Combining Unstructured and Structured Clinical Data in a Hybrid Transformer Model to Enhance Cardiovascular Analytics and Clinical Decision-Making
International Journal of Bioinformatics and Computational Biology · 2026
DOI: 10.37591/ijbcb.v04i01.236368 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Bioinformatics and Computational Biology, 2026. Verfasst von Kalyani Neve und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Since cardiovascular disease (CVD) continues to be a major global cause of morbidity and mortality, early and accurate risk prediction is essential for prompt intervention and individualized treatment. This study introduces a new hybrid transformer-based model that combines unstructured clinical narratives, structured data, and customized lifestyle characteristics. A comprehensive understanding of disease progression is made possible by the model’s ability to capture contextual, temporal, and patient- specific insights through the use of transformer architectures and sophisticated natural language processing. Clinical interpretability and transparency are guaranteed by a special explainability module. Our method combines insights from deep learning, statistical modeling, and graph-based temporal embeddings to improve prediction accuracy and clinical relevance, building on significant advancements in time-aware LSTMs, hybrid modeling, self-attention transformers, and automated machine learning from previous works [1–20]. Assessed using reference datasets, the model The model outperformed both conventional and cutting- edge methods on benchmark datasets, obtaining a Precision@5 of 78.65%, an AUC of 0.86, and an F1- score of 0.76. Its exceptional performance across comorbid conditions and demographic groups demonstrates its generalizability and practicality. This hybrid framework, which seamlessly integrates various data modalities for actionable and equitable CVD risk prediction, is a prime example of the future of predictive analytics in healthcare and advances precision medicine.
Zitieren
APA
Neve, K., Mishra, P., & Chaudhari, K. (2026). Combining Unstructured and Structured Clinical Data in a Hybrid Transformer Model to Enhance Cardiovascular Analytics and Clinical Decision-Making. International Journal of Bioinformatics and Computational Biology. https://doi.org/10.37591/ijbcb.v04i01.236368
Vancouver
Neve K, Mishra P, Chaudhari K. Combining Unstructured and Structured Clinical Data in a Hybrid Transformer Model to Enhance Cardiovascular Analytics and Clinical Decision-Making. International Journal of Bioinformatics and Computational Biology. 2026. doi:10.37591/ijbcb.v04i01.236368
BibTeX
@article{Neve2026,
author = {Neve, Kalyani and Mishra, Padma and Chaudhari, Karishma},
title = {Combining Unstructured and Structured Clinical Data in a Hybrid Transformer Model to Enhance Cardiovascular Analytics and Clinical Decision-Making},
journal = {International Journal of Bioinformatics and Computational Biology},
year = {2026},
doi = {10.37591/ijbcb.v04i01.236368}
}
EUVIMED