Related Experiment Video
Updated: Jan 10, 2026
06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
2.2K
Feature Selection and Model Optimization for Survival Prediction in Patients with Angina Pectoris
Róbert Bata1, Amr Sayed Ghanem1, Attila Csaba Nagy1
1Department of Epidemiology, Faculty of Health Sciences, University of Debrecen, H-4032 Debrecen, Hungary.
Journal of Clinical Medicine
|November 27, 2025
Summary
Novel survival models, like random survival forest (RSF), significantly improve angina pectoris prediction using electronic health records (EHRs). These advanced methods enhance early identification and clinical decision-making for diabetic patients.
Area of Science:
- Computational medicine and bioinformatics
- Health informatics and data science
Background:
- The proliferation of new survival models and feature selection techniques necessitates comparison with traditional methods to establish optimal performance contexts.
- Electronic Health Record (EHR) data offers a rich resource for predictive modeling in clinical settings.
Purpose of the Study:
- To systematically evaluate and compare the performance of nine survival models and nine feature selection methods for predicting angina pectoris.
- To identify the most effective combination of survival modeling and feature selection for EHR data analysis.
- To assess the impact of methodological innovations on predictive accuracy and clinical decision support.
Main Methods:
- Evaluation of nine survival models and nine feature selection methods on a large EHR dataset (n=29,655, 1150 features) from a Hungarian hospital.
- Performance assessment using concordance index (C-index) for predictive accuracy and integrated Brier score (IBS) for calibration.
- Bayesian hyperparameter tuning for model optimization and time-dependent Area Under the Curve (AUC) for performance over time.
Main Results:
- Tree-based survival models, specifically gradient-boosted survival (GBS) and random survival forest (RSF), outperformed conventional methods in C-index.
- RSF, optimized via Bayesian tuning, demonstrated the best overall performance.
- Tree-based feature selection methods (Boruta, RSF-based) were superior; consensus feature sets were generated and analyzed.
Conclusions:
- Recent innovations in survival analysis significantly enhance predictive accuracy and efficiency for clinical applications.
- Advanced models like RSF provide substantial gains, supporting more robust clinical decision-making in early angina pectoris identification.
- The findings are particularly relevant for identifying angina pectoris risk in diabetic patients using EHR data.
Related Concept Videos
01:19Survival Tree
374
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
374
01:20Angina V: Nursing Management
278
Angina, a symptom of myocardial ischemia, requires a structured nursing management approach to ensure effective care and prevent complications like myocardial infarction. Comprehensive nursing care involves assessing, diagnosing, planning, implementing interventions, and evaluating outcomes, all tailored to the individual patient's needs.Patient AssessmentNursing assessment begins with a detailed subjective evaluation of symptoms, which typically include chest pain or pressure radiating to the...
278
01:15Assumptions of Survival Analysis
388
Survival models analyze the time until one or more events occur, such as death in biological organisms or failure in mechanical systems. These models are widely used across fields like medicine, biology, engineering, and public health to study time-to-event phenomena. To ensure accurate results, survival analysis relies on key assumptions and careful study design.
388
01:21Cancer Survival Analysis
633
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
633
01:29Angina III: Clinical Manifestations and Assessment
192
Angina manifests as chest pain, tightness, or squeezing discomfort typically located behind the breastbone. It can radiate to the neck, jaw, shoulders, and inner aspects of the upper arms, most commonly the left arm. Patients may experience shortness of breath, fatigue, profuse sweating, dizziness, indigestion, heartburn, palpitations, anxiety, and vomiting as accompanying symptoms. This pain often lasts a few minutes and is triggered by physical exertion, emotional stress, heavy meals, or cold...
192
01:26Angina IV: Management
222
IntroductionThe management of angina requires a comprehensive approach that includes pharmacological therapies, medical procedures, and lifestyle modifications.Pharmacological TherapiesAntiplatelet agents, such as aspirin, clopidogrel, prasugrel, and ticagrelor, play a pivotal role in preventing thrombus formation in patients with angina. These medications inhibit platelet aggregation and reduce the likelihood of myocardial infarction and other cardiovascular events.Anticoagulants, including...
222