Impact of an Artificial Intelligence-Based Management Model on Psychological and Behavioral Outcomes in Breast Cancer Patients Undergoing Home CDK4/6 Inhibitor Therapy

Impact of an Artificial Intelligence-Based Management Model on Psychological and Behavioral Outcomes in Breast Cancer Patients Undergoing Home CDK4/6 Inhibitor Therapy: A Multicenter Randomized Controlled Trial

This version uses full terminology and flows well for a research proposal or paper.

Primary Objective: To compare the intervention effects of an "AI-based management model," a "customized active follow-up model," and a "conventional patient education and follow-up model" on anxiety and depression in patients.

Secondary Objectives: To evaluate the impact of these models on patients' quality of life (QoL), patient-reported adverse events, medication adherence, serological markers, progression-free survival (PFS), and overall survival (OS).

Study Overview

• Status: Enrolling by invitation
• Conditions: Breast Cancer; Depression Anxiety Disorder; CDK4/6 Inhibitors
• Intervention / Treatment: Device: The "Zhiliao Doctor" AI management platform; Behavioral: Tailored Active Follow-up Strategy

• Study Type: Interventional
• Enrollment (Estimated): 300
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Tianjin, China, 300000
    • Tianjin Medical University Cancer Institute & Hospital

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

• Females aged ≥ 18 years, regardless of menopausal status.
• Diagnosis of HR+/HER2- breast cancer.
• Currently receiving or scheduled to receive CDK4/6 inhibitor therapy.
• Eastern Cooperative Oncology Group (ECOG) performance status of 0-2.
• No history of severe psychiatric disorders (e.g., bipolar disorder, schizophrenia).
• Baseline psychological state sufficient to understand and participate in psychological interventions.
• Currently engaged in a rehabilitation plan, including exercise therapy and physical therapy.
• Willingness to provide written informed consent.
• Capability to perform online operations via smartphone or computer.

Exclusion Criteria:

