No abstract

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 which 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 ~ 1,300 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.

Clinical data bases 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. Using subsets of these features, one can measure the similarity between two patients in several different manners. We here propose to exploit a recently developed statistical approach, the information imbalance, to compare these different similarity measures, and quantify their relative information content. We apply this approach to a data set of ~ 1,300 COVID-19 patients in Udine hospital before October 2021. Using this approach we find (asymmetric) relationships between single features and systematically compare subsets of up to 20 different features as COVID-19 severity predictors. The identified features can be measured at the moment of the admission of the patient and, if used in combination, are maximally informative of the clinical fate and of the severity of the disease. The approach can be used also if the features are available only for a fraction of the patients and, importantly, is able to select automatically features with small inter-feature correlation.