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

$\textbf{Objective:}$ High-throughput phenotyping will accelerate the use ofelectronic health records (EHRs) for translational research. A criticalroadblock is the extensive medical supervision required for phenotypingalgorithm (PA) estimation and evaluation. To address this challenge, numerousweakly-supervised learning methods have been proposed. However, there is apaucity of methods for reliably evaluating the predictive performance of PAswhen a very small proportion of the data is labeled. To fill this gap, weintroduce a semi-supervised approach (ssROC) for estimation of the receiveroperating characteristic (ROC) parameters of PAs (e.g., sensitivity,specificity).  $\textbf{Materials and Methods:}$ ssROC uses a small labeled dataset tononparametrically impute missing labels. The imputations are then used for ROCparameter estimation to yield more precise estimates of PA performance relativeto classical supervised ROC analysis (supROC) using only labeled data. Weevaluated ssROC through in-depth simulation studies and an extensive evaluationof six PAs from Mass General Brigham (MGB).  $\textbf{Results:}$ ssROC produced ROC parameter estimates with minimal biasand significantly lower variance than supROC in the simulated andsemi-synthetic data. For the five PAs from MGB, the estimates from ssROC are30% to 60% less variable than supROC on average.  $\textbf{Discussion:}$ ssROC enables precise evaluation of PA performancewithout demanding large volumes of labeled data. ssROC is also easilyimplementable in open-source $\texttt{R}$ software.  $\textbf{Conclusion:}$ When used in conjunction with weakly-supervised PAs,ssROC facilitates the reliable and streamlined phenotyping necessary forEHR-based research.

ssROC: Semi-Supervised ROC Analysis for Reliable and Streamlined Evaluation of Phenotyping Algorithms