Author

Chanhyun Park

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Aug 2026

Cardiovascular-Related Death Among Women With Breast Cancer in the United States: Do We Need a Better Approach for Estimating Rates?

Breast cancer is the most common cancer among women in the United States, and cardiovascular disease (CVD) is a leading cause of death in this population. Understanding CVD-related death among breast cancer survivors is critical to inform policies. Previous studies calculating CVD-related death rates in this population used data from the Centers for Disease Control and Prevention (CDC) Wide-ranging ONline Data for Epidemiologic Research (WONDER) with the general US female population as the denominator, which may have produced misleading comparisons. For example, age-adjusted CVD-related death rates have appeared lower among women with breast cancer than in the general US female population, despite survivors facing an elevated CVD risk, understating the need for CVD-focused survivorship care. We demonstrated 2 methodologically appropriate approaches for estimating CVD-related death rates among US women with breast cancer from 1999 through 2020, using a denominator restricted to the breast cancer survivor population, derived from Surveillance, Epidemiology, and End Results (SEER) and Projected Prevalence (ProjPrev) data. We found trends in CVD-related death rates that were broadly consistent with previous studies, with an average annual percentage change of −1.8 (95% CI, −2.0 to −1.6). Our estimates were more intuitive than those from previous studies because they correctly reflected an elevated, rather than reduced, risk relative to the general population: the age-adjusted CVD-related death rate per 100 000 women with breast cancer was 1078.1 in 1999 and 733.1 in 2020. These findings suggest that our approaches can be applied to future research on cause-specific mortality among patients with cancer using CDC WONDER data. Future studies may improve generalizability and identify strategies for linking databases to generate more accessible evidence for public health decision-making.

Le Nguyen, Yan Liu, Chanhyun Park · Public health reports (1974) · 0 citations

Review Aug 2026

Machine learning-based prediction of cardiovascular adverse events in patients with cancer: a systematic review.

INTRODUCTION Cardiovascular (CV) adverse events are increasingly recognized in patients with cancer. Previous reviews of AI/ML have focused on single cancer types, imaging-based data, and lacked evaluation of methodological rigor. This systematic review synthesized AI/ML models developed to predict CV adverse events from patient-level clinical data across diverse cancer populations. METHODS This review followed the PRISMA 2020 guidelines. PubMed and Web of Science were searched through 26 October 2025. Study characteristics, model development, and handling of features and missing data were extracted. Study quality was assessed using the IJMEDI checklist. RESULTS Of 32 included studies, 18 compared multiple algorithms and 14 used a single algorithm. Random forest and XGBoost were the most common methods (n = 17, respectively), and XGBoost was most often the best-performing model in multi-algorithm studies, although substantial study heterogeneity precludes concluding general algorithmic superiority. Common limitations were unreported missing data handling (n = 17), limited external validation (n = 8), and rare calibration assessment (n = 4). Most studies were rated medium quality (n = 28). CONCLUSIONS AI/ML models show promise for predicting CV adverse events in patients with cancer; however, clinical applicability is constrained by insufficient preprocessing transparency, limited external validation, and inadequate calibration reporting.

Li-Wei Wu, Minh-Anh Le-Dang, B. Okoye et al. · Expert review of pharmacoeco... · 0 citations