Predicting Clostridioides difficile infection outcomes with explainable machine learning.

Background: Clostridioides difficile infection results in life-threatening short-term outcomes and the potential for subsequent recurrent infection. Predicting these outcomes at diagnosis, when important clinical decisions need to be made, has proven to be a difficult task.
Methods: 52 clinical features from existing models or the literature were collected retrospectively within ±48 h of diagnosis among 1660 inpatient infections. A modified desirability of outcome ranking (DOOR) was designed to encompass clinically-important severe events attributable to the acute infection (intensive care transfer due to sepsis, shock, colectomy/ileostomy, mortality) and/or 60-day recurrence. A deep neural network was constructed and interpreted using SHapley Additive exPlanations (SHAP). High-importance features were used to train a reduced, shallow network and performance was compared to existing conventional models (7 severity, 7 recurrence; after summing DOOR probabilities to align with conventional binary outputs) using area under the ROC curve (AUROC) and DeLong tests.
Findings: The full (52-feature) model achieved an out-of-sample AUROC 0.823 for severity and 0.678 for recurrence. SHAP identified 13 unique, highly-important features (age, hypotension, initial treatment, onset, PCR cycle threshold, number of prior episodes, antibiotic exposure, fever, hypotension, pressors, leukocytosis, creatinine, lactate) that were used to train a reduced model, which performed similarly to the full model (severity AUROC difference P = 0.130; recurrence P = 0.426) and significantly better than the top severity model (reduced model predicting severity 0.837, ATLAS 0.749; P = 0.001). The reduced model also outperformed the top recurrence model, but this was not statistically-significant (reduced model recurrence AUROC 0.653, IDSA Recurrence Risk Criteria 0.595; P = 0.196). The final, reduced model was deployed as a web application with real-time SHAP explanations.
Interpretation: Our final model outperformed existing severity and recurrence models; however, it requires external validation. A DOOR output allows specific clinical questions to be asked with explainable predictions that can be feasibly implemented with limited computing resources.
Funding: National Institutes of Health-Institute of Allergy and Infectious Diseases.
Competing Interests: Declaration of interests This work was funded by National Institutes of Health (K23AI163368 to G.R.M., R01-AI152477 and -AI124214 (to W.A.P.), 5T32AI055432-20 to R.H.B) and National Center for Advancing Translational Science (UL1TR003015, KL2TR003016 to G.R.M.). W. A. Petri is a consultant for TechLab Inc., a company that manufactures diagnostic tests for C. difficile toxins. All other authors report no conflicts of interest relevant to this article.
(Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved.)