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.).
Insights
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.
Background:
The effectiveness of Large Language Model agent frameworks for hypertension screening and personalized health management has not been fully studied. This study aimed to develop and evaluate a Large Language Model-based Agent, called the Cascade Framework, and assess its effectiveness in hypertension education and clinical decision support.
Methods:
The Cascade Framework was developed utilizing the Dify platform, and its performance was tested via a robust 2-phase evaluation protocol from August 2024 to June 2025. The first phase involved systematic performance benchmarking of 6 configurations: 3 foundational Large Language Models (Chat Generative Pretrained Transformer [ChatGPT]-4o, ChatGPT-4oMini, and DeepSeek-V3) and their respective Cascade-enhanced versions. The second phase included an external validation in a cohort of patients with suspected hypertension.
Results:
Cascade integration yielded significant performance improvements across all models. For ChatGPT-4o, educational outcomes improved (Accuracy: 3.87→4.10, P=0.02; Comprehensiveness: 4.07→4.32, P=0.16; Credibility: 3.79→4.03, P<0.001; Understandability: 3.90→3.96, P=0.005; Emotional Support: 3.87→4.01, P<0.001). Blood pressure classification accuracy rose from 62.5% to 87.0% (P<0.001) and risk factor stratification from 60.4% to 98.6% (P<0.001). Clinical decision-making improved, with accuracy of 72.0% to 92.5%. A similar trend of performance improvement was observed in the external validation cohort, where the 4o-Cascade model achieved increases in blood pressure classification accuracy (58.9%→95.3%), risk stratification accuracy (71.0%→90.7%), and clinical decision appropriateness (66.4%→92.5%), all with P<0.001 and surpassing the performance of the 3 physicians.
Conclusions:
Cascade Framework can improve the management of hypertension. Its extensible architecture allows integration with existing clinical workflows while providing transparent reasoning pathways.
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
