Personalized machine learning approach to predict candidemia in medical wards

Candidemia is a highly lethal infection; several scores have been developed to assist the diagnosis process and recently different models have been proposed. Aim of this work was to assess predictive performance of a Random Forest (RF) algorithm for early detection of candidemia in the internal medical wards (IMWs).

A set of 42 potential predictors was acquired in a sample of 295 patients (male: 142, age: 72 ± 15 years; candidemia: 157/295; bacteremia: 138/295). Using tenfold cross-validation, a RF algorithm was compared with a classic stepwise multivariable logistic regression model; discriminative performance was assessed by C-statistics, sensitivity and specificity, while calibration was evaluated by Hosmer-Lemeshow test.

The best tuned RF algorithm demonstrated excellent discrimination (C-statistics = 0.874 ± 0.003, sensitivity = 84.24% ± 0.67%, specificity = 91% ± 2.63%) and calibration (Hosmer-Lemeshow statistics = 12.779 ± 1.369, p = 0.120), markedly greater than the ones guaranteed by the classic stepwise logistic regression (C-statistics = 0.829 ± 0.011, sensitivity = 80.21% ± 1.67%, specificity = 84.81% ± 2.68%; Hosmer-Lemeshow statistics = 38.182 ± 15.983, p < 0.001). In addition, RF suggests a major role of in-hospital antibiotic treatment with microbioma highly impacting antimicrobials (MHIA) that are found as a fundamental risk of candidemia, further enhanced by TPN. When in-hospital MHIA therapy is not performed, PICC is the dominant risk factor for candidemia, again enhanced by TPN. When PICC is not used and MHIA therapy is not performed, the risk of candidemia is minimum, slightly increased by in-hospital antibiotic therapy.

RF accurately estimates the risk of candidemia in patients admitted to IMWs. Machine learning technique might help to identify patients at high risk of candidemia, reduce the delay in empirical treatment and improve appropriateness in antifungal prescription.