EmoMed adapts medical advice using emotions and updated facts
EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information Retrieval
Artificial IntelligenceComputers and SocietyHuman-Computer Interaction
Summary
Medical advice can be hard to understand and sometimes not sensitive enough to how a person feels. The authors created EmoMed, a smart helper that reads your words and medical images, notices if you seem worried or confused, and changes how it talks to you to feel more caring and clear. It double-checks facts from the web and a medical database to give accurate answers. Tests show EmoMed works better than usual helpers without losing accuracy, and people say its answers feel more empathetic and easier to understand.
What this means in practice
- •For healthcare chatbot developers: Build medical chatbots that tailor advice tone and detail based on patient emotions while ensuring updated clinical facts.
- •For telemedicine platform teams: Integrate emotionally adaptive agents to improve patient communication and trust during remote consultations.
- •For mental health app builders: Enhance apps with emotion-aware medical guidance that responds empathetically to user anxiety or confusion.$Commercial implications: Enables selling advanced emotional interaction features for mental health apps to improve user engagement and support.
Authors
Ivan Nasonov, Nikita Glazkov, Ivan Makovetskiy, Mikhail Mozikov, Daniil Sukhorukov, Andrey Savchenko, Ilya Makarov
Abstract
We present EmoMed - a multimodal medical consultation agent that adapts its responses based on users' emotional states while maintaining clinical accuracy. The system processes text and medical images, detects affect indicators (anxiety, confusion, urgency) from user input, and adjusts response tone, structure, and detail level accordingly. To ensure factual reliability, the agent grounds clinical information through a dual retrieval mechanism: web-based fact-checking and an API-connected, continuously updated medical knowledge base. We evaluate our approach across seven state-of-the-art language models (GPT-4/5, Qwen3, Llama 4, Gemini 2.5, Grok4, Claude3) using comprehensive metrics including LLM-as-judge assessments, MedQA style accuracy tests, BERT Score, safety/helpfulness ratings, and multimodal medical benchmarks. The results demonstrate that emotionally adaptive responses consistently outperform neutral baseline across evaluation dimensions, without compromising clinical accuracy. A controlled user study validated these findings, with participants reporting improved perceived empathy and communication clarity, while maintaining trust in factual accuracy. Source code: https://github.com/NasonovIvan/EmoMed-Agent