Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 13, 2026Health and TechnologyOpen Access

Logistic Models Trees (LMT) achieved the highest predictive performance and strong stability, while simpler models like Naive Bayes and One Rule approached a 90% accuracy threshold.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Do decision tree-based machine learning algorithms like Logistic Models Trees (LMT) improve predictive performance for detecting cardiovascular disease compared to simpler models?

Population

Individuals assessed for cardiovascular disease (CVD) screening (specific dataset details not provided)

Comparison

Decision tree-based machine learning algorithms… vs Simpler machine learning models such as Naive…

Design

Other

Authors

JÁJosé Luis Ávila-JiménezFRFrancisco J. Rodriguez-LozanoVCVanesa Cantón-Habas

Discussion

Loading...

Member takes

Overview

Logistic Models Trees (LMT) offer high predictive performance and interpretability, making them a promising tool to support clinical decision-making in cardiovascular disease screening.

Key Points

  • The research aims to evaluate the effectiveness of various machine learning algorithms in diagnosing and classifying cardiovascular disease.
  • Utilized a stratified cross-validation methodology for performance assessment.
  • Included both simple and complex machine learning models.
  • Focused on accuracy and interpretability of the algorithms.
  • Naive Bayes and One Rule achieved around 90% accuracy.
  • Logistic Models Trees (LMT) had the highest predictive performance.
  • LMT demonstrated strong stability across different data subsets.

Structured PICO

Do decision tree-based machine learning algorithms like Logistic Models Trees (LMT) improve predictive performance for detecting cardiovascular disease compared to simpler models?

P
Population
Individuals assessed for cardiovascular disease (CVD) screening (specific dataset details not provided)
I
Intervention
Decision tree-based machine learning algorithms, particularly Logistic Models Trees (LMT)
C
Comparator
Simpler machine learning models such as Naive Bayes and One Rule
O
Outcome
Predictive performance and interpretability for early diagnosis and classification of cardiovascular disease

Logistic Models Trees (LMT) offer high predictive performance and interpretability, making them a promising tool to support clinical decision-making in cardiovascular disease screening.

Cite This Study

Ávila-Jiménez et al. (2026) studied this question.

synapsesocial.com/papers/69dc87983afacbeac03e9cdchttps://doi.org/10.1007/s12553-026-01067-w
View Full Paper
Ask AI
Bookmark
Share