When Extra Is Not Extra: Heartbeat Irregularities and All-Cause Mortality in Heart Failure Patients
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081731%3A_____%2F25%3A00648265" target="_blank" >RIV/68081731:_____/25:00648265 - isvavai.cz</a>
Result on the web
<a href="https://cinc.org/archives/2025/pdf/CinC2025-272.pdf" target="_blank" >https://cinc.org/archives/2025/pdf/CinC2025-272.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.22489/CinC.2025.272" target="_blank" >10.22489/CinC.2025.272</a>
Alternative languages
Result language
angličtina
Original language name
When Extra Is Not Extra: Heartbeat Irregularities and All-Cause Mortality in Heart Failure Patients
Original language description
Heart Failure (HF) is a condition where the heart cannot pump enough blood to meet the body's needs. When symptoms worsen, patients require urgent care to avoid fatal outcomes. This study examined rhythm and ventricular activation stability features and their link to HF patient mortality. We analyzed data from 10,800 hospitalized HF patients using MIMIC-IV ECG and clinical datasets. Automated processing extracted QRS complex and heart rhythm features. Seventeen features were assessed for their ability to predict 3-year mortality using survival analysis. Lasso regression selected key predictors and built a multivariate model. Hazard ratios (HR) were calculated using the log-rank method. Mortality was strongly associated with QRS morphology and RR-interval instability (e.g., RR-interval variation range, χ<sup>2</sup> = 68.1, p < 0.0001), though age remained the most powerful predictor (χ<sup>2</sup> = 476.7, p < 0.0001). The model built from 13 selected features yielded an HR of 2.26 (95% CI 2.03–2.52), compared to 2.09 (95% CI 1.88–2.33) for age alone. This study highlights the significant role of rhythm and conduction instability in HF mortality, though age remains the dominant predictor.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20601 - Medical engineering
Result continuities
Project
<a href="/en/project/FW06010766" target="_blank" >FW06010766: Remote Therapy in Heart Failure Patients Using Artificial Intelligence and Fusion of Multimodal Inputs</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computing in Cardiology 2025 (CinC 2025)
ISBN
—
ISSN
2325-887X
e-ISSN
—
Number of pages
4
Pages from-to
272
Publisher name
Computing in Cardiology
Place of publication
Neuveden
Event location
Sao Paulo
Event date
Sep 14, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—