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: Medical decision-making impacts both individual and publichealth. Clinical scores are commonly used among a wide variety ofdecision-making models for determining the degree of disease deterioration atthe bedside. AutoScore was proposed as a useful clinical score generator basedon machine learning and a generalized linear model. Its current framework,however, still leaves room for improvement when addressing unbalanced data ofrare events. Methods: Using machine intelligence approaches, we developedAutoScore-Imbalance, which comprises three components: training datasetoptimization, sample weight optimization, and adjusted AutoScore. All scoringmodels were evaluated on the basis of their area under the curve (AUC) in thereceiver operating characteristic analysis and balanced accuracy (i.e., meanvalue of sensitivity and specificity). By utilizing a publicly accessibledataset from Beth Israel Deaconess Medical Center, we assessed the proposedmodel and baseline approaches in the prediction of inpatient mortality.Results: AutoScore-Imbalance outperformed baselines in terms of AUC andbalanced accuracy. The nine-variable AutoScore-Imbalance sub-model achieved thehighest AUC of 0.786 (0.732-0.839) while the eleven-variable original AutoScoreobtained an AUC of 0.723 (0.663-0.783), and the logistic regression with 21variables obtained an AUC of 0.743 (0.685-0.800). The AutoScore-Imbalancesub-model (using down-sampling algorithm) yielded an AUC of 0. 0.771(0.718-0.823) with only five variables, demonstrating a good balance betweenperformance and variable sparsity. Conclusions: The AutoScore-Imbalance toolhas the potential to be applied to highly unbalanced datasets to gain furtherinsight into rare medical events and to facilitate real-world clinicaldecision-making.

AutoScore-Imbalance: An interpretable machine learning tool for development of clinical scores with rare events data