Publications by authors named "E Escriva"

Decision support tools in healthcare require a strong confidence in the developed Machine Learning (ML) models both in terms of performances and in their ability to provide users a deeper understanding of the underlying situation. This study presents a novel method to construct a risk stratification based on ML and local explanations. An open-source dataset was used to demonstrate the efficiency of this method that well identified the main subgroups of patients.

View Article and Find Full Text PDF

As Machine Learning (ML) is now widely applied in many domains, in both research and industry, an understanding of what is happening is becoming a growing demand, especially by non-experts of these models. Several approaches had thus been developed to provide clear insights of a model prediction for a particular observation but at the cost of long computation time or restrictive hypothesis that does not fully take into account interaction between attributes. This paper provides methods based on the detection of relevant groups of attributes -named - influencing a prediction and compares them with the literature.

View Article and Find Full Text PDF

Background: In developed countries, human cytomegalovirus (HCMV) is a major pathogen in congenitally infected and immunocompromised individuals, where multiple-strain infection appears linked to disease severity. The situation is less documented in developing countries. In Zambia, breast milk is a key route for transmitting HCMV and carries higher viral loads in human immunodeficiency virus (HIV)-infected women.

View Article and Find Full Text PDF

Tissue-culture adaptation of viruses can modulate infection. Laboratory passage and bacterial artificial chromosome (BAC)mid cloning of human cytomegalovirus, HCMV, resulted in genomic deletions and rearrangements altering genes encoding the virus entry complex, which affected cellular tropism, virulence, and vaccine development. Here, we analyse these effects on the reference genome for related betaherpesviruses, Roseolovirus, human herpesvirus 6A (HHV-6A) strain U1102.

View Article and Find Full Text PDF

The first example of a triple formato/hydroxido/sulfato (FHS) bridge for any metal is reported in compound [Cu2(bpym)(OH)(HCO2)(SO4)(H2O)2]·3H2O (1). Its structure shows the presence of alternating triple FHS bridges and 2,2'-bipyrimidine (bpym) ones. Although in the initial synthesis the sulfate anions were introduced accidentally, here we report the rational synthesis and the magnetic properties of this compound.

View Article and Find Full Text PDF