CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients

2024-02-07

arXiv.org

AI Summary

Cataract patients face dual challenges of digital health information overload and insufficient credibility, exacerbated by clinicians’ constrained consultation time, widening the patient–provider information gap. To address this, we propose CataractBot—the first expert-collaborative, multimodal chatbot system specifically designed for cataract patients. Methodologically, it integrates retrieval-augmented large language models with a structured medical knowledge base to enable real-time, multilingual, multimodal interactions. Its key innovation is an asynchronous clinician review and closed-loop verification mechanism, ensuring both response timeliness and clinical accuracy. Evaluated in real-world deployment involving 49 patients and caregivers, 4 clinicians, and 2 care coordinators, CataractBot demonstrated high usability across diverse health literacy levels, significantly improved user trust, and markedly enhanced patient–provider communication efficiency.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The healthcare landscape is evolving, with patients seeking reliable information about their health conditions and available treatment options. Despite the abundance of information sources, the digital age overwhelms individuals with excess, often inaccurate information. Patients primarily trust medical professionals, highlighting the need for expert-endorsed health information. However, increased patient loads on experts has led to reduced communication time, impacting information sharing. To address this gap, we developed CataractBot. CataractBot answers cataract surgery related questions instantly using an LLM to query a curated knowledge base, and provides expert-verified responses asynchronously. It has multimodal and multilingual capabilities. In an in-the-wild deployment study with 49 patients and attendants, 4 doctors, and 2 patient coordinators, CataractBot demonstrated potential, providing anytime accessibility, saving time, accommodating diverse literacy levels, alleviating power differences, and adding a privacy layer between patients and doctors. Users reported that their trust in the system was established through expert verification. Broadly, our results could inform future work on designing expert-mediated LLM bots.

Problem

• Addresses cataract surgery information gap
• Provides expert-verified responses asynchronously
• Supports multimodal and multilingual capabilities

Innovation

• LLM-powered expert-verified chatbot
• Multimodal and multilingual capabilities
• Curated knowledge base for cataract queries