A Deep Learning Framework for Image-Based Screening of Kawasaki Disease.

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.

A deep convolutional neural network for Kawasaki disease diagnosis.

Kawasaki disease (KD), the most common cause of acquired heart disease in children, can be easily missed as it shares clinical findings with other pediatric illnesses, leading to risk of myocardial infarction or death. KD remains a clinical diagnosis for which there is no diagnostic test, yet there are classic findings on exam that can be captured in a photograph. This study aimed to develop a deep convolutional neural network, KD-CNN, to differentiate photographs of KD clinical signs from those of other pediatric illnesses. To create the dataset, we used an innovative combination of crowdsourcing images and downloading from public domains on the Internet. KD-CNN was then pretrained using transfer learning from VGG-16 and fine-tuned on the KD dataset, and methods to compensate for limited data were explored to improve model performance and generalizability. KD-CNN achieved a median AUC of 0.90 (IQR 0.10 from tenfold cross validation), with a sensitivity of 0.80 (IQR 0.18) and specificity of 0.85 (IQR 0.19) to distinguish between children with and without clinical manifestations of KD. KD-CNN is a novel application of CNN in medicine, with the potential to assist clinicians in differentiating KD from other pediatric illnesses and thus reduce KD morbidity and mortality.