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

Obesity is a serious public health concern world-wide, which increases therisk of many diseases, including hypertension, stroke, and type 2 diabetes. Totackle this problem, researchers across the health ecosystem are collectingdiverse types of data, which includes biomedical, behavioral and activity, andutilizing machine learning techniques to mine hidden patterns for obesitystatus improvement prediction. While existing machine learning methods such asRecurrent Neural Networks (RNNs) can provide exceptional results, it ischallenging to discover hidden patterns of the sequential data due to theirregular observation time instances. Meanwhile, the lack of understanding ofwhy those learning models are effective also limits further improvements ontheir architectures. Thus, in this work, we develop a RNN based time-awarearchitecture to tackle the challenging problem of handling irregularobservation times and relevant feature extractions from longitudinal patientrecords for obesity status improvement prediction. To improve the predictionperformance, we train our model using two data sources: (i) electronic medicalrecords containing information regarding lab tests, diagnoses, anddemographics; (ii) continuous activity data collected from popular wearables.Evaluations of real-world data demonstrate that our proposed method can capturethe underlying structures in users' time sequences with irregularities, andachieve an accuracy of 77-86% in predicting the obesity status improvement.

Recurrent Neural Networks based Obesity Status Prediction Using Activity Data