Effectiveness of Chat-based Mobile Application for Consultation (Zalo) in Improving Compliance With Follow-up Tests After Abnormal Chest X-ray Findings Interpret by Artificial Intelligent

The study titled "Effectiveness of Chat-based Mobile Application for Consultation (Zalo) in Improving Compliance with Follow-up Tests after Abnormal Chest X-ray Findings Interpreted by Artificial Intelligence" aims to evaluate whether digital communication can enhance patient adherence to follow-up evaluations after lung disease screening in Vietnam.

Lung cancer and tuberculosis (TB) remain leading causes of morbidity and mortality in Vietnam. Despite advances in screening technologies, including low-dose CT and AI-assisted chest X-rays, many patients fail to follow up after receiving abnormal results, resulting in delayed diagnosis and treatment. Communication barriers, low health literacy, and limited consultation time are key factors behind this gap. Digital health tools such as chat-based mobile applications offer potential to strengthen post-screening engagement and improve health outcomes.

This randomized controlled trial will be conducted at Nhan Dan Gia Dinh Hospital in Ho Chi Minh City between October 2025 and October 2026. Participants aged 40-62 years, who undergo routine chest X-ray screening interpreted by AI software (qXR by QURE.AI), will be randomly assigned to either the intervention or control group. All participants must have an active Zalo account.

In the intervention group, participants will receive their AI-interpreted results and educational guidelines for lung cancer or TB through the research team's Zalo account. The guideline covers disease overview, diagnostic methods, follow-up recommendations, and lifestyle guidance. Participants may ask questions directly to doctors specializing in nutrition, respiratory medicine, and pulmonary pathology, with guaranteed responses within 4 hours during working hours and 10 hours after hours. Messages are also sent via email as backup. The hospital's IT department oversees the Zalo platform to ensure data security.

In the control group, participants will receive only the doctor's conclusion and brief advice via Zalo and email. They will be invited to connect with the hospital's official Zalo account for general inquiries but will not receive further digital consultation.

Follow-up calls will assess compliance. For positive or suspected cases, research staff will call one month after result notification to confirm whether participants completed follow-up tests. For negative cases, calls will occur at six months to check for new symptoms or additional imaging. Structured questionnaires will document reasons for compliance or noncompliance. The study does not provide additional diagnostic services; all follow-up costs are covered by participants or their health insurance.

The primary outcome is the rate of compliance with recommended follow-up tests. The secondary outcome measures participants' responsiveness to follow-up phone calls. Statistical analyses will compare compliance rates between groups using chi-square or Fisher's exact tests and risk ratios with 95% confidence intervals.

Sample size calculations estimate that 2,692 participants are required to detect a 10% improvement in follow-up compliance (from 85% to 95%) with 80% power and 5% significance. Randomization will use REDCap software with block sizes of 2-8. Interviewers conducting follow-up calls will be blinded to group allocation.

Ethical approval will be obtained from the Nhan Dan Gia Dinh Hospital Ethics Committee, and the study will be registered at ClinicalTrials.gov. Data confidentiality will be strictly maintained, with all digital records password-protected and accessible only to authorized research members.

This project is the first randomized controlled trial in Vietnam to evaluate the effectiveness of chat-based mobile consultation in improving post-screening compliance for lung diseases. It leverages Vietnam's high mobile phone penetration and the popularity of Zalo to create a scalable model for patient engagement. Expected benefits include improved communication, increased awareness of lung cancer and TB, reduced loss to follow-up, and faster diagnostic confirmation.

The findings will provide scientific evidence for integrating digital communication into screening programs and contribute to national efforts to improve early detection and management of lung diseases.

Study Overview

• Status: Not yet recruiting
• Conditions: Lung Cancer; Compliance Behavior; Tuberculosis (TB); Artificial Intelligence in Radiology; Chat-based Mobile Application
• Intervention / Treatment: Other: chat-based mobile application (Zalo)

• Study Type: Interventional
• Enrollment (Estimated): 2692
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Kiet Anh Vu, MPH; Phone Number: +84962762479; Email: kietva@bvndgiadinh.org.vn

Study Locations

• Vietnam
  • Ho Chi Minh City
    • Ho Chi Minh City, Ho Chi Minh City, Vietnam, 700000
      • Nhan Dan Gia Dinh Hospital
      • Contact: Binh Van Huynh, Specialist level 2, MD; Phone Number: +84918051820; Email: binhhv@bvndgiadinh.org.vn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Individuals aged 40 to 62 years old and are still working

• In risk population, which means they exposure at least 2 risk factors of lung cancer, following:

