Research on the Development and Validation of Personalized Exercise Prescriptions for Breast Cancer Patients Based on Large Language Models

The goal of this observational study is to develop and evaluate a large language model (LLM)-based decision support system for exercise prescription in breast cancer patients, aiming to provide personalized decision-making support for postoperative breast cancer rehabilitation.

The main questions it aims to answer are:

How accurate, personalized, and safe are the exercise prescriptions generated by the fine-tuned LLM? How does the model's performance compare with other mainstream or non-fine-tuned models across different stages and subtypes of breast cancer? Participants are postoperative breast cancer rehabilitation patients treated at Sun Yat-sen Memorial Hospital of Sun Yat-sen University. They will have demographic, tumor, treatment, and physical fitness data collected; receive personalized exercise prescriptions automatically generated by the LLM-based system; and provide subjective evaluations on the feasibility and executability of the prescriptions.

Study Overview

• Status: Active, not recruiting
• Conditions: Breast Cancer

• Study Type: Observational
• Enrollment (Estimated): 220

Contacts and Locations

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510000
      • Sun Yat-sen Memorial Hospital, Sun Yat-sen University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with breast cancer who have completed primary surgery and entered the postoperative rehabilitation stage at Sun Yat-sen Memorial Hospital, Sun Yat-sen University (Guangzhou, China).All participants receive individualized exercise prescriptions generated by large language models under physician supervision and approval, and their feedback on the feasibility of these prescriptions is collected.

Description

Inclusion Criteria:

• Adult patients aged 18-75 years with early-stage breast cancer who have undergone surgical treatment, such as mastectomy or breast-conserving surgery.
• ECOG performance status of 0-1, with adequate physical condition to participate in rehabilitation assessment and exercise prescription activities.
• Availability of essential clinical data, including demographic characteristics, tumor stage and subtype, treatment history, and baseline physical fitness assessment.
• Able to communicate effectively, maintain stable follow-up contact, and voluntarily participate in evaluation and feedback on exercise prescriptions.

Exclusion Criteria:

• Presence of severe postoperative complications or comorbidities (e.g., uncontrolled cardiac or pulmonary disease) that may interfere with participation in rehabilitation or pose a safety risk.
• Significant physical or mobility impairments preventing the performance of prescribed exercises.
• Severe psychiatric illness or cognitive dysfunction that hinders cooperation with assessments or follow-up.
• Incomplete or missing key clinical data, making evaluation or follow-up impossible.
• Any other condition deemed inappropriate for participation by the investigators.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Postoperative breast cancer patients receiving LLM-based exercise prescription evaluation; Postoperative breast cancer patients at Sun Yat-sen Memorial Hospital will have clinical and physical data collected. Each patient receives an exercise prescription generated by a fine-tuned large language model (LLM)-based decision support system and provides feedback on its feasibility.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
Average 5-point Likert scores across five expert-defined dimensions-individualization, comprehensiveness, scientific rationality, safety, and executability-are used to compare the performance of fine-tuned models with that of mid-level physicians.	From enrollment to completion of prescription evaluation at 1 week

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Evaluation Form for Consistency Between Model Diagnostic Logic and Medical Consensus	Measurement Method/Unit: A panel of expert reviewers (at least 3 senior physicians) conducts a blinded assessment of the model's diagnostic reasoning pathways in test cases using a dedicated evaluation form. The outcome is expressed as the mean score (points). Rating Scale: 5-point Likert scale (1=Highly Unsound, 5=Highly Sound) Interpretation of Scores: A higher score indicates better consistency of the model's diagnostic logic with established medical consensus.	From enrollment to completion of prescription evaluation at 1 week

Collaborators and Investigators

• Sponsor: Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

Study record dates

Study Major Dates

• Study Start (Actual): October 1, 2025
• Primary Completion (Estimated): September 1, 2026
• Study Completion (Estimated): July 1, 2027

Study Registration Dates

• First Submitted: November 25, 2025
• First Submitted That Met QC Criteria: June 1, 2026
• First Posted (Actual): June 2, 2026

Study Record Updates

• Last Update Posted (Actual): June 2, 2026
• Last Update Submitted That Met QC Criteria: June 1, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Skin Diseases; Breast Diseases; Skin and Connective Tissue Diseases; Breast Neoplasms
• Other Study ID Numbers: SYSKY-2025-786-01

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No