Introduced here are diabetes management platforms able to make annotations to physiological data of a subject whose glycemic health state is being monitored. These annotations can be used to classify excursions detected in the physiological data to facilitate the identification of a therapeutic behavior change intended to improve the glycemic health state of the subject. For example, a health coach may review the annotation(s) associated with the subject before generating a recommendation for improving the glycemic health state. As another example, the diabetes management platform can automatically identify an appropriate recommendation based on the annotation(s).
