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

Clinical predictive algorithms are increasingly being used to form the basisfor optimal treatment policies--that is, to enable interventions to be targetedto the patients who will presumably benefit most. Despite taking advantage ofrecent advances in supervised machine learning, these algorithms remain, in asense, blunt instruments--often being developed and deployed without a fullaccounting of the causal aspects of the prediction problems they are intendedto solve. Indeed, in many settings, including among patients at risk ofreadmission, the riskiest patients may derive less benefit from a preventativeintervention compared to those at lower risk. Moreover, targeting anintervention to a population, rather than limiting it to a small group ofhigh-risk patients, may lead to far greater overall utility if the patientswith the most modifiable (or preventable) outcomes across the population couldbe identified. Based on these insights, we introduce a causal machine learningframework that decouples this prediction problem into causal and predictiveparts, which clearly delineates the complementary roles of causal inference andprediction in this problem. We estimate treatment effects using causal forests,and characterize treatment effect heterogeneity across levels of predicted riskusing these estimates. Furthermore, we show how these effect estimates could beused in concert with the modeled "payoffs" associated with successfulprevention of individual readmissions to maximize overall utility. Based ondata taken from before and after the implementation of a readmissionsprevention intervention at Kaiser Permanente Northern California, our resultssuggest that nearly four times as many readmissions could be prevented annuallywith this approach compared to targeting this intervention using predictedrisk.

A Causal Machine Learning Framework for Predicting Preventable Hospital Readmissions