A machine learning approach to predict intravenous immunoglobulin resistance in Kawasaki disease patients: A study
Tengyang Wang1, Guanghua Liu1, Hongye Lin2
1Department of pediatrics, Fujian Provincial Maternity and Children's Hospital, Fuzhou, Fujian, China.
Insights
Machine learning accurately predicts intravenous immunoglobulin resistance in Kawasaki disease patients, outperforming existing scoring models. This approach offers improved clinical decision support for pediatric cardiology.
Area of Science:
- Pediatric Cardiology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Kawasaki disease is a leading cause of acquired heart disease in children.
- Coronary artery abnormalities are a significant complication, particularly in patients resistant to intravenous immunoglobulin (IVIG).
- Existing models for predicting IVIG resistance have poor performance, limiting clinical utility.
Purpose of the Study:
- To develop and validate a novel machine learning model for predicting IVIG resistance in Kawasaki disease patients.
- To compare the performance of the machine learning model against established clinical scoring systems.
Main Methods:
- Retrospective analysis of 644 Kawasaki disease patient observations with 82 variables.
- Utilized seven machine learning algorithms, including Gradient Boosting Machine (GBM), for binary classification of IVIG resistance.
- Evaluated model performance using Area Under the ROC Curve (AUC), accuracy, sensitivity, and specificity.
Main Results:
- The Gradient Boosting Machine model demonstrated superior performance with an AUC of 0.7423 and high specificity (0.9919).
- Feature importance was assessed using SHAP values, and clinical utility was confirmed via decision curve analysis.
- The developed machine learning model outperformed the Kobayashi, Egami, Formosa, and Kawamura scores.
Conclusions:
- A robust machine learning model can effectively predict IVIG resistance in Kawasaki disease.
- This approach shows potential for integration into electronic health record systems for clinical decision support.
- The findings suggest a more accurate method for identifying high-risk pediatric patients requiring closer monitoring or alternative treatments.
Abstract:
Kawasaki disease is the leading cause of pediatric acquired heart disease. Coronary artery abnormalities are the main complication of Kawasaki disease. Kawasaki disease patients with intravenous immunoglobulin resistance are at a greater risk of developing coronary artery abnormalities. Several scoring models have been established to predict resistance to intravenous immunoglobulin, but clinicians usually do not apply those models in patients because of their poor performance. To find a better model, we retrospectively collected data including 753 observations and 82 variables. A total of 644 observations were included in the analysis, and 124 of the patients observed were intravenous immunoglobulin resistant (19.25%). We considered 7 different linear and nonlinear machine learning algorithms, including logistic regression (L1 and L1 regularized), decision tree, random forest, AdaBoost, gradient boosting machine (GBM), and lightGBM, to predict the class of intravenous immunoglobulin resistance (binary classification). Data from patients who were discharged before Sep 2018 were included in the training set (n = 497), while all the data collected after 9/1/2018 were included in the test set (n = 147). We used the area under the ROC curve, accuracy, sensitivity, and specificity to evaluate the performances of each model. The gradient GBM had the best performance (area under the ROC curve 0.7423, accuracy 0.8844, sensitivity 0.3043, specificity 0.9919). Additionally, the feature importance was evaluated with SHapley Additive exPlanation (SHAP) values, and the clinical utility was assessed with decision curve analysis. We also compared our model with the Kobayashi score, Egami score, Formosa score and Kawamura score. Our machine learning model outperformed all of the aforementioned four scoring models. Our study demonstrates a novel and robust machine learning method to predict intravenous immunoglobulin resistance in Kawasaki disease patients. We believe this approach could be implemented in an electronic health record system as a form of clinical decision support in the near future.
