Evaluating Binary Classifiers for Cardiovascular Disease Prediction: Enhancing Early Diagnostic Capabilities

Paul Iacobescu, Virginia Marina, Catalin Anghel, Aurelian-Dumitrache Anghele, Alan P Sawchuk · 2024

Read Evaluating Binary Classifiers for Cardiovascular Disease Prediction: Enhancing Early Diagnostic Capabilities by Paul Iacobescu, Virginia Marina, Catalin Anghel, Aurelian-Dumitrache Anghele, Alan P Sawchuk (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11678659.txt.

Description

Paul Iacobescu and co-authors compare, in a 2024 study, seven machine learning methods for predicting heart and vessel disease from patient data. Such disease is the top cause of death in many countries. Catching it early can cut the risk of complications and death, which makes a sound prediction tool valuable.

The seven methods range from logistic regression and naive Bayes to random forests, boosted trees, and neural networks. The team cleaned the data with care first. They balanced the classes with a combined sampling method, and tuned each model's settings by grid search with cross checks. They judged the models on accuracy, precision, recall, a combined score, and a curve based measure. The goal was to see which simple classifier serves early diagnosis best, and how data prep lifts them all.

Catalog record

CREATORPaul Iacobescu, Virginia Marina, Catalin Anghel, Aurelian-Dumitrache Anghele, Alan P Sawchuk
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE44 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11678659

Browse the full library · About the Tower of Babel