Clinical Study on an Artificial Intelligence-Assisted Chest Radiograph Model Based on Big Data and Deep Learning for Early Detection of Kawasaki Disease

NCT07405658 | Not Yet Recruiting DMC

• 1 other identifier: XH-25-010
• Study Type: observational
• Target: 20,000
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to develop an AI-based early warning system for Kawasaki Disease (KD) using chest X-rays (CXR) in children diagnosed with Kawasaki Disease. The main question\[s\] it aims to answer are:

1. 1.Can AI modeling of CXR features help identify high-risk KD patients earlier than current diagnostic methods?
2. 2.Can the AI system predict the optimal IVIG treatment window and coronary artery risks in KD patients?

Conditions

Kawasaki Disease; Chest X-ray for Clinical Evaluation; Mucocutaneous Lymph Node Syndrome

Keywords

Kawasaki Disease; Artificial Intelligence; Mucocutaneous lymph node syndrome

Outcome Measures

Primary Outcomes (3)

• Area Under Curve

  Up to 14 days after fever onset

• sensitivity

  Up to 14 days after fever onset

• specificity

  Up to 14 days after fever onset

Study Arms (2)

Case group

Inclusion criteria: (1) The age of seeking medical treatment is less than or equal to 18 years old; (2) The medical record system diagnosis contains the diagnosis of "Kawasaki Disease", "mucocutaneous lymph node syndrome" or "IVIG non-response Kawasaki disease". (3) At least one complete chest X-ray examination data (images and reports) is available during the same hospitalization. Exclusion criteria: (1) Chest X-ray quality issues: Severe artifacts, overexposure/underexposure leading to inability to assess key structures. (2) Incomplete clinical information, including lack of chest X-ray examination, laboratory tests, and unclear days of fever. (3) Inability to determine the final diagnosis (such as loss to follow-up, diagnosis in doubt).

Diagnostic Test: AI-Based Early Warning System for Kawasaki Disease

Control group

Inclusion criteria: (1) The age of seeking medical treatment is less than or equal to 18 years old; (2) The same period as the case group; (3) Fever lasts for 3 days or more; (4) Rule out the possibility of diagnosing Kawasaki disease Exclusion criteria: (1) Chest X-ray quality issues: Severe artifacts, overexposure/underexposure leading to inability to assess key structures. (2) Incomplete clinical information, including lack of chest X-ray examination, laboratory tests, and unclear days of fever. (3) Inability to make a clear final diagnosis (such as loss to follow-up, questionable diagnosis)

Diagnostic Test: AI-Based Early Warning System for Kawasaki Disease

Interventions

AI-Based Early Warning System for Kawasaki Disease DIAGNOSTIC_TEST

This study utilizes an AI-based early warning system for Kawasaki Disease (KD) to predict the optimal IVIG treatment window and assess coronary risk. The system analyzes chest X-ray (CXR) images and integrates them with clinical data such as CRP levels and clinical symptoms. The intervention involves the development of a multi-modal dynamic prediction model that uses a dual-pathway convolutional neural network (CNN) to extract relevant CXR features and a graph neural network to integrate laboratory indicators. The AI system outputs a prediction of the IVIG treatment window and estimates the risk of coronary artery damage. This early warning system aims to reduce diagnosis time and improve treatment outcomes by identifying high-risk KD patients earlier, enabling timely intervention and personalized treatment plans. The model is designed to be lightweight (under 50MB) to be easily applicable in primary care settings.

Case group; Control group

Eligibility Criteria

• Age: 0 Years - 18 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

The case group consists of children diagnosed with Kawasaki Disease (KD) over the past 10 years. The inclusion criteria include: Children diagnosed with Kawasaki Disease based on clinical symptoms and confirmed by medical records. The control group consists of data from patients with fever lasting ≥3 days, matched to the KD cohort based on diagnosis year, month, and clinical characteristics. The study focuses on examining the relationship between chest X-ray features and Kawasaki Disease in these patients.

You may qualify if:

• Case group
• The age of seeking medical treatment is less than or equal to 18 years old; ·The medical record system diagnosis contains the diagnosis of "Kawasaki Disease", "mucocutaneous lymph node syndrome" or "IVIG non-response Kawasaki disease"
• At least one complete chest X-ray examination data (images and reports) is available during the same hospitalization
• Control group
• The age of seeking medical treatment is less than or equal to 18 years old
• The same period as the case group
• Fever lasts for 3 days or more
• Rule out the possibility of diagnosing Kawasaki disease

You may not qualify if:

• Case group
• Chest X-ray quality issues: Severe artifacts, overexposure/underexposure leading to inability to assess key structures
• Incomplete clinical information, including lack of chest X-ray examination, laboratory tests, and unclear days of fever Inability to determine the final diagnosis (such as loss to follow-up, diagnosis in doubt)
• Control group
• Chest X-ray quality issues: Severe artifacts, overexposure/underexposure leading to inability to assess key structures
• Incomplete clinical information, including lack of chest X-ray examination, laboratory tests, and unclear days of fever
• Inability to make a clear final diagnosis (such as loss to follow-up, questionable diagnosis)

Sponsors & Collaborators

• Xinhua Hospital, Shanghai Jiao Tong University School of Medicine: lead
• Children's Hospital of Soochow University: collaborator
• Hunan Provincial People's Hospital: collaborator
• Women and Children Hospital of Qinghai Province: collaborator
• Yangzhou No.1 People's Hospital: collaborator

Study Sites (1)

Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine

Shanghai, Shanghai Municipality, 2000000, China

Location

MeSH Terms

Conditions

Mucocutaneous Lymph Node Syndrome

Condition Hierarchy (Ancestors)

Vasculitis; Vascular Diseases; Cardiovascular Diseases; Lymphatic Diseases; Hemic and Lymphatic Diseases; Skin Diseases, Vascular; Skin Diseases; Skin and Connective Tissue Diseases

Study Officials

• Kun Sun, Doctoral degree

  Xinhua hospital affiliated with Shanghai Jiao Tong university school of medicine

  STUDY CHAIR

Central Study Contacts

Jian Wang, Doctoral Degree

CONTACT

86-15900861356; wangjian@xinhuemed.com.cn

Bo Wang, PhD Candidate

CONTACT

86-19921875669; 18bowang@sjtu.edu.cn

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: January 12, 2026
• First Posted: February 12, 2026
• Study Start: February 1, 2026
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2027
• Last Updated: February 12, 2026

Record last verified: 2025-12

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)