Related Experiment Video
Updated: Jun 1, 2025
Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
Development and Validation of KCPREDICT: A Deep Learning Model for Early Detection of Coronary Artery Lesions in
Lei Yang1, Xiaoyu Shen2, Yiman Liu1
1Department of Cardiology, Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine, Shanghai, 200127, China.
Insights
An artificial intelligence algorithm, KCPREDICT, accurately identifies coronary artery lesions in children with Kawasaki disease (KD). This tool aids early diagnosis and treatment, preventing severe complications.
Area of Science:
- Pediatric Cardiology
- Artificial Intelligence in Medicine
- Vasculitis Research
Background:
- Kawasaki disease (KD) is a critical febrile vasculitis in children.
- Coronary artery lesions (CALs) are the most severe KD complication.
- Early CAL detection is hindered by echocardiography limitations.
Purpose of the Study:
- Develop and validate an AI algorithm for CAL detection in KD patients.
- Support clinical decision-making upon admission for KD.
- Improve diagnostic accuracy for CALs in pediatric vasculitis.
Main Methods:
- A deep learning algorithm, KCPREDICT, was created using 24 features.
- Data from 1474 KD patients (Feb 2017-May 2023) were analyzed.
- An 80:20 training/validation split with fivefold cross-validation was used.
Main Results:
- The decision tree model achieved 95.42% accuracy, 98.83% precision, and 96.00% AUROC.
- KCPREDICT demonstrated high performance in distinguishing KD with and without CALs.
- Utilizing all 24 features proved optimal for CAL prediction.
Conclusions:
- KCPREDICT aids clinicians in early CAL identification in KD patients.
- Timely diagnosis facilitates prompt treatment and complication prevention.
- AI-powered tools enhance pediatric cardiovascular disease management.
Abstract:
Kawasaki disease (KD) is a febrile vasculitis disorder, with coronary artery lesions (CALs) being the most severe complication. Early detection of CALs is challenging due to limitations in echocardiographic equipment (UCG). This study aimed to develop and validate an artificial intelligence algorithm to distinguish CALs in KD patients and support diagnostic decision-making at admission. A deep learning algorithm named KCPREDICT was developed using 24 features, including basic patient information, five classic KD clinical signs, and 14 laboratory measurements. Data were collected from patients diagnosed with KD between February 2017 and May 2023 at Shanghai Children's Medical Center. Patients were split into training and internal validation cohorts at an 80:20 ratio, and fivefold cross-validation was employed to assess model performance. Among the 1474 KD cases, the decision tree model performed best during the full feature experiment, achieving an accuracy of 95.42%, a precision of 98.83%, a recall of 93.58%, an F1 score of 96.14%, and an area under the receiver operating characteristic curve (AUROC) of 96.00%. The KCPREDICT algorithm can aid frontline clinicians in distinguishing KD patients with and without CALs, facilitating timely treatment and prevention of severe complications. The use of the complete set of 24 diagnostic features is the optimal choice for predicting CALs in children with KD.
