Related Experiment Video
Updated: Jan 15, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Large Language Model Agent for Managing Patients With Suspected Hypertension
Yijun Wang1,2, Wuping Tan3, Siyi Cheng4
1Department of Cardiology, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, P.R. China (Y.W., J.L., J.W.).
The Cascade Framework, an AI agent, significantly improves hypertension management by enhancing patient education and clinical decision support. This AI tool shows promise for personalized health strategies and better patient outcomes.
Area of Science:
- Artificial Intelligence in Healthcare
- Clinical Decision Support Systems
- Digital Health and Personalized Medicine
Background:
- The efficacy of Large Language Model (LLM) agent frameworks for hypertension screening and personalized health management remains under-explored.
- Hypertension requires effective screening, education, and management strategies to mitigate health risks.
Purpose of the Study:
- To develop and evaluate the Cascade Framework, an LLM-based agent designed for hypertension education and clinical decision support.
- To assess the framework's effectiveness in improving patient understanding and clinical decision-making accuracy for hypertension.
Main Methods:
- Developed the Cascade Framework using the Dify platform.
- Conducted a two-phase evaluation (August 2024 - June 2025) involving performance benchmarking of LLMs (ChatGPT-4o, ChatGPT-4oMini, DeepSeek-V3) and their Cascade-enhanced versions.
- Performed external validation on a cohort of patients with suspected hypertension.
Main Results:
- Cascade integration significantly improved educational outcomes (accuracy, credibility, emotional support) and LLM performance.
- Blood pressure classification accuracy increased from 62.5% to 87.0%, and risk factor stratification improved from 60.4% to 98.6%.
- Clinical decision-making accuracy rose to 92.5%, surpassing physician performance in external validation (95.3% accuracy).
Conclusions:
- The Cascade Framework demonstrates potential to enhance hypertension management through improved patient education and clinical decision support.
- Its extensible architecture facilitates integration into existing clinical workflows, offering transparent reasoning pathways for healthcare providers.
Related Concept Videos
Hypertension IV: Drug Therapy and Lifestyle Modifications
Hypertension V: Nursing Management
Hypertension III: Clinical Manifestations and Diagnostic Studies
Hypertension and Regulation of Blood Pressure
Hypertension I: Introduction
Heart Failure Drugs: Inhibitors of Renin-Angiotensin System
