Efficient and Personalized Mobile Health Event Prediction via Small Language Models

TL;DR

This paper evaluates small language models for mobile health monitoring, demonstrating that a 1.1 billion parameter model can effectively analyze health data locally, ensuring privacy and real-time performance.

Contribution

It investigates the performance of small language models in healthcare, showing their potential for privacy-preserving, on-device health data analysis, which was previously unexplored.

Findings

TinyLlama outperforms other SOTA SLMs in healthcare tasks

TinyLlama achieves 0.48s latency on mobile devices

SLMs can be deployed for real-time, privacy-preserving health monitoring

Abstract

Healthcare monitoring is crucial for early detection, timely intervention, and the ongoing management of health conditions, ultimately improving individuals' quality of life. Recent research shows that Large Language Models (LLMs) have demonstrated impressive performance in supporting healthcare tasks. However, existing LLM-based healthcare solutions typically rely on cloud-based systems, which raise privacy concerns and increase the risk of personal information leakage. As a result, there is growing interest in running these models locally on devices like mobile phones and wearables to protect users' privacy. Small Language Models (SLMs) are potential candidates to solve privacy and computational issues, as they are more efficient and better suited for local deployment. However, the performance of SLMs in healthcare domains has not yet been investigated. This paper examines the capability of SLMs to accurately analyze health data, such as steps, calories, sleep minutes, and other vital statistics, to assess an individual's health status. Our results show that, TinyLlama, which has 1.1 billion parameters, utilizes 4.31 GB memory, and has 0.48s latency, showing the best performance compared other four state-of-the-art (SOTA) SLMs on various healthcare applications. Our results indicate that SLMs could potentially be deployed on wearable or mobile devices for real-time health monitoring, providing a practical solution for efficient and privacy-preserving healthcare.