• Severe complications (e.g., heart disease, severe hepatic or renal dysfunction) that render the patient unable to tolerate CDK4/6i therapy.
• History of severe psychiatric illness (e.g., severe depression, bipolar disorder, or schizophrenia) that precludes self-assessment.
• Other malignant tumors within the past 5 years (excluding specific cured carcinomas).
• Pregnant or breastfeeding women.
• Positive baseline pregnancy test for women of childbearing potential.
• Inability to adapt to or intolerance of the AI virtual doctor's intervention formats.
• Any other condition that the investigator deems unsuitable for participation in the study.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Group A: AI-integrated Care Mode; On the basis of routine follow-up, the 'Zhiliao Doctor' AI management platform is utilized to provide intelligent services, including emotional companionship, medication reminders, and adverse reaction assessment and guidance.	Device: The "Zhiliao Doctor" AI management platform; Participants in Group A will receive standard clinical care supplemented by the 'Zhiliao Doctor' AI management platform. This 24/7 intelligent platform provides emotional companionship, medication reminders, and adverse reaction assessment based on CTCAE standards to enhance self-management and quality of life.
Experimental: Group B: Tailored Active Follow-up Strategy; Receiving personalized active follow-up services, such as phone calls and text messages, provided by the follow-up center.	Behavioral: Tailored Active Follow-up Strategy; Participants receive tailored active follow-up, including personalized phone calls and SMS messages, managed by a professional follow-up center.
No Intervention: Group C: Standard Patient Education and Follow-up; Patients receive routine medical advice and patient education.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Depression	Depression is evaluated using the Self-rating Depression Scale (SDS). The SDS consists of 20 items, with each item scored on a 4-point scale ranging from 1 to 4. The raw total score is calculated by summing the scores of all items and is then converted into a standard score. The cutoff value for the standard score is set at 50. Higher scores indicate a greater severity of depression.	24weeks
anxiety	Anxiety is evaluated using the Self-rating Anxiety Scale (SAS). The scale consists of 20 items, with each item scored on a 4-point scale ranging from 1 to 4. The raw total score is obtained by summing the scores of all individual items and is subsequently converted into a standard score. The threshold for the standard score is 50. Higher scores reflect a greater severity of anxiety.	24weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Quality of Life (QoL)	The EORTC QLQ-C30 consists of five functional scales (physical, role, cognitive, emotional, and social), a global QoL scale, three symptom scales (fatigue, nausea and vomiting, and pain), single items assessing common symptoms (dyspnoea, loss of appetite, insomnia, constipation, and diarrhoea), and a single item assessing the perceived financial impact. After linear transformation, all scales and single-item measures range in score from 0 to 100. A higher score for a functional scale and the global QoL scale represents a higher level of functioning and a higher level of HRQoL. Conversely, a higher score for a symptom scale or item and the financial impact item indicates a higher level of symptom burden or financial impact.	24weeks
PRO-CTCAE	The PRO-CTCAE is a validated library of patient-reported items designed to measure 78 distinct symptomatic adverse events (AEs). For each AE, up to three separate attribute items assess the frequency, severity, and interference with daily activities over the past 7 days. Scores for each attribute can be reported individually or integrated into a single composite score ranging from 0 to 3 for each symptom using established algorithms. Higher individual or composite scores indicate greater symptom severity. Relevant PRO-CTCAE items are typically selected for a specific clinical trial based on prior evidence and/or the mechanism of action, and then compiled into a survey. In this trial, investigators selected 10 PRO-CTCAE symptoms based on CDK4/6 inhibitor-related side effects reported in the literature. The selected symptoms include: decreased appetite, nausea, constipation, diarrhea, dizziness, pain, insomnia, fatigue, dejection, and sadness.	24weeks
Medication Adherence	This study utilizes the Proportion of Days Covered (PDC) as a quantitative indicator of medication adherence. The formula is as follows: PDC = Number of days covered by medication during the observation period/Total number of days in the observation period× 100%.In this study, "high adherence" is defined as a PDC≥80%.	24weeks
Overall Survival(OS)		2years
Progression-Free Survival (PFS)		2years

Collaborators and Investigators

• Sponsor: Tianjin Medical University Cancer Institute and Hospital
• Collaborators: Tianjin Medical University General Hospital; Tianjin Third Central Hospital; Tianjin Medical University Second Hospital; Tianjin First Central Hospital; Tianjin People's Hospital; Tianjin Fifth Central Hospital; First Affiliated Hospital of Tianjin University of Traditional Chinese Medicine

Study record dates

Study Major Dates

• Study Start (Actual): July 5, 2025
• Primary Completion (Estimated): May 24, 2026
• Study Completion (Estimated): May 30, 2026

Study Registration Dates

• First Submitted: January 20, 2026
• First Submitted That Met QC Criteria: February 6, 2026
• First Posted (Actual): February 13, 2026

Study Record Updates

• Last Update Posted (Actual): February 13, 2026
• Last Update Submitted That Met QC Criteria: February 6, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Keywords: Psychological Intervention; AI-based Management Model; Customized Follow-up Mode
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Skin Diseases; Breast Diseases; Skin and Connective Tissue Diseases; Breast Neoplasms
• Other Study ID Numbers: E20251024

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: Individual participant data (IPD) will not be shared primarily because the study involves highly sensitive psychological assessments (e.g., SAS and SDS scores) and detailed interaction logs with the "Zhiliao Doctor" AI platform; such unstructured data pose significant de-identification challenges and potential privacy risks. Additionally, the current institutional review board (IRB) approval and the informed consent forms signed by participants do not include provisions for the public sharing of individual-level raw data. Furthermore, as a multicenter study involving serological markers, data sharing is strictly limited by inter-institutional agreements, intellectual property protections, and national regulatory requirements for the management of human genetic resource data.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No