Abstract: The features of physiological signals can be mapped to a latent space in order to draw inferences about activity, health, and age of an individual. For example, heart rate pulses for a population can be acquired as PPG signals and features of these acquired PPG signals can be mapped to a latent space, along with biological age, in order to encode data in the latent space such that location and/or distance within the latent space can be used to infer a corresponding cardiovascular age. Features of a current pulse of PPG data for a user can then be transformed into the latent space with an autoencoder or the like in order to estimate a cardiovascular age for the user, which can also be compared to the user's biological age in order to draw inferences about fitness and/or provide recommendations, coaching, and the like.

Abstract: Variations in pulse shape over time can be used to draw inferences about activity, health, and age of an individual. For example, PPG pulses may be mapped to a latent space where variations in shape can be measured directly in terms of distance between pulses. In one aspect, pulse-to-pulse comparisons for an individual can be used to estimate strain, recovery, sleep, and so forth. Longer term measurements (e.g., over weeks, month, or years) can be used to detect changes in health and fitness for the individual. In another aspect, pulse-to-pulse comparisons among different individuals can be used to estimate relative cardiovascular health, age, and the like.