High-risk ECG patterns in ST elevation myocardial infarction for mortality prediction

Lahti, Roope; Rankinen, Jani; Lyytikäinen, Leo-Pekka; Eskola, Markku; Nikus, Kjell; Hernesniemi, Jussi

doi:10.1016/j.jelectrocard.2022.07.068

Cited by 5 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This research marks the first instance of calculating kurtosis and skewness from ECG signals specifically for mortality prediction, demonstrating their pivotal role in such predictive analysis. Similarly, previous research highlighted a positive correlation between elevated HB and mortality [48,49]. Lower SBP and DBP were also shown to be predictors for inhospital, 30-day, and 1-year mortality in patients with STEMI [29].…”

Section: Discussionmentioning

confidence: 53%

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

Razavi,

Szun,

Zaremba

et al. 2024

Medicina

View full text Add to dashboard Cite

Background and Objectives: Patients presenting with ST Elevation Myocardial Infarction (STEMI) due to occlusive coronary arteries remain at a higher risk of excess morbidity and mortality despite being treated with primary percutaneous coronary intervention (PPCI). Identifying high-risk patients is prudent so that close monitoring and timely interventions can improve outcomes. Materials and Methods: A cohort of 605 STEMI patients [64.2 ± 13.2 years, 432 (71.41%) males] treated with PPCI were recruited. Their arterial pressure (AP) wave recorded throughout the PPCI procedure was analyzed to extract features to predict 1-year mortality. After denoising and extracting features, we developed two distinct feature selection strategies. The first strategy uses linear discriminant analysis (LDA), and the second employs principal component analysis (PCA), with each method selecting the top five features. Then, three machine learning algorithms were employed: LDA, K-nearest neighbor (KNN), and support vector machine (SVM). Results: The performance of these algorithms, measured by the area under the curve (AUC), ranged from 0.73 to 0.77, with accuracy, specificity, and sensitivity ranging between 68% and 73%. Moreover, we extended the analysis by incorporating demographics, risk factors, and catheterization information. This significantly improved the overall accuracy and specificity to more than 76% while maintaining the same level of sensitivity. This resulted in an AUC greater than 0.80 for most models. Conclusions: Machine learning algorithms analyzing hemodynamic traces in STEMI patients identify high-risk patients at risk of mortality.

show abstract

Section: Discussionmentioning

confidence: 53%

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

Razavi,

Szun,

Zaremba

et al. 2024

Medicina

View full text Add to dashboard Cite

show abstract

“…New-onset LBBB or RBBB in the setting of ACS has previously been found to predict cardiovascular death (35)(36)(37). These events include deaths due to heart failure and sudden arrhythmic deaths, but also deaths due to other cardiovascular complications of ACS.…”

Section: Conduction Disorders and Scdmentioning

confidence: 99%

Prognostic implications of intraventricular conduction disorders for sudden cardiac death in coronary artery disease

Lahti,

Rankinen,

Järvensivu-Koivunen

et al. 2023

Preprint

View full text Add to dashboard Cite

Backround and aimsProlonged QRS duration (≥ 110 ms) and coronary artery disease are risk factors for sudden cardiac death (SCD). We explored the SCD risk associated with intraventricular conduction disorders – a prolonged QRS duration of 110–119 ms, right bundle branch block (RBBB), left bundle branch block (LBBB), and a nonspecific intraventricular conduction delay (NIVCD) – in patients with acute coronary syndrome (ACS).MethodsThis is a retrospective study of 9,700 consecutive, invasively treated ACS patients with ECGs available for analysis (2007–2018). SCD definition was based on an in-depth review of written medical records and death certificates describing the circumstances leading to the events. Endpoint data were available until December 31, 2021 (no losses to follow-up). The risk associated with conduction disorders was analyzed by calculating subdistribution hazard estimates (deaths due to other causes being considered competing events).ResultsThe median follow-up time was 6.8 years (IQR 4.0–10.2), during which 3,420 (35.3%) patients died. SCDs were overrepresented as a cause of death among patients with NIVCD (16.4%) or with a prolonged QRS duration (15.3%) when compared to patients with LBBB (5.3%), RBBB (7.1%), or with a normal QRS duration (10.5%). In an analysis adjusted for age, sex, and cardiac comorbities, NIVCD and a prolonged QRS were significant predictors of SCD (HR 3.00, 2.06– 4.35, P < 0.001; and HR 1.80, 1.37–2.35, P < 0.001, respectively). After adjusting the analysis with left ventricular ejection fraction, NIVCD and a prolonged QRS duration remained as significant risk factors for SCD. LBBB and RBBB did not predict SCD.ConclusionThe incidence of SCD is significantly higher in patients with NIVCD and a prolonged QRS duration. Approximately 23% of all SCDs occur among these patients.

show abstract

A self-adjusting ant colony clustering algorithm for ECG arrhythmia classification based on a correction mechanism

Liu

Yang

et al. 2023

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

High-risk ECG patterns in ST elevation myocardial infarction for mortality prediction

Cited by 5 publications

References 30 publications

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

1-Year Mortality Prediction through Artificial Intelligence Using Hemodynamic Trace Analysis among Patients with ST Elevation Myocardial Infarction

Prognostic implications of intraventricular conduction disorders for sudden cardiac death in coronary artery disease

A self-adjusting ant colony clustering algorithm for ECG arrhythmia classification based on a correction mechanism

Contact Info

Product

Resources

About