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

Models for predicting the risk of cardiovascular events based on individualpatient characteristics are important tools for managing patient care. Mostcurrent and commonly used risk prediction models have been built from carefullyselected epidemiological cohorts. However, the homogeneity and limited size ofsuch cohorts restricts the predictive power and generalizability of these riskmodels to other populations. Electronic health data (EHD) from large healthcare systems provide access to data on large, heterogeneous, andcontemporaneous patient populations. The unique features and challenges of EHD,including missing risk factor information, non-linear relationships betweenrisk factors and cardiovascular event outcomes, and differing effects fromdifferent patient subgroups, demand novel machine learning approaches to riskmodel development. In this paper, we present a machine learning approach basedon Bayesian networks trained on EHD to predict the probability of having acardiovascular event within five years. In such data, event status may beunknown for some individuals as the event time is right-censored due todisenrollment and incomplete follow-up. Since many traditional data miningmethods are not well-suited for such data, we describe how to modify bothmodelling and assessment techniques to account for censored observation times.We show that our approach can lead to better predictive performance than theCox proportional hazards model (i.e., a regression-based approach commonly usedfor censored, time-to-event data) or a Bayesian network with {\em{ad hoc}}approaches to right-censoring. Our techniques are motivated by and illustratedon data from a large U.S. Midwestern health care system.

Data mining for censored time-to-event data: A Bayesian network model for predicting cardiovascular risk from electronic health record data