Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 4, 2024Scalable Computing Practice and ExperienceOpen Access

Logistic regression achieved the highest mean classification accuracy of 93.18% for cardiovascular disease detection, while decision trees provided the highest precision and F1-score at 95.3%.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Cardiovascular diseases are a leading cause of death globally, creating a pressing need to evaluate innovative machine learning methodologies for early diagnosis.

Which machine learning model provides the best classification accuracy and practicality for the early diagnosis of cardiovascular disease?

Population

Heart disease dataset evaluated across 14 features without missing data

Comparison

SVM vs logistic regression vs DT vs ANN

Design

Comparative machine learning model evaluation study

Key result

Logistic regression achieved the highest mean classification accuracy of 93.18% for cardiovascular disease detection, while decision trees provided the highest precision and F1-score at 95.3%.

Authors

MCMukkoti Maruthi Venkata ChalapathiDVDudekula Khasim ValiYKY. V. Pavan Kumar

Discussion

Loading...

Member takes

Overview

Hypothesis-generating for ML-based CVD detection; leaves open prospective validation before clinical use.

Structured PICO

Which machine learning model provides the best classification accuracy and practicality for the early diagnosis of cardiovascular disease?

P
Population
297 patients from the Cleveland heart disease dataset evaluated to compare the accuracy of machine learning models for early cardiovascular disease diagnosis.
I
Intervention
Machine learning models (support vector machine [SVM], logistic regression, decision trees [DT], and artificial neural networks [ANN])
C
Comparator
Comparison among the four distinct machine learning models
O
Outcome
Classification accuracy and possible practicality in cardiovascular disease classification

Basic machine learning models demonstrate similar accuracy for cardiovascular disease classification, with decision trees offering the greatest practicality for clinical use due to their interpretability.

Limitations

  • Small dataset size of only 297 patients limits generalizability.
  • Only a subset of 14 features was used.
  • Binary classification only, unable to diagnose different types of cardiovascular disease.
  • Did not include image-based data.
  • Ensemble learning and other model-specific optimizations were not included, relying only on basic implementations of the models.

Cite This Study

Chalapathi et al. (2024) studied Cardiovascular disease (n=297). Machine learning models (Logistic Regression, Decision Tree, ANN, SVM) vs. Comparison among models was evaluated on Classification accuracy. Logistic regression achieved the highest mean classification accuracy of 93.18% for cardiovascular disease detection, while decision trees provided the highest precision and F1-score at 95.3%.

synapsesocial.com/papers/6a61896c346eb5614926e96dhttps://doi.org/10.12694/scpe.v25i1.2326
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Cardiovascular disease prediction with machine learning techniques2024 · 9 citations
  2. 2Early Detection of Cardiovascular Disease with Different Machine Learning Approaches2024 · 2 citations
  3. 3Comparative of machine learning methods for detecting cardiovascular disease2026
  4. 4A Comprehensive Review of Machine Learning Algorithms in Predicting Cardiovascular Diseases2026
  5. 5Performance Evaluation of Machine Learning Models for Cardiovascular Disease Prediction2025