PulseTrendingJournal ClubResearchersJournalsExplore
Instagram
HomeTrendingJournal ClubExplore
Synapse
⌘+K
Synapse
August 3, 2023PeerJOpen Access

Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study

View Full Paper
Ask AI
Bookmark
Share

Why the study?

The study aimed to evaluate multiple machine learning methods for predicting the association between cardiovascular risk factors and CAD-RADS scores.

Can machine learning algorithms accurately predict high CAD-RADS scores based on cardiovascular risk factors in patients with CAD?

Population

442 CAD patients with CCTA examinations

Comparison

CAD-RADS score 0-2 group vs CAD-RADS score 3-5 group

Design

Retrospective cohort study

Authors

YDYueli DaiCOChenyu OuyangGLGuanghua Luo

Discussion

Loading...

Member takes

Overview

ML models accurately predict CAD-RADS from risk factors retrospectively; leaves open prospective validation before clinical use.

Structured PICO

Can machine learning algorithms accurately predict high CAD-RADS scores based on cardiovascular risk factors in patients with CAD?

P
Population
442 patients with coronary artery disease (CAD) who underwent coronary CT angiography (CCTA) examinations.
I
Intervention
Machine learning algorithms (random forest, k-nearest neighbors, support vector machines, neural network, decision tree classification, and linear discriminant analysis) using 19 clinical features.
O
Outcome
Prediction of high CAD-RADS score (3-5) vs low CAD-RADS score (0-2) based on cardiovascular risk factors.surrogate

Machine learning algorithms, particularly random forest, can accurately predict high CAD-RADS scores using clinical risk factors such as plasma fibrinogen, age, and diabetes.

Cite This Study

Dai et al. (2023) studied this question.

synapsesocial.com/papers/6a8566196e0f1d231d20256bhttps://doi.org/10.7717/peerj.15797
View Full Paper
Ask AI
Bookmark
Share