A Guideline-Concordant Chatbot Framework for Structured Colorectal Cancer Screening: Multistage Feasibility Study
Journal of Medical Internet Research · 2026-07-16 · 28 · e93042
DOI: 10.2196/93042 ↗At a glance
Leitlinie in Journal of Medical Internet Research, published online on 2026-07-16. Written by Futao Wu and 8 co-authors. Institution: Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Ch…. Major MEDLINE topics: Colorectal Neoplasms, Early Detection of Cancer. Cited 2 times so far (Crossref); 36 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Colorectal cancer (CRC) screening relies on structured risk assessment and guideline-concordant communication, which remain challenging to implement consistently in real-world practice. Digital tools based on large language models (LLMs) may support such workflows, but their feasibility and safety in structured screening contexts have not been well evaluated.
Objective
This study aimed to develop and evaluate a guideline-concordant chatbot framework for structured CRC screening.
Methods
A multistage feasibility study was conducted. In phase 1, baseline performance of contemporary LLMs was assessed using 14 standardized CRC screening questions and validated expert-rated instruments. In phase 2, structured prompt versions were iteratively optimized based on screening guidelines and expert feedback and tested using simulated user scenarios. In phase 3, the optimized chatbot was evaluated in 50 screening-eligible adults to assess feasibility, safety, and guideline concordance.
Results
In phase 1, both LLMs demonstrated satisfactory performance in responding to standardized CRC screening questions, with DISCERN instrument for AI-generated content scores of 12.02 (SD 0.30) for GPT-4o and 13.36 (SD 0.26) for DeepSeek-V3, Global Quality Score scores of 3.96 (SD 0.10) for GPT-4o and 4.39 (SD 0.08) for DeepSeek-V3, Natural Language Assessment Tool for AI scores of 21.41 (SD 0.34) for GPT-4o and 22.73 (SD 0.27) for DeepSeek-V3, and Patient Education Materials Assessment Tool adapted for AI outputs scores of 0.900 (SD 0.016) for GPT-4o and 0.906 (SD 0.015) for DeepSeek-V3. In phase 2, iterative prompt optimization significantly improved all 6 expert-rated dialogue evaluation dimensions (all P values
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
- Department of Gastroenterology, Affiliated Qingyuan Hospital, Guangzhou Medical University, Qingyuan People's Hospital, Qingyuan, China.
- Department of Gastroenterology, Nanfang Hospital (Zengcheng Branch), Southern Medical University, Guangzhou, China.
- Department of Gastroenterology, Zhuhai People's Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai, China.
ORCID profiles: Futao Wu, Xue Li, Yingyi Zeng, Yan Tang, Zhenhua Xiao, Siqi Yang, Kangcheng Wu, Side Liu, Aimin Li
Cite
APA
Wu, F., Li, X., Zeng, Y., Tang, Y., Xiao, Z., Yang, S., Wu, K., Liu, S., & Li, A. (2026). A Guideline-Concordant Chatbot Framework for Structured Colorectal Cancer Screening: Multistage Feasibility Study. Journal of Medical Internet Research, 28, e93042. https://doi.org/10.2196/93042
Vancouver
Wu F, Li X, Zeng Y, Tang Y, Xiao Z, Yang S, et al. A Guideline-Concordant Chatbot Framework for Structured Colorectal Cancer Screening: Multistage Feasibility Study. Journal of Medical Internet Research. 2026;28:e93042. doi:10.2196/93042
BibTeX
@article{Wu2026,
author = {Wu, Futao and Li, Xue and Zeng, Yingyi and Tang, Yan and Xiao, Zhenhua and Yang, Siqi and Wu, Kangcheng and Liu, Side and Li, Aimin},
title = {A Guideline-Concordant Chatbot Framework for Structured Colorectal Cancer Screening: Multistage Feasibility Study},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e93042},
doi = {10.2196/93042}
}
EUVIMED