Publications by authors named "Katia Mitiko Firmino Suzuki"
Article Synopsis
- - The study focuses on developing and validating machine learning models to predict major adverse cardiovascular events (MACE) by evaluating their reliability and interpretability across different populations, utilizing data from Brazil and the USA.
- - Eight machine learning algorithms were trained using a balanced dataset and assessed for their predictive performance based on accuracy and ROC curve metrics, with emphasis on Random Forest, which outperformed the others in both internal and external validations.
- - Findings indicate that while Random Forest was the most effective model, Shapley values offered more consistent insights for understanding feature importance compared to LIME during exploratory analyses.
The record linkage is a strategy that allows linking different databases of information from patient records. Adopting the deterministic method and similarity functions (Dice, Jaro, Jaro-Winkler and Levenshtein) for the integration of heterogeneous databases aimed at different levels of health care Brazilian (primary, secondary and tertiary). The sensitivity of deterministic method was 54.
View Article and Find Full Text PDF