English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Mobile health (mHealth) apps such as menstrual trackers provide a rich sourceof self-tracked health observations that can be leveraged for health-relevantresearch. However, such data streams have questionable reliability since theyhinge on user adherence to the app. Therefore, it is crucial for researchers toseparate true behavior from self-tracking artifacts. By taking a machinelearning approach to modeling self-tracked cycle lengths, we can both make moreinformed predictions and learn the underlying structure of the observed data.In this work, we propose and evaluate a hierarchical, generative model forpredicting next cycle length based on previously-tracked cycle lengths thataccounts explicitly for the possibility of users skipping tracking theirperiod. Our model offers several advantages: 1) accounting explicitly forself-tracking artifacts yields better prediction accuracy as likelihood ofskipping increases; 2) because it is a generative model, predictions can beupdated online as a given cycle evolves, and we can gain interpretable insightinto how these predictions change over time; and 3) its hierarchical natureenables modeling of an individual's cycle length history while incorporatingpopulation-level information. Our experiments using mHealth cycle length dataencompassing over 186,000 menstruators with over 2 million natural menstrualcycles show that our method yields state-of-the-art performance against neuralnetwork-based and summary statistic-based baselines, while providing insightson disentangling menstrual patterns from self-tracking artifacts. This work canbenefit users, mHealth app developers, and researchers in better understandingcycle patterns and user adherence.

A generative, predictive model for menstrual cycle lengths that accounts for potential self-tracking artifacts in mobile health data