  • smoking
  • expose second-hand smoke
  • expose air pollution, bio-mass fuels
  • expose arsenic
  • expose radon
  • expose asbestos
  • having chronic pulmonary illness
  • having HIV
  • have family member's history of lung cancer (relatives within 3 generations)
• Have mobile phone registered Zalo account

Exclusion Criteria:

• Individual smoked or had history of smoking more than 30 packs per year because they will be advised to do low dose CT scan. That is based on the guideline from Vietnam Misnitry of Health101
• Pregnant woman. It is for safety reason because we will recommend the (+) cases or (-) cases with symptoms do LDCT or CT scan for lung cancer, that can affect the pregnancy. Therefore, if they are pregnant, we will invite them to meet obstetricians.
• History of lung cancer or TB
• Who have problem in mental health is diagnosed by doctor.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention group; Participants receive lung disease screening (chest x-ray interpreted by AI) announcements and educational guidelines via the study's Zalo app account (and by email as backup). Guidelines include information on disease overview, diagnosis, follow-up, and healthy behavior for TB or lung cancer will also be provided to participants. Furthermore, doctors in nutrition, respiratory, and pulmonary fields answer participants' related respiratory illness questions within 4 hours in working time and 10 hours after, supervised by coordinators and the PI. The Zalo platform is research-managed but monitored by hospital IT. We will follow-up one month for positive result cases and 6 months for negative result cases. A structured questionnaire will be interviewed by phone call for reasons for doing follow-up tests or not. Diagnostic tests and costs are participants' responsibility per health insurance or self-payment.	Other: chat-based mobile application (Zalo); this intervention are chat-based activities (including providing illness guidelines and chat-based environment) to encourage participants to compliance doctor's recommendation to do early further tests if they have positive lung disease screening result or they develop lung disease symptoms which suspected to lung cancer or TB
No Intervention: Control group; Participants receive lung disease screening (chest x-ray interpreted by AI) announcements and doctor's advice via the study's Zalo app account (and by email as backup). If they have any question related to their health issues, they will be invited to connect to Nhan dan Gia Dinh hospital's official Zalo account (separately from research team's Zalo account). We will also follow-up one month for positive result cases and 6 months for negative result cases. A structured questionnaire will be interviewed by phone call for reasons for doing follow-up tests or not. Diagnostic tests and costs are participants' responsibility per health insurance or self-payment. in summary, the control group won't recieve guildelines about the illness which provided by research team and chat-based support for respiratory illness compare to intervention group

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
compliance rate of the follow-up test(s)	The main outcome of this study is the compliance rate of the follow-up test(s). This mean participants doing follow-up tests over the period of one month for positive cases and 6 months for negative cases. For outcome ascertainment, it is considered importantly to verify the clinical status using hospital medical records for patients who continued lung disease follow tests. Reliance on telephone interviews alone may lead to misclassification. Therefore, we will try to make confirmation through review of existing medical records should be conducted, particularly for those who did in our healthcare facility. For those did in another healthcare facilities, we will try to encourage them to provide the health record if possible.	one month for positive cases, 6 months for negative cases

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
compliance rate of responding to phone call	Receiving the call from the medical research team is one of necessary key outcomes for evaluating the compliance. Therefore, if the participants refused or missed the call from the medical team for the follow-up time (maybe 3 times), we will consider as non-compliance. However, we will also try to contact their relatives to ensure that no health issues for them (for instance: accident and death), if we can't find any information, we will mark them as non- compliance	one month for positive cases, 6 months for negatives cases

Collaborators and Investigators

• Sponsor: Gia Dinh People Hospital
• Collaborators: AstraZeneca; Prince of Songkla University
• Investigators: Principal Investigator: Kiet Anh Vu, MPH, Nhan Dan Gia Dinh Hospital

Study record dates

Study Major Dates

• Study Start (Estimated): November 15, 2025
• Primary Completion (Estimated): December 30, 2026
• Study Completion (Estimated): December 30, 2027

Study Registration Dates

• First Submitted: November 14, 2025
• First Submitted That Met QC Criteria: November 14, 2025
• First Posted (Actual): November 19, 2025

Study Record Updates

• Last Update Posted (Actual): November 19, 2025
• Last Update Submitted That Met QC Criteria: November 14, 2025
• Last Verified: November 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Infections; Respiratory Tract Diseases; Lung Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Actinomycetales Infections; Mycobacterium Infections; Behavior; Treatment Adherence and Compliance; Health Behavior; Patient Acceptance of Health Care; Lung Neoplasms; Tuberculosis; Patient Compliance
• Other Study ID Numbers: 151/2025/NDGĐ- HĐĐĐ

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED

Drug and device information, study documents

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