Deep Learning-Based Retinal Disease Classification: A Multi-Model Study on Fundus Imaging Data
International Journal of Advance Research and Innovation · 31.03.2026 · 14 (1) · 28-32
DOI: 10.69996/ijari.2026005 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advance Research and Innovation, online erschienen am 31.03.2026.
Abstract (Originalsprache)
The early detection of cardiac arrest in newborns remains a critical challenge in neonatal care, especially within Cardiac Intensive Care Units (CICUs), where timely intervention can be lifesaving. In order to detect early indicators of cardiac arrest from physiological data and vital signs, this research presents a new Cardiac Machine Learning Model (CMLM) that combines statistical and machine learning methods. Logistic regression and support vector machines are among the classification methods used in the model. Feature optimisation is achieved by normalisation and correlation-based filtering. A comprehensive dataset comprising clinical parameters was used to train and evaluate the model, and the results demonstrated high accuracy, sensitivity, and specificity in predicting cardiac arrest events. Visual dashboards and detection interfaces were also developed to facilitate user interaction and real-time monitoring. The proposed CMLM showcases its potential as a clinical decision-support tool for neonatal healthcare, offering reliable and efficient early warning mechanisms to improve outcomes and reduce mortality rates in newborns
Zitieren
APA
(2026). Deep Learning-Based Retinal Disease Classification: A Multi-Model Study on Fundus Imaging Data. International Journal of Advance Research and Innovation, 14(1), 28-32. https://doi.org/10.69996/ijari.2026005
Vancouver
Deep Learning-Based Retinal Disease Classification: A Multi-Model Study on Fundus Imaging Data. International Journal of Advance Research and Innovation. 2026;14(1):28-32. doi:10.69996/ijari.2026005
BibTeX
@article{euvimed2026,
title = {Deep Learning-Based Retinal Disease Classification: A Multi-Model Study on Fundus Imaging Data},
journal = {International Journal of Advance Research and Innovation},
year = {2026},
volume = {14},
number = {1},
pages = {28--32},
doi = {10.69996/ijari.2026005}
}
EUVIMED