Related Experiment Video
Updated: Jan 11, 2026
Hydra, a Computer-Based Platform for Aiding Clinicians in Cardiovascular Analysis and Diagnosis
Published on: September 26, 2018
Explainable artificial intelligence for predicting cardiovascular events in hospitalised COVID-19 patients
Milena Soriano Marcolino1,2, Isabella Viana Gomes Schettini3,4, Guilherme Fonseca do Nascimento5
1Medical School and University Hospital, Universidade Federal de Minas Gerais, Av. Professor Alfredo Balena, 190, room 246, Belo Horizonte, Brazil.
Insights
Artificial intelligence (AI) models showed moderate accuracy in predicting cardiovascular events in hospitalized COVID-19 patients but struggled with detecting rare events due to class imbalance. Key predictors identified include age, urea, platelet count, and oxygen saturation.
Area of Science:
- Cardiology
- Medical Informatics
- Artificial Intelligence
Background:
- COVID-19 is associated with increased cardiovascular complications.
- Artificial intelligence (AI) presents potential for early risk prediction in these cases.
Purpose of the Study:
- To develop and evaluate AI models for identifying cardiovascular event predictors in hospitalized COVID-19 patients.
- To assess the performance of AI models in predicting a composite cardiovascular outcome.
Main Methods:
- Retrospective analysis of 10,700 adult COVID-19 patients from 25 hospitals.
- Development of two LightGBM AI models using demographic, clinical, laboratory, and socioeconomic data.
- Performance evaluation using accuracy, macro-F1, recall, precision, and AUROC; SHAP values for predictor identification; random oversampling for class imbalance.
Main Results:
- Both AI models achieved moderate discrimination (AUROC ~0.75) and high overall accuracy (~94.5%).
- Significant class imbalance led to low macro-F1 scores and very low F1 scores for the minority class (cardiovascular events, <5.2%).
- Even with oversampling, minority class performance remained limited (max F1 score 21.5%), with improved recall at the expense of precision. Key predictors: age, urea, platelet count, SatO2/FiO2.
Conclusions:
- AI models demonstrated moderate predictive ability but were limited in detecting cardiovascular events in COVID-19 patients due to severe class imbalance.
- Low F1 scores for the minority class highlight the challenge of identifying rare events.
- Age, urea, platelet count, and SatO2/FiO2 emerged as significant predictors of cardiovascular complications.
Introduction:
Coronavirus disease (COVID-19) increases the risk of cardiovascular complications, and artificial intelligence (AI) offers promising tools for early risk prediction.
Objective:
To develop AI models capable of identifying predictors of cardiovascular events in hospitalized COVID-19 patients.
Methodology:
Retrospective multicentre cohort, which included adult COVID-19 patients from 25 hospitals (March/2021-August/2022). Cardiovascular outcomes, inluding arrhythmia, acute heart failure, myocardial infarction, myocarditis, and pericarditis, were combined into a composite outcome. Two predictive models were developed using the Light gradient-boosting machine (LightGBM): model 1 used 59 variables (demographic, clinical, laboratory, and socioeconomic data) while model 2 used 52 variables (excluding socioeconomic factors). Model performance was assessed using accuracy, macro-F1, recall, precision, and area under the receiving operating characteristic curve (AUROC). Shapley additive explanation (SHAP) values identified the most influencial predictors. To address class imbalance, we applied random oversampling.
Results:
Among 10,700 patients (median age 59 years [interquatile range 48-70]), 5.3% experienced the composite outcome. Both models showed moderate discrimination (AUROC: 0.752 and 0.760) and high accuracy (94.6% and 94.5%). However, class imbalance resulted in low macro-F1 scores (51.2% and 50.7%). F1 scores were high for the majority class (non-events: 97.2%) but very low for the minority class (cardiovascular events: 5.2% and 4.2%). Even after oversampling, performance for the minority class remained limited, with a maximum F1 score of 21.5%, primarily driven by gains in recall. SHAP analysis identified age, urea, platelet count, and oxygen saturation/inspired oxygen fraction (SatO2/FiO2) as key predictors.
Conclusion:
Despite moderate AUROC and high accuracy, both AI models demonstrated limited ability to detect cardiovascular events due to class imbalance. The persistently low F1 score for the minority class underscores this limitation. Traditional rebalancing techniques produced only small gains, mostly improving recall occurring at the expense of precision. Age, urea levels, platelet count, and SatO2/FiO2 were identified as the most relevant predictors of cardiovascular complications in this cohort.
Related Concept Videos
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
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...
01:25Correlation between ECG and Cardiac Cycle
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...