Large Language Models are Few-Shot Health Learners
This work addresses the challenge of applying LLMs to health applications that require numerical data, offering a method for both clinical and wellness contexts, though it is incremental as it adapts existing models to new data types.
The paper tackled the problem of grounding large language models in numerical health data like vital signs and activity metrics, which are not easily expressed as text, and demonstrated that with few-shot tuning, the model can perform meaningful inferences on tasks such as cardiac analysis and stress estimation, achieving competitive results on new benchmarks.
Large language models (LLMs) can capture rich representations of concepts that are useful for real-world tasks. However, language alone is limited. While existing LLMs excel at text-based inferences, health applications require that models be grounded in numerical data (e.g., vital signs, laboratory values in clinical domains; steps, movement in the wellness domain) that is not easily or readily expressed as text in existing training corpus. We demonstrate that with only few-shot tuning, a large language model is capable of grounding various physiological and behavioral time-series data and making meaningful inferences on numerous health tasks for both clinical and wellness contexts. Using data from wearable and medical sensor recordings, we evaluate these capabilities on the tasks of cardiac signal analysis, physical activity recognition, metabolic calculation (e.g., calories burned), and estimation of stress reports and mental health screeners.