AI-empowered Nudge to Improve Colonoscopy Uptake (AINC)

NCT07612436 | Not Yet Recruiting DMC

• 1 other identifier: Fudan-AINC
• Study Type: interventional
• Target: 1,680
• Locations: 0 countries
• Sites: N/A

Brief Summary

Colorectal cancer (CRC) ranks third in both incidence and mortality among all malignant tumors in China. Studies have shown that early screening can significantly reduce its incidence and mortality. Colonoscopy is the gold standard for CRC screening; however, compliance with colonoscopy among high-risk groups in China is very low. Artificial intelligence (AI)-assisted tools can provide real-time, personalized health education, and nudge strategies can help translate intent into action. This trial aims to evaluate the effectiveness of AI-empowered nudge for improving colonoscopy uptake among high-risk individuals aged 45 to 74 in China. It's a two-arm, pragmatic cluster randomized controlled trial. The main question it aims to answer is whether the AI-enabled personalized health education and nudge strategies improve colonoscopy adherence. Participants will:

1. 1.Be recruited and allocated into one of two groups according to the assigned clusters. Participants in one group will be invited to receive usual care. In addition to usual care, participants in the other group will receive AI-empowered nudge, featuring an AI chatbot providing real-time personalized responses and a nudge environment with default screening option.
2. 2.Have their colonoscopy status checked at the end of trial.

Conditions

Colorectal Neoplasms; Colonoscopy

Keywords

Colorectal cancer; artificial intelligence; screening adherence; randomized controlled trial; nudge; Behavioral intervention

Outcome Measures

Primary Outcomes (1)

• Uptake of colonoscopy

  Defined as whether the participant completes the colonoscopy. Data will be collected through the Hospital Information System (HIS) using participants' identification.

  Three months after recruitment

Secondary Outcomes (1)

• Time to completion of colonoscopy

  Three months after recruitment

Other Outcomes (3)

• User engagement level with intervention

  Three months after recruitment

• Usability of AI-empowered Nudge Intervention

  Three months after recruitment

• Intervention Cost

  Three months after recruitment

Study Arms (2)

AI-empowered nudge group

EXPERIMENTAL

This arm implements a multi-component AI-empowered nudge strategy: Default Appointment: On-site pre-scheduling of colonoscopies for high-risk individuals, providing an "opt-out" mechanism. AI Chatbot: Guided on-site use (≥3 mins) of a dedicated chatbot offering personalized responses on CRC questions to facilitate self-learning. LLM-produced SMS Reminders: For non-adherent participants, ChatGPT-5 generates risk-tailored SMS reminders sent bi-weekly to participants and their families (5 times).

Behavioral: AI-empowered nudge (AINC) strategy

Control Group

ACTIVE COMPARATOR

Usual care: Based on the results of the risk assessment questionnaire and FIT test, village doctors will notify the screening results to colorectal cancer high-risk individuals, and instructs recipients to go to the designated hospital for a colonoscopy. Colonoscopy appointments will be scheduled only for residents who are willing to undergo a colonoscopy.

Other: Usual Care

Interventions

Usual Care OTHER

Usual notification of screening results and opt-in appointment for colonoscopy.

Control Group

AI-empowered nudge (AINC) strategy BEHAVIORAL

A digital health education and behavioral nudge intervention. It utilizes an intelligent chatbot to provide real-time, personalized information about colonoscopy and implements a default screening mechanism to facilitate the translation from screening intention to behavior.

AI-empowered nudge group

Eligibility Criteria

• Age: 45 Years - 74 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged 45-74 years;
• Test positive on the Colorectal Cancer Risk Assessment Scale and the immunochemical fecal occult blood test;
• In good general health, mentally competent;
• Provide informed consent.

You may not qualify if:

• History of colorectal resection;
• Previous diagnosis of cancer or currently undergoing any cancer-related treatment;
• Underwent a colonoscopy or sigmoidoscopy within the past 5 years;
• Contraindications to colonoscopy (e.g. severe cardiac, cerebral, lung diseases, or renal dysfunction).

Sponsors & Collaborators

• Fudan University: lead
• Nantong Center for Disease Control and Prevention: collaborator

Related Publications (8)

• Zhang Q, Wong AKC, Bayuo J. The Role of Chatbots in Enhancing Health Care for Older Adults: A Scoping Review. J Am Med Dir Assoc. 2024 Sep;25(9):105108. doi: 10.1016/j.jamda.2024.105108. Epub 2024 Jun 22.

