AUTHOR=Chaikovsky Illya , Dziuba Dmytro , Kryvova Olga , Marushko Katerina , Vakulenko Julia , Malakhov Kyrylo , Loskutov Оleg 

TITLE=Subtle changes on electrocardiogram in severe patients with COVID-19 may be predictors of treatment outcome

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 8 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1561079

DOI=10.3389/frai.2025.1561079

ISSN=2624-8212

ABSTRACT=BackgroundTwo years after the COVID-19 pandemic, it became known that one of the complications of this disease is myocardial injury. Electrocardiography (ECG) and cardiac biomarkers play a vital role in the early detection of cardiovascular complications and risk stratification. The study aimed to investigate the value of a new electrocardiographic metric for detecting minor myocardial injury in patients during COVID-19 treatment.MethodsThe study was conducted in 2021. A group of 26 patients with verified COVID-19 diagnosis admitted to the intensive care unit for infectious diseases was examined. The severity of a patient’s condition was calculated using the NEWS score. The digital ECGs were repeatedly recorded (at the beginning and 2–4 times during the treatment). A total of 240 primary and composite ECG parameters were analyzed for each electrocardiogram. Among these patients, 6 patients died during treatment. Cluster analysis was used to identify subgroups of patients that differed significantly in terms of disease severity (NEWS), SрО2 and integral ECG index (an indicator of the state of the cardiovascular system).ResultsUsing analysis of variance (ANOVA repeated measures), a statistical assessment of changes of indicators in subgroups at the end of treatment was given. These subgroup differences persisted at the end of the treatment. To identify potential predictors of mortality, critical clinical and ECG parameters of surviving (S) and non-surviving patients (D) were compared using parametric and non-parametric statistical tests. A decision tree model to classify survival in patients with COVID-19 was constructed based on partial ECG parameters and NEWS score.ConclusionA comparison of potential mortality predictors showed no significant differences in vital signs between survivors and non-survivors at the beginning of treatment. A set of ECG parameters was identified that were significantly associated with treatment outcomes and may be predictors of COVID-19 mortality: T-wave morphology (SVD), Q-wave amplitude, and R-wave amplitude (lead I).