EUVIMEDEUVIMED entdecken
Crossref

CARE-XAI: A Privacy-Preserving, Fair, and Explainable AI Framework for Multimodal Early Cardiovascular Risk Prediction

Revathy S P., Swetha A B., Vaishali Srija P B.

Journal of Ubiquitous Computing and Communication Technologies · 20.04.2026 · 8 (2) · 89-102

DOI: 10.36548/jucct.2026.2.002 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Ubiquitous Computing and Communication Technologies, online erschienen am 20.04.2026. Verfasst von Revathy S P. und 2 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early prediction of cardiovascular diseases has always been a significant challenge due to data privacy risks, non-interpretable outcomes, and demographic biases associated with current machine learning approaches. In this paper, CARE-XAI (Comprehensive AI Risk Evaluation with Explainable Artificial Intelligence) is presented as a novel framework that combines federated learning, fairness optimization methods, and explainable artificial intelligence to predict cardiovascular diseases based on multiple clinical modalities. CARE-XAI uses the UCI Heart Disease database as the fundamental clinical modality, along with simulated behavioral and wearable datasets to improve predictive accuracy. Federated learning using the FedAvg algorithm ensures privacy-preserving training in a decentralized manner without any leakage of sensitive information about patients. Fairness optimization with the help of AIF360 is used to counteract demographic biases, while model transparency is guaranteed through SHAP explanations. Experimental results show that CARE-XAI provides an accuracy score of 83.1% with 82.5% precision, 84.3% recall, and 0.881 AUC values, while also performing comparably well with centralized frameworks.

Zitieren

APA

P., R. S., B., S. A., & B., V. S. P. (2026). CARE-XAI: A Privacy-Preserving, Fair, and Explainable AI Framework for Multimodal Early Cardiovascular Risk Prediction. Journal of Ubiquitous Computing and Communication Technologies, 8(2), 89-102. https://doi.org/10.36548/jucct.2026.2.002

Vancouver

P. RS, B. SA, B. VSP. CARE-XAI: A Privacy-Preserving, Fair, and Explainable AI Framework for Multimodal Early Cardiovascular Risk Prediction. Journal of Ubiquitous Computing and Communication Technologies. 2026;8(2):89-102. doi:10.36548/jucct.2026.2.002

BibTeX
@article{P2026,
  author = {P., Revathy S and B., Swetha A and B., Vaishali Srija P},
  title = {CARE-XAI: A Privacy-Preserving, Fair, and Explainable AI Framework for Multimodal Early Cardiovascular Risk Prediction},
  journal = {Journal of Ubiquitous Computing and Communication Technologies},
  year = {2026},
  volume = {8},
  number = {2},
  pages = {89--102},
  doi = {10.36548/jucct.2026.2.002}
}
Kostenlos starten →