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) technologies aim to improve distal outcomes, such asclinical conditions, by optimizing proximal outcomes through just-in-timeadaptive interventions. Contextual bandits provide a suitable framework forcustomizing such interventions according to individual time-varying contexts,intending to maximize cumulative proximal outcomes. However, unique challengessuch as modeling count outcomes within bandit frameworks have hindered thewidespread application of contextual bandits to mHealth studies. The currentwork addresses this challenge by leveraging count data models into onlinedecision-making approaches. Specifically, we combine four common offline countdata models (Poisson, negative binomial, zero-inflated Poisson, andzero-inflated negative binomial regressions) with Thompson sampling, a popularcontextual bandit algorithm. The proposed algorithms are motivated by andevaluated on a real dataset from the Drink Less trial, where they are shown toimprove user engagement with the mHealth system. The proposed methods arefurther evaluated on simulated data, achieving improvement in maximizingcumulative proximal outcomes over existing algorithms. Theoretical results onregret bounds are also derived. A user-friendly R package countts thatimplements the proposed methods for assessing contextual bandit algorithms ismade publicly available at https://cran.r-project.org/web/packages/countts.

Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study