RHealthTwin: Towards Responsible and Multimodal Digital Twins for Personalized Well-being

2025-06-10

AI Summary

Addressing pervasive hallucination, bias, lack of interpretability, and ethical risks of large language models (LLMs) in consumer-grade health digital twins, this paper introduces the first responsible multimodal digital twin system designed specifically for personal health and well-being. Our core innovation is the Responsible Prompting Engine (RPE), which employs dynamic semantic slot extraction to generate structured, context-aware, and personalized inputs; integrates a health-domain fine-tuned LLM, multimodal fusion, LLM-as-judge evaluation, and a closed-loop feedback mechanism to ensure fairness, reliability, and explainability. Experiments across four health-related tasks yield BLEU=0.41, ROUGE-L=0.63, and BERTScore=0.89. Ethical compliance and instruction-following rates both exceed 90%, significantly outperforming all baselines.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Prompt Engineering / Prompting
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The rise of large language models (LLMs) has created new possibilities for digital twins in healthcare. However, the deployment of such systems in consumer health contexts raises significant concerns related to hallucination, bias, lack of transparency, and ethical misuse. In response to recommendations from health authorities such as the World Health Organization (WHO), we propose Responsible Health Twin (RHealthTwin), a principled framework for building and governing AI-powered digital twins for well-being assistance. RHealthTwin processes multimodal inputs that guide a health-focused LLM to produce safe, relevant, and explainable responses. At the core of RHealthTwin is the Responsible Prompt Engine (RPE), which addresses the limitations of traditional LLM configuration. Conventionally, users input unstructured prompt and the system instruction to configure the LLM, which increases the risk of hallucination. In contrast, RPE extracts predefined slots dynamically to structure both inputs. This guides the language model to generate responses that are context aware, personalized, fair, reliable, and explainable for well-being assistance. The framework further adapts over time through a feedback loop that updates the prompt structure based on user satisfaction. We evaluate RHealthTwin across four consumer health domains including mental support, symptom triage, nutrition planning, and activity coaching. RPE achieves state-of-the-art results with BLEU = 0.41, ROUGE-L = 0.63, and BERTScore = 0.89 on benchmark datasets. Also, we achieve over 90% in ethical compliance and instruction-following metrics using LLM-as-judge evaluation, outperforming baseline strategies. We envision RHealthTwin as a forward-looking foundation for responsible LLM-based applications in health and well-being.

Problem

• Addresses AI hallucination and bias in health digital twins
• Ensures safe, explainable responses for well-being assistance
• Improves ethical compliance in personalized health LLM applications

Innovation

• Multimodal inputs guide health-focused LLM
• Responsible Prompt Engine structures LLM inputs
• Feedback loop updates prompts for user satisfaction