Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jul 26;9(7):e24651.
doi: 10.2196/24651.

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

Junsang Yoo #  1 , Si-Ho Kim #  2 , Sujeong Hur  3   4 , Juhyung Ha  5 , Kyungmin Huh  6 , Won Chul Cha  4   7   8
Affiliations

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

Junsang Yoo et al. JMIR Med Inform. .

Erratum in

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.

Keywords: candidemia; decision support; decision support systems, clinical; development; infection control; machine learning; model; precision medicine; prediction; risk; supervised machine learning; validation.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: None declared.

Figures

Figure 1
Figure 1
Eligibility process diagram.
Figure 2
Figure 2
Variable groups used for training algorithms and a detailed list of variable group 1.
Figure 3
Figure 3
Area under the receiver operating characteristic curve of the developed models by algorithm type and variables groups: (A) Group 1, (B) Group 2, (C) Group 3, and (D) Group 4. AutoML: automated machine learning.
Figure 4
Figure 4
Decision curve of the CanDETEC model. Arrow indicates the threshold to determine candidemia high risk group.
Figure 5
Figure 5
Calibration plot of the CanDETEC model. A point represents mean decile grouped by predicted probability. Error bars represent 95% confidence interval.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Clancy CJ, Nguyen MH. T2 magnetic resonance for the diagnosis of bloodstream infections: charting a path forward. J Antimicrob Chemother. 2018 Mar 01;73(suppl_4):iv2–iv5. doi: 10.1093/jac/dky050.4951491 - DOI - PubMed
    1. Viscoli C, Girmenia C, Marinus A, Collette L, Martino P, Vandercam B, Doyen C, Lebeau B, Spence D, Krcmery V, De Pauw B, Meunier F. Candidemia in cancer patients: a prospective, multicenter surveillance study by the Invasive Fungal Infection Group (IFIG) of the European Organization for Research and Treatment of Cancer (EORTC) Clin Infect Dis. 1999 May;28(5):1071–9. doi: 10.1086/514731. - DOI - PubMed
    1. Tang H, Liu W, Lin H, Lai C. Epidemiology and prognostic factors of candidemia in cancer patients. PLoS One. 2014 Jun 5;9(6):e99103. doi: 10.1371/journal.pone.0099103. https://dx.plos.org/10.1371/journal.pone.0099103 PONE-D-14-02103 - DOI - DOI - PMC - PubMed
    1. Li D, Xia R, Zhang Q, Bai C, Li Z, Zhang P. Evaluation of candidemia in epidemiology and risk factors among cancer patients in a cancer center of China: an 8-year case-control study. BMC Infect Dis. 2017 Aug 03;17(1):536. doi: 10.1186/s12879-017-2636-x. https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-017-2636-x 10.1186/s12879-017-2636-x - DOI - DOI - PMC - PubMed
    1. Anaissie E J, Rex J H, Uzun O, Vartivarian S. Predictors of adverse outcome in cancer patients with candidemia. Am J Med. 1998 Mar;104(3):238–45. doi: 10.1016/s0002-9343(98)00030-8.S0002934398000308 - DOI - PubMed

LinkOut - more resources