1:1 allocation, recruited from six tertiary hospitals stratified by regional economic levels. Eligibility criteria include histologically confirmed primary breast cancer, smartphone access and regular social media use; those with cognitive impairment, concurrent malignancies or active suicidal ideation are excluded. The intervention group receives usual care plus an LLM-based emotion management system that analyses patient text to generate personalised emotion labels and match symptom keywords, then provides tailored evidence-based interventions. The control group receives usual care. Assessments are conducted at baseline, 1, 3 and 6 months. The primary outcome is HRQoL assessed using the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire-Core 30 (EORTC QLQ-C30) summary score, with the primary endpoint defined as the 6-month assessment after randomisation; secondary outcomes cover individual HRQoL domains of the EORTC QLQ-C30 to examine effects on function and symptom status, anxiety (Generalised Anxiety Disorder-7), depression (Patient Health Questionnaire-9), symptom burden (Memorial Symptom Assessment Scale), rate of unplanned hospitalisation and time to first unplanned hospitalisation. Ethics and dissemination: This trial is conducted in accordance with the principles of the Declaration of Helsinki and the International Council for Harmonisation Guidelines for Good Clinical Practice. Ethical approval was obtained from the ethics committees of 6 hospitals. Written informed consent was collected from all participants before enrolment. Participants can withdraw freely at any time without prejudice to routine clinical care. Trial results will be submitted for publication in peer-reviewed journals. Trial registration number: NCT07452055.
SN - 2044-6055
SN - 2044-6055
ER -