Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 6, 2022SHILAP Revista de lepidopterologíaOpen Access

Using Machine Learning Techniques to Predict MACE in Very Young Acute Coronary Syndrome Patients

View Full Paper
Ask AI
Bookmark
Share

Key result

Random forest models outperform traditional logistic regression in predicting MACE for patients ≤40 years.

  • p = 0.021

Why the study?

Coronary artery disease incidence has increased in young subjects, and predicting MACE in very young patients impacts medical decision-making following coronary angiography and treatment selection.

Do machine learning approaches predict MACE more effectively than traditional logistic regression in very young patients undergoing coronary angiography?

Population

492 patients <=40 years old undergoing coronary angiography

Comparison

Machine learning approaches vs traditional statistical methods using logistic regression

Design

Prognostic study

Follow-up

1 year and 60 +- 27 months

Authors

PJPablo Juan‐SalvadoresCVCésar VeigaVDVíctor Alfonso Jiménez Díaz

Discussion

Loading...

Member takes

Overview

May improve MACE prediction in young angiography patients; leaves open prospective validation before clinical use.

Structured PICO

Do machine learning approaches predict MACE more effectively than traditional logistic regression in very young patients undergoing coronary angiography?

P
Population
492 patients ≤40 years old undergoing coronary angiography for acute coronary syndrome
I
Intervention
Machine learning (ML) approaches, specifically Random Forest (RF)
C
Comparator
Traditional statistical methods using logistic regression (LR)
O
Outcome
Prediction of major adverse cardiac events (MACE)composite

Machine learning models, particularly random forest, significantly outperform traditional logistic regression in predicting MACE in very young patients undergoing coronary angiography.

Limitations

  • small sample size

Cite This Study

Juan‐Salvadores et al. (2022) studied this question. Machine learning techniques, specifically random forest, predicted MACE in patients ≤40 years more accurately (AUC 0.79) than traditional logistic regression (AUC 0.66, p = 0.021).

synapsesocial.com/papers/698cd1bdcf5273e9093378cdhttps://doi.org/10.3390/diagnostics12020422
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Coronary heart disease incidence still decreased between 2006 and 2014 in France, except in young age groups: Results from the French MONICA registries2020 · 27 citations
  2. 2pROC: an open-source package for R and S+ to analyze and compare ROC curves2011 · 14,554 citations
  3. 3PRROC: computing and visualizing precision-recall and receiver operating characteristic curves in R2015 · 465 citations