Construction and validation of predictive models for intravenous immunoglobulin-resistant Kawasaki disease using an interpretable machine learning approach.

Autor: Deng L; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China.; Mianyang Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Mianyang, China., Zhao J; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China., Wang T; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China., Liu B; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China., Jiang J; Department of General Surgery (Thyroid Surgery), The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Metabolic Vascular Diseases Key Laboratory of Sichuan Province, Luzhou, China., Jia P; Department of Pediatrics, Zigong First People's Hospital, Zigong, China., Liu D; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China., Li G; Department of Pediatrics, The Affiliated Hospital of Southwest Medical University, Luzhou, China.; Sichuan Clinical Research Center for Birth Defects, Luzhou, China.
Jazyk: angličtina
Zdroj: Clinical and experimental pediatrics [Clin Exp Pediatr] 2024 Aug; Vol. 67 (8), pp. 405-414. Date of Electronic Publication: 2024 Jul 23.
DOI: 10.3345/cep.2024.00549
Abstrakt: Background: Intravenous immunoglobulin (IVIG)-resistant Kawasaki disease is associated with coronary artery lesion development.
Purpose: This study aimed to explore the factors associated with IVIG-resistance and construct and validate an interpretable machine learning (ML) prediction model in clinical practice.
Methods: Between December 2014 and November 2022, 602 patients were screened and risk factors for IVIG-resistance investigated. Five ML models are used to establish an optimal prediction model. The SHapley Additive exPlanations (SHAP) method was used to interpret the ML model.
Results: Na+, hemoglobin (Hb), C-reactive protein (CRP), and globulin were independent risk factors for IVIG-resistance. A nonlinear relationship was identified between globulin level and IVIG-resistance. The XGBoost model exhibited excellent performance, with an area under the receiver operating characteristic curve of 0.821, accuracy of 0.748, sensitivity of 0.889, and specificity of 0.683 in the testing set. The XGBoost model was interpreted globally and locally using the SHAP method.
Conclusion: Na+, Hb, CRP, and globulin levels were independently associated with IVIG-resistance. Our findings demonstrate that ML models can reliably predict IVIG-resistance. Moreover, use of the SHAP method to interpret the established XGBoost model's findings would provide evidence of IVIG-resistance and guide the individualized treatment of Kawasaki disease.
Databáze: MEDLINE
Externí odkaz: