Menstrual cycle tracking

A computer-implemented method, comprising:

• obtaining historical information related to a menstrual cycle of a user;
• determining, based at least in part on the historical information, a predictive model for the menstrual cycle;
• obtaining, using a non-invasive measurement system of a monitoring device, heart rate data for the user;
• automatically determining, based at least in part on the heart rate data and the predictive model, at least one pattern in the heart rate data;
• determining, based at least in part on the at least one pattern and the predictive model, an updated predictive model;
• determining, based at least in part on the updated predictive model, a future event related to the menstrual cycle, the updated predictive model using machine learning to analyze the heart-rate derived data, and the historical user information being used to refine or retrain the updated predictive model;
• and
• presenting, on the monitoring device, the future event.

A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor, cause the at least one processor to:

• obtain historical user information for one or more events related to a menstrual cycle of a user;
• generate a prediction for a future event related to the menstrual cycle, the prediction based at least in part on the historical user information as input into a predictive model;
• obtain, using a non-invasive measurement sub-system of a monitoring device, heart rate-derived data for the user over a period of time;
• correlate, through the predictive model, patterns in the heart rate-derived data with events in the menstrual cycle;
• provide the heart rate-derived data as additional input to the predictive model;
• and
• generate, using the predictive model and the additional input, an updated prediction for the future event related to the menstrual cycle the predictive model using machine learning to analyze the heart-rate derived data, and the historical user information being used to refine or retrain the predictive model.