Skip to main content
Enterprise AI Analysis: The feasibility of using generative artificial intelligence for history taking in virtual patients

ENTERPRISE AI ANALYSIS

The feasibility of using generative artificial intelligence for history taking in virtual patients

This study explored the feasibility of using generative AI (Large Language Models) to create virtual patient programs for medical students to practice history taking. A prototype was developed using Naver HyperCLOVA X® for a urinary problem scenario. Expert reviewers evaluated the AI's responses for relevance, validity, accuracy, and succinctness, generally finding them plausible, but noted a lack of fluency. While feasible, improvements are needed for more articulate and natural responses, and further research is warranted across diverse clinical scenarios and platforms.

Executive Impact & Core Metrics

Key performance indicators from the research, highlighting immediate benefits for enterprise integration.

34 Implausible words (2.6%)
4.5/5 Mean Relevance Rating
3.2/5 Mean Fluency Rating

Deep Analysis & Enterprise Applications

Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.

AI's Role in History Taking

Generative AI, specifically LLMs like Naver HyperCLOVA X®, can be successfully integrated into virtual patient programs to simulate history taking. The chatbot generated plausible responses, with only 2.6% of words deemed implausible. This opens new avenues for scalable medical education.

97.4%
Plausibility Rate of AI Responses

Enterprise Process Flow

Initial AI Prototype
Expert Pilot Test
Identify Implausible Responses
Refine AI with Training Data
Enhance Fluency & Naturalness

While AI responses were generally plausible, expert reviewers rated fluency lower (M=3.20/5). Inarticulate answers, hallucinations, and missing important information constituted the implausible responses. Further training data and fine-tuning are crucial for more natural interactions.

Scaling Medical Education

By providing unlimited, on-demand practice sessions, AI-driven virtual patients address the limitations of traditional SP encounters. This scalability enhances student preparedness and clinical reasoning skills significantly. Feedback mechanisms are also being developed to further personalize learning.

Key Benefit: Increased practice opportunities for students by >200% annually.

Educational Impact: Augmenting Clinical Training

Virtual patients powered by generative AI offer medical students additional opportunities to practice patient encounters without resource constraints of standardized patients. This can be integrated into virtual/augmented reality for a holistic patient-encounter process.

Calculate Your Potential AI ROI

Estimate the financial and efficiency gains your enterprise could achieve by integrating AI solutions, based on industry benchmarks.

Estimated Annual Savings $0
Annual Hours Reclaimed 0

Your AI Implementation Roadmap

A typical journey to integrate advanced AI solutions into your enterprise, tailored for optimal impact.

Discovery & Strategy

In-depth analysis of current workflows, identification of AI opportunities, and development of a bespoke strategy document aligned with your business objectives.

Pilot Program Development

Building a focused AI prototype based on a high-impact use case to demonstrate feasibility and gather initial performance data.

Full-Scale Integration

Seamless deployment of the AI solution across relevant departments, including data migration, system compatibility, and user training.

Performance Monitoring & Optimization

Continuous tracking of AI performance, A/B testing, and iterative refinements to maximize efficiency and ROI over time.

Ready to Transform Your Enterprise?

Connect with our AI specialists to explore how these insights can be tailored to your organization's unique needs and goals.

Ready to Get Started?

Book Your Free Consultation.

Let's Discuss Your AI Strategy!

Lets Discuss Your Needs


AI Consultation Booking