  PMID: 38917965 BACKGROUND

• Maida M, Mori Y, Fuccio L, Sferrazza S, Vitello A, Facciorusso A, Hassan C. Exploring ChatGPT effectiveness in addressing direct patient queries on colorectal cancer screening. Endosc Int Open. 2025 May 12;13:a25689416. doi: 10.1055/a-2568-9416. eCollection 2025.

  PMID: 40376022 BACKGROUND

• Heald B, Keel E, Marquard J, Burke CA, Kalady MF, Church JM, Liska D, Mankaney G, Hurley K, Eng C. Using chatbots to screen for heritable cancer syndromes in patients undergoing routine colonoscopy. J Med Genet. 2021 Dec;58(12):807-814. doi: 10.1136/jmedgenet-2020-107294. Epub 2020 Nov 9.

  PMID: 33168571 BACKGROUND

• Chen D, Avison K, Alnassar S, Huang RS, Raman S. Medical accuracy of artificial intelligence chatbots in oncology: a scoping review. Oncologist. 2025 Apr 4;30(4):oyaf038. doi: 10.1093/oncolo/oyaf038.

  PMID: 40285677 BACKGROUND

• Dougherty MK, Brenner AT, Crockett SD, Gupta S, Wheeler SB, Coker-Schwimmer M, Cubillos L, Malo T, Reuland DS. Evaluation of Interventions Intended to Increase Colorectal Cancer Screening Rates in the United States: A Systematic Review and Meta-analysis. JAMA Intern Med. 2018 Dec 1;178(12):1645-1658. doi: 10.1001/jamainternmed.2018.4637.

  PMID: 30326005 BACKGROUND

• Yu Z, Li B, Zhao S, Du J, Zhang Y, Liu X, Guo Q, Zhou H, He M. Uptake and detection rate of colorectal cancer screening with colonoscopy in China: A population-based, prospective cohort study. Int J Nurs Stud. 2024 May;153:104728. doi: 10.1016/j.ijnurstu.2024.104728. Epub 2024 Feb 20.

  PMID: 38461798 BACKGROUND

• Chen H, Li N, Ren J, Feng X, Lyu Z, Wei L, Li X, Guo L, Zheng Z, Zou S, Zhang Y, Li J, Zhang K, Chen W, Dai M, He J; group of Cancer Screening Program in Urban China (CanSPUC). Participation and yield of a population-based colorectal cancer screening programme in China. Gut. 2019 Aug;68(8):1450-1457. doi: 10.1136/gutjnl-2018-317124. Epub 2018 Oct 30.

  PMID: 30377193 BACKGROUND

• Chen Y, Zhang Y, Yan Y, Han J, Zhang L, Cheng X, Lu B, Li N, Luo C, Zhou Y, Song K, Iwasaki M, Dai M, Wu D, Chen H. Global colorectal cancer screening programs and coverage rate estimation: an evidence synthesis. J Transl Med. 2025 Jul 22;23(1):811. doi: 10.1186/s12967-025-06887-4.

  PMID: 40696392 BACKGROUND

MeSH Terms

Conditions

Colorectal Neoplasms

Condition Hierarchy (Ancestors)

Intestinal Neoplasms; Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Colonic Diseases; Intestinal Diseases; Rectal Diseases

Study Officials

• Zhiyuan Hou, PhD

  Fudan University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Zhiyuan Hou, PhD

CONTACT

86+21 54231112; zyhou@fudan.edu.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Associate Professor

Model Details: This study employs a two-arm, parallel, cluster-randomized controlled trial design. To minimize intervention contamination between participants, randomization is conducted at the cluster level (community/village) rather than the individual level. A total of 70 communities/villages will be randomly assigned in a 1:1 ratio to either the control arm (usual care) or the experimental arm (AI-powered nudge strategy). All eligible high-risk residents identified within a specific cluster will receive the identical intervention assigned to that cluster. Both arms will run simultaneously and parallelly throughout the study period.

Study Record Dates

• First Submitted: May 21, 2026
• First Posted: May 28, 2026
• Study Start: May 30, 2026
• Primary Completion (Estimated): October 1, 2026
• Study Completion (Estimated): December 31, 2027
• Last Updated: June 4, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share