A retrospective cohort study using machine learning to predict coronary artery lesions in children with Kawasaki
Yanan Duan1, Aiping Chen1, Xuedi Cheng2
1Department of Obstetrics and Gynecology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong Province, 266000, China.
Insights
A new predictive model identifies early clinical symptoms and lab results to predict coronary artery lesions in children with Kawasaki disease (KD). This tool aids clinicians in optimizing treatment and improving outcomes for KD patients at risk of CAL.
Area of Science:
- Pediatric Cardiology
- Infectious Diseases
- Biostatistics
Background:
- Kawasaki disease (KD) is a leading cause of acquired heart disease in children.
- Coronary artery lesions (CAL) are the most common complication of KD, necessitating early detection.
- Global incidence of KD is rising, underscoring the need for improved diagnostic tools.
Purpose of the Study:
- To develop and validate a predictive model for coronary artery lesions (CAL) in children diagnosed with Kawasaki disease (KD).
- To identify early clinical symptoms and laboratory markers predictive of CAL development in KD patients.
- To provide clinicians with a tool for early risk stratification and management of CAL in KD.
Main Methods:
- Retrospective cohort study of 436 children with KD.
- Propensity score matching (PSM) to control for confounding factors.
- Machine learning (LASSO regression) to construct a predictive column chart model using clinical and laboratory data.
- Model validation using ROC, calibration, and DCA curves.
Main Results:
- Independent risk factors for concurrent CAL included gender, medical history, cough, diarrhea, and elevated C-reactive protein (CRP).
- The developed predictive model demonstrated strong discriminative ability in both training (AUC: 0.879) and validation (AUC: 0.859) sets.
- The model shows high accuracy and potential clinical utility for predicting CAL risk.
Conclusions:
- A novel predictive tool for CAL risk in KD patients has been developed.
- This model can assist clinicians in more accurate prediction and management of CAL.
- Optimized treatment strategies and improved efficacy are anticipated through the use of this predictive tool.
Background:
Kawasaki disease (KD) mainly occurs in children under 5 years old, and the most common complication of KD is coronary artery lesion (CAL). In recent years, the incidence rate of KD has increased year by year worldwide, so it is particularly important to strengthen the diagnosis of KD and identify CAL early.
Method:
This retrospective cohort study included a total of 436 children diagnosed with Kawasaki disease and aimed to develop a predictive model for CAL using early clinical symptoms and laboratory features. To reduce potential confounding, propensity score matching (PSM) was applied, and both univariate and multivariate analyses were conducted to identify significant predictors of CAL. Subsequently, through machine learning, a predictive column chart model was constructed using clinical features and routine laboratory blood indicators, and the model was evaluated using ROC curves, calibration curves, and DCA curves.
Result:
This study found that gender, medical history, cough, diarrhea symptoms, and high CRP levels were independent risk factors for concurrent CAL. To further predict CAL risk, a column chart model was constructed based on LASSO regression and ten fold cross validation. The ROC curve in the training queue showed good discriminative ability (AUC: 0.879), while the ROC curve in the validation queue showed good discriminative ability (AUC: 0.859). This model exhibits good discriminative ability, high accuracy, and potential clinical benefits in both training and validation sets.
Conclusion:
Through this study, we provide clinicians with a new tool to more accurately predict and manage CAL risk in children with KD, which can help optimize treatment strategies and improve efficacy.
More Related Videos
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
10:03Coronary Progenitor Cells and Soluble Biomarkers in Cardiovascular Prognosis after Coronary Angioplasty
Published on: January 28, 2020
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:30Coronary Artery Disease I: Introduction
01:22Rheumatic Heart Disease II: Clinical Manifestations and Diagnostic Studies
01:26Coronary Artery Disease II: Pathophysiology