Lisa M Mayer1, Jeffrey R Strich2, Sameer S Kadri2, Michail S Lionakis3, Nicholas G Evans4, D Rebecca Prevots5, Emily E Ricotta5. 1. Office of Data Science and Emerging Technologies, Office of Science Management and Operations, National Institute of Allergy and Infectious Diseases (NIAID), National Institutes of Health (NIH), Rockville, Maryland, USA. 2. Critical Care Medicine Department, NIH Clinical Center, NIH, Bethesda, Maryland, USA. 3. Fungal Pathogenesis Section, Laboratory of Clinical Immunology & Microbiology (LCIM), NIAID, NIH, Bethesda, Maryland, USA. 4. Department of Philosophy, University of Massachusetts Lowell, Lowell, Maryland, USA. 5. Epidemiology and Population Studies Unit, LCIM, NIAID, NIH, Bethesda, Maryland, USA.
Abstract
Background: Machine learning (ML) models can handle large data sets without assuming underlying relationships and can be useful for evaluating disease characteristics, yet they are more commonly used for predicting individual disease risk than for identifying factors at the population level. We offer a proof of concept applying random forest (RF) algorithms to Candida-positive hospital encounters in an electronic health record database of patients in the United States. Methods: Candida-positive encounters were extracted from the Cerner HealthFacts database; invasive infections were laboratory-positive sterile site Candida infections. Features included demographics, admission source, care setting, physician specialty, diagnostic and procedure codes, and medications received before the first positive Candida culture. We used RF to assess risk factors for 3 outcomes: any invasive candidiasis (IC) vs non-IC, within-species IC vs non-IC (eg, invasive C. glabrata vs noninvasive C. glabrata), and between-species IC (eg, invasive C. glabrata vs all other IC). Results: Fourteen of 169 (8%) variables were consistently identified as important features in the ML models. When evaluating within-species IC, for example, invasive C. glabrata vs non-invasive C. glabrata, we identified known features like central venous catheters, intensive care unit stay, and gastrointestinal operations. In contrast, important variables for invasive C. glabrata vs all other IC included renal disease and medications like diabetes therapeutics, cholesterol medications, and antiarrhythmics. Conclusions: Known and novel risk factors for IC were identified using ML, demonstrating the hypothesis-generating utility of this approach for infectious disease conditions about which less is known, specifically at the species level or for rarer diseases. Published by Oxford University Press on behalf of Infectious Diseases Society of America 2022.
Background: Machine learning (ML) models can handle large data sets without assuming underlying relationships and can be useful for evaluating disease characteristics, yet they are more commonly used for predicting individual disease risk than for identifying factors at the population level. We offer a proof of concept applying random forest (RF) algorithms to Candida-positive hospital encounters in an electronic health record database of patients in the United States. Methods: Candida-positive encounters were extracted from the Cerner HealthFacts database; invasive infections were laboratory-positive sterile site Candida infections. Features included demographics, admission source, care setting, physician specialty, diagnostic and procedure codes, and medications received before the first positive Candida culture. We used RF to assess risk factors for 3 outcomes: any invasive candidiasis (IC) vs non-IC, within-species IC vs non-IC (eg, invasive C. glabrata vs noninvasive C. glabrata), and between-species IC (eg, invasive C. glabrata vs all other IC). Results: Fourteen of 169 (8%) variables were consistently identified as important features in the ML models. When evaluating within-species IC, for example, invasive C. glabrata vs non-invasive C. glabrata, we identified known features like central venous catheters, intensive care unit stay, and gastrointestinal operations. In contrast, important variables for invasive C. glabrata vs all other IC included renal disease and medications like diabetes therapeutics, cholesterol medications, and antiarrhythmics. Conclusions: Known and novel risk factors for IC were identified using ML, demonstrating the hypothesis-generating utility of this approach for infectious disease conditions about which less is known, specifically at the species level or for rarer diseases. Published by Oxford University Press on behalf of Infectious Diseases Society of America 2022.
Authors: Mihai G Netea; Leo A B Joosten; Jos W M van der Meer; Bart-Jan Kullberg; Frank L van de Veerdonk Journal: Nat Rev Immunol Date: 2015-09-21 Impact factor: 53.106
Authors: N Peiffer-Smadja; T M Rawson; R Ahmad; A Buchard; P Georgiou; F-X Lescure; G Birgand; A H Holmes Journal: Clin Microbiol Infect Date: 2019-09-17 Impact factor: 8.067
Authors: Emily E Ricotta; Yi Ling Lai; Ahmed Babiker; Jeffrey R Strich; Sameer S Kadri; Michail S Lionakis; D Rebecca Prevots; Jennifer Adjemian Journal: J Infect Dis Date: 2021-04-08 Impact factor: 5.226