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/

Zendy Plus

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

Zendy Tools

Zendy Open

In recent years, increasingly augmentation of health data, such as patientElectronic Health Records (EHR), are becoming readily available. This providesan unprecedented opportunity for knowledge discovery and data mining algorithmsto dig insights from them, which can, later on, be helpful to the improvementof the quality of care delivery. Predictive modeling of clinical risk,including in-hospital mortality, hospital readmission, chronic disease onset,condition exacerbation, etc., from patient EHR, is one of the health dataanalytic problems that attract most of the interests. The reason is not onlybecause the problem is important in clinical settings, but also there arechallenges working with EHR such as sparsity, irregularity, temporality, etc.Different from applications in other domains such as computer vision andnatural language processing, the labeled data samples in medicine (patients)are relatively limited, which creates lots of troubles for effective predictivemodel learning, especially for complicated models such as deep learning. Inthis paper, we propose MetaPred, a meta-learning for clinical risk predictionfrom longitudinal patient EHRs. In particular, in order to predict the targetrisk where there are limited data samples, we train a meta-learner from a setof related risk prediction tasks which learns how a good predictor is learned.The meta-learned can then be directly used in target risk prediction, and thelimited available samples can be used for further fine-tuning the modelperformance. The effectiveness of MetaPred is tested on a real patient EHRrepository from Oregon Health & Science University. We are able to demonstratethat with CNN and RNN as base predictors, MetaPred can achieve much betterperformance for predicting target risk with low resources comparing with thepredictor trained on the limited samples available for this risk.

MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records