Candidemia Risk Prediction (CanDETEC) Model for Patients With Malignancy: Model Development and Validation in a Single-Center Retrospective Study

Abstract

Background Appropriate empirical treatment for candidemia is associated with reduced mortality; however, the timely diagnosis of candidemia in patients with sepsis remains poor. Objective We aimed to use machine learning algorithms to develop and validate a candidemia prediction model for patients with cancer. Methods We conducted a single-center retrospective study using the cancer registry of a tertiary academic hospital. Adult patients diagnosed with malignancies between January 2010 and December 2018 were included. Our study outcome was the prediction of candidemia events. A stratified undersampling method was used to extract control data for algorithm learning. Multiple models were developed—a combination of 4 variable groups and 5 algorithms (auto-machine learning, deep neural network, gradient boosting, logistic regression, and random forest). The model with the largest area under the receiver operating characteristic curve (AUROC) was selected as the Candida detection (CanDETEC) model after comparing its performance indexes with those of the Candida Score Model. Results From a total of 273,380 blood cultures from 186,404 registered patients with cancer, we extracted 501 records of candidemia events and 2000 records as control data. Performance among the different models varied (AUROC 0.771- 0.889), with all models demonstrating superior performance to that of the Candida Score (AUROC 0.677). The random forest model performed the best (AUROC 0.889, 95% CI 0.888-0.889); therefore, it was selected as the CanDETEC model. Conclusions The CanDETEC model predicted candidemia in patients with cancer with high discriminative power. This algorithm could be used for the timely diagnosis and appropriate empirical treatment of candidemia.

[Retracted] Prediction of Prognostic Risk Factors in Patients with Invasive Candidiasis and Cancer: A Single‐Centre Retrospective Study

“…To develop and test a predictive model for Candidaemia in cancer patients, Liu et al used machine learning algorithms to analyse clinical data from 186,404 cancer patients. All machine learning models (AUROC 0.771-0.889) outperformed statistical models (AUROC 0.677), with RF being the best (AUROC 0.889) [33]. In this study, the overall mortality rate was 15.89%, which is lower than that reported in other studies [34][35][36], i.e., between 31.9% and 58%.…”

Multifaceted Evaluation of Antibiotic Therapy as a Factor Associated with Candidemia in Non-Neutropenic Patients

“…Furthermore, anti-pseudomonal BL treatment for a duration of ≥3 days was significantly associated with candidemia in the non-CRBSI population. Along with antibiotic factors, immunosuppression, CVC, and TPN were independent factors for candidemia, consistent with previous studies [ 7 , 8 , 9 , 10 , 11 , 12 , 16 ]. Further detailed investigation of these factors could provide insights into the origin of candidemia and point the way to preventive measures.…”

“…These findings may indirectly reflect the close association between antibiotic therapy and candidemia. Furthermore, among these factors, anti-anaerobic therapy is well known to be associated with candidemia originating from the gastrointestinal tract [ 16 , 32 ]. However, anti-anaerobic therapy was not an independent factor for candidemia in this study.…”

Advancing Bloodstream Infection Prediction Using Explanable Artificial Intelligence Framework

“…These studies predominantly focused on inpatient settings, constituting 56% (n=17) of the research, followed by emergency department (ED) settings at 23% (n=7), and ICU settings at 20% (n=6). Within the inpatient group, the studies varied, with nine examining general populations [14–22], two targeting inpatients with central venous catheters (CVC) [23, 24], and others focusing on specific patient categories such as, hemodialysis (HD) patients [26], cancer patients [27], maternity patients [28], patients with low procalcitonin levels (PCT ≤2.0 ng/ml) [29], and HIV patients [30]. Bacteremia was the primary condition under study in 24 articles, including varied focuses such as fungemia [14] and Candidemia [27, 43], while three studies aimed at predicting central line-associated bloodstream infections (CLABSIs) [33, 34, 41] and one on hospital-acquired BSI (HA-BSI) [22].…”