Related Experiment Video
Updated: Jul 8, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
A Deep Learning Framework for Image-Based Screening of Kawasaki Disease
Insights
A new deep learning tool analyzes images of clinical signs to assess the risk of Kawasaki disease (KD) in children. This screening framework enables earlier detection and intervention, potentially preventing serious heart complications.
Area of Science:
- Pediatric Cardiology
- Artificial Intelligence in Medicine
- Medical Imaging Analysis
Background:
- Kawasaki disease (KD) is a primary cause of acquired heart disease in children.
- Early diagnosis and treatment with intravenous immunoglobulin are crucial to prevent coronary artery aneurysms.
- Current diagnosis often occurs days after symptom onset in emergency departments.
Purpose of the Study:
- To develop a deep learning framework for a novel screening tool to calculate the relative risk of KD.
- To analyze images of the five clinical signs of KD for early detection.
- To enable families to identify potential KD cases for earlier medical evaluation.
Main Methods:
- A deep learning framework utilizing convolutional neural networks was developed.
- Separate networks were used to calculate risk for each of the five clinical signs.
- A novel algorithm was created to identify specific clinical signs within images.
Main Results:
- The image analysis algorithm achieved a mean accuracy of 90% during 10-fold cross-validation.
- External validation of the algorithm yielded an 88% accuracy rate.
- The framework demonstrated the potential for accurate identification of KD clinical signs from images.
Conclusions:
- The proposed screening tool's algorithms can be used by families to determine the need for clinical evaluation.
- This framework offers a potential pathway for earlier detection of Kawasaki disease.
- Earlier detection can significantly reduce the risk of coronary artery complications in children.
Abstract:
Kawasaki disease (KD) is a leading cause of acquired heart disease in children and is characterized by the presence of a combination of five clinical signs assessed during the physical examination. Timely treatment of intravenous immunoglobin is needed to prevent coronary artery aneurysm formation, but KD is usually diagnosed when pediatric patients are evaluated by a clinician in the emergency department days after onset. One or more of the five clinical signs usually manifests in pediatric patients prior to ED admission, presenting an opportunity for earlier intervention if families receive guidance to seek medical care as soon as clinical signs are observed along with a fever for at least five days. We present a deep learning framework for a novel screening tool to calculate the relative risk of KD by analyzing images of the five clinical signs. The framework consists of convolutional neural networks to separately calculate the risk for each clinical sign, and a new algorithm to determine what clinical sign is in an image. We achieved a mean accuracy of 90% during 10-fold cross-validation and 88% during external validation for the new algorithm. These results demonstrate the algorithms in the proposed screening tool can be utilized by families to determine if their child should be evaluated by a clinician based on the number of clinical signs consistent with KD.Clinical Relevance- This screening framework has the potential for earlier clinical evaluation and detection of KD to reduce the risk of coronary artery complications.
