GlucoFM-Bench: Benchmarking Time-Series Foundation Models for Blood Glucose Forecasting
Researchers have introduced GlucoFM-Bench, a new benchmark designed to evaluate time-series foundation models (TSFMs) for blood glucose forecasting. The study assessed eight different model architectures, including pre-trained TSFMs and traditional deep learning models, across 15 public datasets representing various diabetes populations. While TSFMs like Chronos-2 and TimesFM demonstrated strong performance in zero-shot and few-shot scenarios, a simple LSTM model remained superior when ample task-specific data was available. AI
IMPACT Provides a standardized evaluation framework for time-series foundation models in a critical healthcare application.