Validation of Clinical Risk Models for Clostridioides difficile-Attributable Outcomes

Abstract

Clostridioides difficile is the leading health care-associated pathogen, leading to substantial morbidity and mortality; however, there is no widely accepted model to predict C. difficile infection severity. Most currently available models perform poorly or were calibrated to predict outcomes that are not clinically relevant.

A Predictive Model to Identify ComplicatedClostridiodes difficileInfection

“…In the largest external validation to date, our group recently reported that these models yielded AUC scores below 0.70 [ 14 ]. A recent study in a similarly sized cohort in Virginia also showed poor performance of published models upon external validation [ 27 ]. Thus, current models cannot reliably predict risk for severe complications from CDI.…”

Novel Biomarkers, Including tcdB PCR Cycle Threshold, for Predicting Recurrent Clostridioides difficile Infection

“…Unlike predicting CDI severity, where a multitude of clinical severity scoring systems exist with reasonable performance, such as ATLAS ( 47 , 48 ), there are currently no well-established tools to predict the recurrence of C. difficile infection. We used a naive Bayesian approach to evaluate a rich set of novel predictors shown to be important in CDI pathogenesis ( 19 , 20 ).…”

Predicting Clostridioides difficile infection outcomes with explainable machine learning

“…18 Further details regarding the retrospective cohort and how risk models were selected from the literature and calculated are previously-described. 4 …”

“… 3 Existing C. difficile outcome models are trained to predict only one or a composite of severe outcomes with varying degrees of clinical importance and no model simultaneously predicts severe outcomes and recurrence. For instance, the ATLAS score, perhaps the top-performing risk model, 4 was originally trained to predict “clinical failure” (lack of markedly improved diarrhea or need for additional C. difficile therapy based on investigator opinion 5 ) and is not useful for predicting future recurrent infection.…”