<b>Background/objectives</b>: Kawasaki disease is the leading cause of acquired heart disease in children within developed countries. Although treatment with intravenous immunoglobulin (IVIG) significantly reduces the incidence of coronary artery aneurysm (CAA), the risk of it persists, affecting long-term patient outcomes. While intensified primary treatment is recommended for patients at high risk of IVIG resistance or CAA development, a universally accepted predictive model for such resistance remains unestablished. This study aims to develop a machine learning model to predict the occurrence of CAAs prior to initiating IVIG therapy. <b>Methods</b>: Data from two nationwide epidemiological surveys conducted between 2012 and 2017 were analyzed, encompassing 17,189 patients with calculable coronary artery z-scores and Harada scores. Various supervised machine learning algorithms were applied to develop a model for predicting CAA. Afterward, unsupervised learning techniques were employed to explore the data's inherent structure. <b>Results</b>: The Harada score's receiver operating characteristic (ROC) analysis yielded an area under the curve (AUC) of 0.558. The highest AUC among the machine learning models was 0.661, achieved by the Light Gradient Boosting Machine. However, this model's sensitivity was 0.615, and specificity was 0.647, indicating limited clinical applicability. Unsupervised learning revealed no distinct distribution patterns between patients with/without CAAs. <b>Conclusions</b>: Despite utilizing a large dataset to develop a machine learning-based prediction model for CAAs, the performance was unsatisfactory. Future studies should focus on enhancing predictive models by incorporating additional clinical data, such as acute-phase coronary artery diameter measurements, to improve accuracy and clinical utility.

<b>Background/objectives</b>: Kawasaki disease is the leading cause of acquired heart disease in children within developed countries. Although treatment with intravenous immunoglobulin (IVIG) significantly reduces the incidence of coronary artery aneurysm (CAA), the risk of it persists, affecting long-term patient outcomes. While intensified primary treatment is recommended for patients at high risk of IVIG resistance or CAA development, a universally accepted predictive model for such resistance remains unestablished. This study aims to develop a machine learning model to predict the occurrence of CAAs prior to initiating IVIG therapy. <b>Methods</b>: Data from two nationwide epidemiological surveys conducted between 2012 and 2017 were analyzed, encompassing 17,189 patients with calculable coronary artery z-scores and Harada scores. Various supervised machine learning algorithms were applied to develop a model for predicting CAA. Afterward, unsupervised learning techniques were employed to explore the data's inherent structure. <b>Results</b>: The Harada score's receiver operating characteristic (ROC) analysis yielded an area under the curve (AUC) of 0.558. The highest AUC among the machine learning models was 0.661, achieved by the Light Gradient Boosting Machine. However, this model's sensitivity was 0.615, and specificity was 0.647, indicating limited clinical applicability. Unsupervised learning revealed no distinct distribution patterns between patients with/without CAAs. <b>Conclusions</b>: Despite utilizing a large dataset to develop a machine learning-based prediction model for CAAs, the performance was unsatisfactory. Future studies should focus on enhancing predictive models by incorporating additional clinical data, such as acute-phase coronary artery diameter measurements, to improve accuracy and clinical utility.

Becker muscular dystrophy is an infrequent genetic disorder that results from dystrophin gene mutations. Cardiac involvement is a primary manifestation. The time of onset of underlying cardiac functional abnormalities remains largely undefined. This study involved 17 pediatric patients with Becker muscular dystrophy who visited our hospital between January 1, 2002, and December 31, 2018, and underwent echocardiographic imaging analysis. Another set of 17 controls matched for age and sex to the patient cohort was chosen for comparison. Patients with Becker muscular dystrophy demonstrated a decline in echocardiographic measures, especially deformation parameters, compared with the control group. This alteration is influenced by age. Our findings suggest that early echocardiographic monitoring may help identify subclinical cardiac dysfunction, particularly in younger patients (<10 years of age).

Older age at onset and female sex were predictors of unresolved PVCs in healthy children, highlighting the need for tailored monitoring for these subgroups, despite the generally favorable prognosis of PVCs.

High log EASIX levels are associated with an increased risk of AKI in HF patients. In clinical practice, log EASIX, being simple to operate and readily accessible, may serve as an effective tool for the early identification of high-risk patients and help to develop individualized treatment strategies.

Donor factors did not show significant impact on post-transplant survival but some factors were predictive of post-transplant rejection and cardiac allograft vasculopathy.

A longer paced QRS duration was associated with poor outcomes, indicating its potential to predict adverse outcomes among Fontan patients.

Recent efforts have sought to analyze major issues related to the diagnosis, treatment, and prognosis of Kawasaki disease patients using machine learning. Presentations have highlighted the application of image analysis related to clinical findings that correspond to the diagnostic criteria for Kawasaki disease, as well as the evaluation of coronary artery ultrasound images. Additionally, studies have aimed to utilize machine learning models based on numerical data to predict the diagnosis of Kawasaki disease, the occurrence of coronary artery lesions, and resistance to immunoglobulin treatment. Furthermore, it is anticipated that future research will increasingly employ machine learning for the categorization and classification of data types in studies that extensively incorporate genetic and immunological biomarkers.