Related Experiment Video
Updated: Jul 20, 2025
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Derivation and external validation of machine-learning models for risk stratification in chest pain with normal
Agustín Fernández-Cisnal1, Pedro Lopez-Ayala2, Ernesto Valero1
1Cardiology Department, Hospital Clínico Universitario de València, Instituto de Investigación Sanitaria (INCLIVA), University of València, Centro de Investigación Biomédica en Red Enfermedades Cardiovaculares (CIBERCV), València, Spain.
Insights
New machine-learning models effectively risk-stratify patients with chest pain and low high-sensitivity cardiac troponin T (hs-cTnT) levels, outperforming existing scores and reducing unnecessary testing.
Area of Science:
- Cardiology
- Medical Diagnostics
- Machine Learning in Healthcare
Background:
- Risk stratification for chest pain patients with normal high-sensitivity cardiac troponin T (hs-cTnT) is challenging.
- Accurate prediction of 90-day death or myocardial infarction is crucial for timely intervention.
Purpose of the Study:
- Develop and externally validate clinical models for predicting 90-day death or myocardial infarction.
- Improve risk stratification in emergency department patients with chest pain and initial hs-cTnT below the upper reference limit (URL).
Main Methods:
- Trained four machine-learning models and one logistic regression (LR) model on a Spanish cohort (4075 patients).
- Externally validated models on an international cohort (3609 patients).
- Compared model performance against GRACE and HEART scores and an undetectable hs-cTnT strategy (u-cTn).
Main Results:
- Gradient boosting full (GBf) model demonstrated superior discrimination (AUC = 0.808).
- GBf model identified the highest proportion of patients for safe discharge (36.7%) with comparable safety to other methods.
- All developed models outperformed HEART and GRACE scores (P < 0.001).
Conclusions:
- Machine-learning and LR models are superior for risk stratification in chest pain patients with baseline hs-cTnT < URL.
- Gradient boosting full models offer an optimal balance of discrimination, calibration, and efficacy.
- These models can reduce the need for serial hs-cTnT testing by over one-third.
Aims:
Risk stratification of patients with chest pain and a high-sensitivity cardiac troponin T (hs-cTnT) concentration
Methods And Results:
Four machine-learning-based models and one logistic regression (LR) model were trained on 4075 patients (single-centre Spanish cohort) and externally validated on 3609 patients (international prospective Advantageous Predictors of Acute Coronary syndromes Evaluation cohort). Models were compared with GRACE and HEART scores and a single undetectable hs-cTnT-based strategy (u-cTn; hs-cTnT < 5 ng/L and time from symptoms onset >180 min). Probability thresholds for safe discharge were derived in the derivation cohort. The endpoint occurred in 105 (2.6%) patients in the training set and 98 (2.7%) in the external validation set. Gradient boosting full (GBf) showed the best discrimination (area under the curve = 0.808). Calibration was good for the reduced neural network and LR models. Gradient boosting full identified the highest proportion of patients for safe discharge (36.7 vs. 23.4 vs. 27.2%; GBf vs. LR vs. u-cTn, respectively) with similar safety (missed endpoint per 1000 patients: 2.2 vs. 3.5 vs. 3.1, respectively). All derived models were superior to the HEART and GRACE scores (P < 0.001).
Conclusion:
Machine-learning and LR prediction models were superior to the HEART, GRACE, and u-cTn for risk stratification of patients with chest pain and a baseline hs-cTnT
Clinical Trial Registration:
ClinicalTrials.gov number, NCT00470587, https://clinicaltrials.gov/ct2/show/NCT00470587.
More Related Videos
06:16Signal Acquisition, Score Interpretation, and Economics of a Non-Invasive Point-of-Care Test for Coronary Artery Disease
Published on: August 9, 2024
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:29Angina III: Clinical Manifestations and Assessment
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...
01:30Acute Coronary Syndrome III: Diagnostic Studies