Maximally informative feature selection using Information Imbalance: Application to COVID-19 severity prediction.

Clinical databases typically include, for each patient, many heterogeneous features, for example blood exams, the clinical history before the onset of the disease, the evolution of the symptoms, the results of imaging exams, and many others. We here propose to exploit a recently developed statistical approach, the Information Imbalance, to compare different subsets of patient features and automatically select the set of features that is maximally informative for a given clinical purpose, especially in minority classes. We adapt the Information Imbalance approach to work in a clinical framework, where patient features are often categorical and are generally available only for a fraction of the patients. We apply this algorithm to a data set of ∼ 1300 patients treated for COVID-19 in Udine hospital before October 2021. Using this approach, we find combinations of features which, if used in combination, are maximally informative of the clinical fate and of the severity of the disease. The optimal number of features, which is determined automatically, turns out to be between 10 and 15. These features can be measured at admission. The approach can be used also if the features are available only for a fraction of the patients, does not require imputation and, importantly, is able to automatically select features with small inter-feature correlation. Clinical insights deriving from this study are also discussed.

Cefditoren: a clinical overview.

Cefditoren is an oral third-generation cephalosporin with a large spectrum activity against Gram-negative and Gram-positive bacteria which are reported to be responsible for respiratory tract and skin and skin structure infections. In this work we reviewed the pharmacodynamics, pharmacokinetics, and the main clinical indications of cefditoren. Similarly to other beta-lactams, cefditoren is a time-dependent antibiotic, and its "best" PK/PD target is probably 40% dosing interval time > 4- 5-fold MIC and 40-70% dosing interval time > 4- 5-fold MIC for bacteriostatic and bactericidal effect, respectively. In fasting patients oral bioavailability is low and increases when the drug is taken with food. This cephalosporin has significant bactericidal activity against S. pneumoniae (both penicillin-susceptible and penicillin-resistant strains), S. pyogenes, H. Influenzae and M. catarrhalis, as well as methicillin-susceptible S. aureus (MSSA). Regarding Enterobacterales, cefditoren has very low MICs90 against K. pneumoniae andE. coli but is not active against AmpC-, ESBL- and carbapenemase-producer' strains. Licensed indications are treatment of exacerbations of chronic bronchitis,acute rhinosinusitis, otitis media, upper respiratory tract infections (pharyngitis/tonsillitis), lower community-acquired respiratory tract infections (LRTIs), and skin and skin-structure infections (SSTI). Cefditoren might have a role in switching from parenteral to oral therapy in acute pyelonephritis and LRTIs. with a reduction of adverse effects and hospital costs. Eventually, due to its supposed binding to enterococcal penicillin binding proteins (PBPs) cefditoren, in combination with other beta-lactams, might have a role in partial oral enterococcal endocarditis treatment..