سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / اولین همایش بین المللی تحول خدمات سلامت: تلفیق مراقبت، درمان، بازتوانی و امیدبخشی

Artificial Intelligence for Uncovering the Underlying Etiology of Hypertension

نویسندگان :

Ali Ataei kachooei¹ Samira Shariati najafabadi²

1- دانشگاه آزاد اسلامی واحد نجف آباد ، اصفهان 2- دانشگاه آزاد اسلامی واحد نجف آباد ، اصفهان

کلمات کلیدی :

Hypertension،Artificial Intelligence،Machine Learning،Precision Medicine،Etiology،Secondary Hypertension

چکیده :

Abstract Background: Hypertension represents one of the most challenging diseases worldwide, as its underlying etiology remains complex and incompletely understood (1). With the advent of artificial intelligence (AI), it is possible to integrate various datasets such as genomic, proteomic, metabolomic, and clinical datasets (2, 3). This approach may provide new opportunities to uncover hidden risk factors and disease phenotypes. This review highlights current evidence on the potential of AI to advance precision medicine in hypertension. Methods: A narrative review was conducted by searching major scientific databases, such as PubMed. The search was performed using keywords related to hypertension, artificial intelligence, machine Learning, precision medicine, and etiology. Findings: Recent findings show that AI can extend hypertension assessment beyond conventional blood pressure-based diagnosis by identifying complex disease patterns, distinct phenotypes, and potential etiological signatures (3, 4). AI algorithms have demonstrated high performance in recognizing secondary etiologies of hypertension (2, 3), while multi-omics approaches integrating genomic and metabolomic data may improve the characterization of biologically distinct hypertension subtypes (2). The integration of multimodal data provides an opportunity to uncover unrecognized associations and candidate biological drivers of hypertension (2, 4, 5). Conclusion: AI has the potential to shift hypertension research from conventional diagnosis to etiology-oriented precision medicine. By means of integration of multi-omics data using AI, it is possible to identify hidden phenotypes, secondary causes, and candidate mechanisms of hypertension. Causality-aware models are needed to translate these discoveries into clinically actionable strategies for early risk prediction and management. Key words: Hypertension, Artificial Intelligence, Machine Learning, Precision Medicine, Etiology, Secondary Hypertension