Clinical predictive models of invasive Candida infection: a systematic literature review

Machine Learning in Infectious Disease for Risk Factor Identification and Hypothesis Generation: Proof of Concept Using Invasive Candidiasis

Background

Machine learning (ML) models can handle large datasets without assuming underlying relationships and can be useful for evaluating disease characteristics; yet, they are more commonly used for predicting individual disease risk rather than 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 U.S.

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 prior to the first positive Candida culture. We used RF to assess risk factors for three outcomes: any invasive candidiasis (IC) vs non-IC, within-species IC vs non-IC (e.g. invasive C. glabrata vs non-invasive C. glabrata), and between-species IC (e.g. invasive C. glabrata vs all other IC).

Results

14 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, ICU 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 hypotheses generating utility of this approach for infectious disease conditions about which less is known, specifically at the species-level or for rarer diseases.

Synthesis and Study of Antifungal Properties of New Cationic Beta-Glucan Derivatives

The interaction of positively charged polymers (polycations) with a biological membrane is considered to be the cause of the frequently observed toxicity of these macromolecules. If it is possible to obtain polymers with a predominantly negative effect on bacterial and fungal cells, such systems would have great potential in the treatment of infectious diseases, especially now when reports indicate the growing risk of fungal co-infections in COVID-19 patients. We describe in this article cationic derivatives of natural beta-glucan polymers obtained by reacting the polysaccharide isolated from Saccharomyces boulardii (SB) and Cetraria islandica (CI) with glycidyl trimethyl ammonium chloride (GTMAC). Two synthesis strategies were applied to optimize the product yield. Fungal diseases particularly affect low-income countries, hence the emphasis on the simplicity of the synthesis of such drugs so they can be produced without outside help. The three structures obtained showed selective anti-mycotic properties (against, i.e., Scopulariopsis brevicaulis, Aspergillus brasiliensis, and Fusarium solani), and their toxicity established using fibroblast 3T3-L1 cell line was negligible in a wide range of concentrations. For one of the polymers (SB derivative), using in vivo model of Aspergillus brasiliensis infection in Galleria mellonella insect model, we confirmed the promising results obtained in the preliminary study.