AI-Assisted Chemotherapy Side Effect Management

NCT07198581 | Recruiting

• 1 other identifier: ALLIANCE
• Study Type: interventional
• Target: 174
• Locations: 1 country
• Sites: 1

Brief Summary

This two-stage adaptive randomized controlled trial evaluates the feasibility and preliminary efficacy of large language model (LLM)-assisted intervention for managing chemotherapy side effects in patients with solid tumors. Adults with histologically confirmed breast or colorectal cancer scheduled for at least 3 months of systemic chemotherapy will be randomly assigned (1:1) to receive either LLM-assisted care or standard care. The study employs an adaptive design with initial enrollment of 60 patients (30 per arm), followed by interim analysis. Unless enrollment is stopped for safety reasons identified at interim analysis, an additional 114 patients will be enrolled for a maximum total of 174 patients (87 per arm). In the intervention group, healthcare providers input anonymized patient symptom data into an LLM system using sessions where data is not retained, which generates evidence-based management recommendations. Physicians critically review these recommendations and use them as reference for clinical decision-making, with final treatment decisions remaining under physician discretion. The control group receives standard supportive care without LLM assistance. The primary outcome is change in health-related quality of life measured by EORTC QLQ-C30 global health status/QoL scale from baseline to end of treatment. Secondary outcomes include proportion achieving clinically meaningful improvement (≥8-point increase), treatment adherence, dose intensity, healthcare resource utilization, and physician acceptance of LLM recommendations.

Conditions

Breast Cancer; Colorectal Cancer

Keywords

Large Language Model; LLM; Breast cancer; Side effect; Supportive care; colorectal cancer

Outcome Measures

Primary Outcomes (1)

• Change in health-related quality of life measured by EORTC QLQ-C30 global health status/QoL scale (European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 - Global Health Status/Quality of Life Scale)

  Change in health-related quality of life measured by EORTC QLQ-C30 global health status/QoL scale (range 0-100, higher scores indicate better outcomes; less decline indicates better outcomes)

  Baseline, mid-treatment, end of treatment, 3 months post-treatment (up to 9 months)

Secondary Outcomes (6)

• Proportion of patients with ≥8 points improvement in EORTC QLQ-C30 global health status/QoL scale

  Baseline, mid-treatment, end of treatment, 3 months post-treatment (up to 9 months)

• Proportion of patients completing all planned chemotherapy cycles

  Throughout chemotherapy treatment period (approximately 3-6 months)

• Relative dose intensity (percentage of planned dose actually administered)

  Throughout chemotherapy treatment period (approximately 3-6 months)

• Frequency of grade 3-4 toxicities according to CTCAE v5.0

  Throughout chemotherapy treatment period (approximately 3-6 months)

• Number of emergency department visits and unplanned hospitalizations

  From baseline through 3 months after treatment completion (up to 9 months)

Study Arms (2)

LLM Intervention Group

EXPERIMENTAL

Patients receive standard chemotherapy with AI-assisted symptom management. Healthcare providers input anonymized patient symptoms into a large language model system during clinic visits. The LLM generates management recommendations that physicians review and consider for treatment decisions.

Behavioral: LLM-assisted chemotherapy side effect management

Standard Care Group

NO INTERVENTION

Patients receive standard chemotherapy with conventional symptom management based on institutional protocols and physician clinical judgment.

Interventions

LLM-assisted chemotherapy side effect management BEHAVIORAL

Healthcare providers collect patient symptoms during clinic visits, anonymize the information, and input it into the LLM system via temporary chat sessions. The LLM generates management recommendations which physicians review and consider when adjusting treatment plans. Healthcare providers anonymize patient information and input into LLM using temporary chat sessions. LLM recommendations serve as reference only, with physicians making all final clinical decisions.

LLM Intervention Group

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adult patients (≥ 18 years old) diagnosed with histologically confirmed solid malignancies (breast cancer, colorectal cancer)
• Patients scheduled to receive at least 3 months of systemic chemotherapy
• ECOG performance status 0-2

You may not qualify if:

• Severe psychiatric disorders
• Cognitive impairment affecting ability to report symptoms
• Presence of cancer-related symptoms prior to chemotherapy initiation
• Concurrent participation in trials evaluating other symptom management interventions Inability to provide informed consent Life expectancy less than 6 months

Sponsors & Collaborators

• Incheon St.Mary's Hospital: lead

Study Sites (1)

Incheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea

Incheon, 21431, South Korea

RECRUITING

MeSH Terms

Conditions

Breast Neoplasms; Colorectal Neoplasms

Condition Hierarchy (Ancestors)

Neoplasms by Site; Neoplasms; Breast Diseases; Skin Diseases; Skin and Connective Tissue Diseases; Intestinal Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Colonic Diseases; Intestinal Diseases; Rectal Diseases

Central Study Contacts

Young-Joon Kang

CONTACT

+82322805179; yjkang.md@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, OUTCOMES ASSESSOR
• Masking Details: The primary outcome (EORTC QLQ-C30 global health status/quality of life scale) is a patient-reported outcome; because participants are masked to treatment allocation, outcome assessment is performed in a masked manner. Care providers and site investigators cannot be masked given the clinician-facing nature of the LLM-based decision-support intervention. The study statistician and data analysts will remain masked to treatment allocation until the primary analysis is locked.
• Purpose: SUPPORTIVE CARE
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Assistant Professor

Study Record Dates

• First Submitted: September 3, 2025
• First Posted: September 30, 2025
• Study Start: November 12, 2025
• Primary Completion (Estimated): October 31, 2026
• Study Completion (Estimated): October 31, 2026
• Last Updated: April 22, 2026

Record last verified: 2026-04

Locations

KR (1)