Multi Agent based Medical Assistant for Edge Devices
Sakharam Gawade, Shivam Akhouri, Chinmay Kulkarni, Jagdish Samant, Pragya Sahu, Aastik, Jai Pahal, Saswat Meher
2025-03-13
Summary
This paper talks about a smart medical assistant that runs on phones or small devices, using multiple mini-AI helpers to manage health tasks like appointments and medicine reminders without needing the internet.
What's the problem?
Big AI health tools often need constant internet, risking privacy delays and making them unusable offline.
What's the solution?
The system uses small specialized AI helpers (like a planner and reminder bot) that work together on the device itself, keeping data private and fast.
Why it matters?
This helps people manage health securely on their own devices, especially in areas with poor internet or for those needing quick, private care.
Abstract
Large Action Models (LAMs) have revolutionized intelligent automation, but their application in healthcare faces challenges due to privacy concerns, latency, and dependency on internet access. This report introduces an ondevice, multi-agent healthcare assistant that overcomes these limitations. The system utilizes smaller, task-specific agents to optimize resources, ensure scalability and high performance. Our proposed system acts as a one-stop solution for health care needs with features like appointment booking, health monitoring, medication reminders, and daily health reporting. Powered by the Qwen Code Instruct 2.5 7B model, the Planner and Caller Agents achieve an average RougeL score of 85.5 for planning and 96.5 for calling for our tasks while being lightweight for on-device deployment. This innovative approach combines the benefits of ondevice systems with multi-agent architectures, paving the way for user-centric healthcare solutions.