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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Diabetes prediction is an important data science application in the socialhealthcare domain. There exist two main challenges in the diabetes predictiontask: data heterogeneity since demographic and metabolic data are of differenttypes, data insufficiency since the number of diabetes cases in a singlemedical center is usually limited. To tackle the above challenges, we employgradient boosting decision trees (GBDT) to handle data heterogeneity andintroduce multi-task learning (MTL) to solve data insufficiency. To this end,Task-wise Split Gradient Boosting Trees (TSGB) is proposed for the multi-centerdiabetes prediction task. Specifically, we firstly introduce task gain toevaluate each task separately during tree construction, with a theoreticalanalysis of GBDT's learning objective. Secondly, we reveal a problem whendirectly applying GBDT in MTL, i.e., the negative task gain problem. Finally,we propose a novel split method for GBDT in MTL based on the task gainstatistics, named task-wise split, as an alternative to standard feature-wisesplit to overcome the mentioned negative task gain problem. Extensiveexperiments on a large-scale real-world diabetes dataset and a commonly usedbenchmark dataset demonstrate TSGB achieves superior performance againstseveral state-of-the-art methods. Detailed case studies further support ouranalysis of negative task gain problems and provide insightful findings. Theproposed TSGB method has been deployed as an online diabetes risk assessmentsoftware for early diagnosis.

Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction