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

Background: Risk prediction models are useful tools in clinicaldecision-making which help with risk stratification and resource allocationsand may lead to a better health care for patients. AutoScore is a machinelearning-based automatic clinical score generator for binary outcomes. Thisstudy aims to expand the AutoScore framework to provide a tool forinterpretable risk prediction for ordinal outcomes. Methods: TheAutoScore-Ordinal framework is generated using the same 6 modules of theoriginal AutoScore algorithm including variable ranking, variabletransformation, score derivation (from proportional odds models), modelselection, score fine-tuning, and model evaluation. To illustrate theAutoScore-Ordinal performance, the method was conducted on electronic healthrecords data from the emergency department at Singapore General Hospital over2008 to 2017. The model was trained on 70% of the data, validated on 10% andtested on the remaining 20%. Results: This study included 445,989 inpatientcases, where the distribution of the ordinal outcome was 80.7% alive without30-day readmission, 12.5% alive with 30-day readmission, and 6.8% diedinpatient or by day 30 post discharge. Two point-based risk prediction modelswere developed using two sets of 8 predictor variables identified by theflexible variable selection procedure. The two models indicated reasonably goodperformance measured by mean area under the receiver operating characteristiccurve (0.785 and 0.793) and generalized c-index (0.737 and 0.760), which werecomparable to alternative models. Conclusion: AutoScore-Ordinal provides anautomated and easy-to-use framework for development and validation of riskprediction models for ordinal outcomes, which can systematically identifypotential predictors from high-dimensional data.

AutoScore-Ordinal: An interpretable machine learning framework for generating scoring models for ordinal outcomes