A machine learning algorithm to predict treatment effectiveness for Kawasaki disease in China: a retrospective model...

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.