SleepApp - Providing Contextualized and Actionable Sleep Feedback.

Most commercial sleep sensors typically rely on population-level data and focus on recommendations based on objective metrics such as sleep duration or sleep efficiency. However, there is inter-individual trait-variability to sleep and people's sleep habits are individualized. To prompt users to adopt habits that improve sleep health, meaningful sleep feedback must not only provide evidence of how users' behaviors affect their sleep quality, as objectified by some of the metrics, but also show how carry-over effects of sleep affect daytime cognitive function. In this paper, we propose and validate an approach that combines both subjective and objective measures of sleep, accounting for a person's lifestyle and ties it to meaningful and measurable carryover effects such as daytime alertness and working memory. Our approach is based on the medical community's Ru-SATED framework, which characterizes sleep through six dimensions: Regularity, Satisfaction, Alertness, Timing, Efficiency and Duration. Using data collected by a smart phone app: SleepApp, with a suite of ecological momentary assessment tests from 9 participants over 14 days, we demonstrate how sleep health can be contextualized to the individual lifestyle and actionable feedback can be generated. In a follow up survey with 57 respondents, we show how the actionable feedback generated by SleepApp can encourage in users the intent to make adjustments to their sleep habits that may impact their daytime cognitive function