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

Physical activity and sleep play a major role in the prevention andmanagement of many chronic conditions. It is not a trivial task to understandtheir impact on chronic conditions. Currently, data from electronic healthrecords (EHRs), sleep lab studies, and activity/sleep logs are used. The rapidincrease in the popularity of wearable health devices provides a significantnew data source, making it possible to track the user's lifestyle real-timethrough web interfaces, both to consumer as well as their healthcare provider,potentially. However, at present there is a gap between lifestyle data (e.g.,sleep, physical activity) and clinical outcomes normally captured in EHRs. Thisis a critical barrier for the use of this new source of signal for healthcaredecision making. Applying deep learning to wearables data provides a newopportunity to overcome this barrier.  To address the problem of the unavailability of clinical data from a majorfraction of subjects and unrepresentative subject populations, we propose anovel unsupervised (task-agnostic) time-series representation learningtechnique called act2vec. act2vec learns useful features by taking into accountthe co-occurrence of activity levels along with periodicity of human activitypatterns. The learned representations are then exploited to boost theperformance of disorder-specific supervised learning models. Furthermore, sincemany disorders are often related to each other, a phenomenon referred to asco-morbidity, we use a multi-task learning framework for exploiting the sharedstructure of disorder inducing life-style choices partially captured in thewearables data. Empirical evaluation using actigraphy data from 4,124 subjectsshows that our proposed method performs and generalizes substantially betterthan the conventional time-series symbolic representational methods andtask-specific deep learning models.

Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning