A machine learning algorithm to predict treatment effectiveness for Kawasaki disease in China: a retrospective model
Xuemei Li1, Zihan Zhou1, Jingyi Fan1
1Department of Pediatrics, Shengjing Hospital of China Medical University, Shenyang, Liaoning, China.
Insights
This study developed a machine learning model to predict intravenous immunoglobulin (IVIG) resistance in children with Kawasaki disease (KD). The model aids in personalizing treatment strategies for better outcomes in Chinese pediatric patients.
Area of Science:
- Pediatric Cardiology
- Computational Medicine
- Immunology
Background:
- Kawasaki disease (KD) is a leading cause of acquired heart disease in children.
- Intravenous immunoglobulin (IVIG) is the standard first-line treatment for KD.
- Predictive tools for IVIG resistance in Chinese KD patients are currently lacking.
Purpose of the Study:
- To develop and validate a machine learning model for predicting IVIG non-responsiveness in pediatric patients with KD in China.
- To address the need for reliable treatment efficacy prediction tools in this population.
- To facilitate personalized treatment strategies for KD management.
Main Methods:
- Retrospective cohort study of KD patients from Shengjing Hospital.
- Utilized 36 demographic, clinical, and laboratory parameters.
- Employed Least Absolute Shrinkage and Selection Operator (LASSO) regression and CatBoost machine learning algorithm.
- Internal and external validation using distinct patient cohorts.
Main Results:
- The CatBoost model demonstrated high performance with an AUC of 0.960 (internal validation: 0.862, external validation: 0.834).
- Achieved excellent sensitivity (0.883) and specificity (0.889) in comprehensive evaluation.
- Internal validation showed sensitivity of 0.716 and specificity of 0.877; external validation yielded sensitivity of 0.817 and specificity of 0.838.
Conclusions:
- A robust machine learning model for predicting IVIG non-responsiveness in Chinese KD patients has been developed.
- This predictive tool can assist clinicians in tailoring treatment plans.
- The model holds potential to improve the overall prognosis for children with Kawasaki disease.
Background:
Kawasaki disease (KD) is the primary cause of acquired heart disease in children. Intravenous immunoglobulin (IVIG) is the first-line therapy for KD; however, IVIG resistance can occur. Reliable treatment efficacy prediction tools for Chinese patients are lacking, which this study aimed to address.
Methods:
This retrospective cohort study enrolled patients diagnosed with KD admitted to Shengjing Hospital of China Medical University and collected data on 36 demographic, clinical, and laboratory parameters. Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to identify key predictive variables. The dataset was divided into training (70%) and validation (30%) sets. Ten models were trained through 10-fold cross-validation, and the training set data were balanced using the ROSE method for oversampling. The performance of each model was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Patients with KD admitted to Guangzhou Women and Children's Medical Centre, Guangzhou Medical University, between January 2023 and December 2024 were enrolled as an external validation cohort.
Results:
The CatBoost machine learning algorithm achieved the best comprehensive results (AUC: 0·960; sensitivity: 0·883; specificity: 0·889, and accuracy: 0·887). The internal validation results with CatBoost were AUC: 0·862; 95% confidence interval [CI]: 0·6453-0·7651; sensitivity: 0·716; specificity: 0·877; and accuracy: 0·861. The external validation results were AUC: 0·834; 95% CI: 0·783-0·884; sensitivity: 0·817; specificity: 0·838, and accuracy: 0·835.
Conclusions:
We present a machine learning model that can predict the risk of IVIG non-responsiveness in patients with KD in China. This model may help doctors develop personalized treatment strategies, thus improving the prognosis of KD.