A toolkit for the management of infection or colonization by extended-spectrum beta-lactamase producing Enterobacteriaceae in Italy: implementation and outcome of a European project

A NLP Pipeline for the Automatic Extraction of a Complete Microorganism’s Picture from Microbiological Notes

The Italian “Istituto Superiore di Sanità” (ISS) identifies hospital-acquired infections (HAIs) as the most frequent and serious complications in healthcare. HAIs constitute a real health emergency and, therefore, require decisive action from both local and national health organizations. Information about the causative microorganisms of HAIs is obtained from the results of microbiological cultures of specimens collected from infected body sites, but microorganisms’ names are sometimes reported only in the notes field of the culture reports. The objective of our work was to build a NLP-based pipeline for the automatic information extraction from the notes of microbiological culture reports. We analyzed a sample composed of 499 texts of notes extracted from 1 month of anonymized laboratory referral. First, our system filtered texts in order to remove nonmeaningful sentences. Thereafter, it correctly extracted all the microorganisms’ names according to the expert’s labels and linked them to a set of very important metadata such as the translations into national/international vocabularies and standard definitions. As the major result of our pipeline, the system extracts a complete picture of the microorganism.

Empiric Treatment in HAP/VAP: “Don’t You Want to Take a Leap of Faith?”

Ventilator-associated pneumonia is a frequent cause of ICU-acquired infections. These infections are associated with high morbidity and mortality. The increase in antibiotic resistance, particularly among Gram-negative bacilli, makes the choice of empiric antibiotic therapy complex for physicians. Multidrug-resistant organisms (MDROs) related infections are associated with a high risk of initial therapeutic inadequacy. It is, therefore, necessary to quickly identify the bacterial species involved and their susceptibility to antibiotics. New diagnostic tools have recently been commercialized to assist in the management of these infections. Moreover, the recent enrichment of the therapeutic arsenal effective on Gram-negative bacilli raises the question of their place in the therapeutic management of these infections. Most national and international guidelines recommend limiting their use to microbiologically documented infections. However, many clinical situations and, in particular, the knowledge of digestive or respiratory carriage by MDROs should lead to the discussion of the use of these new molecules, especially the new combinations with beta-lactamase inhibitors in empirical therapy. In this review, we present the current epidemiological data, particularly in terms of MDRO, as well as the clinical and microbiological elements that may be taken into account in the discussion of empirical antibiotic therapy for patients managed for ventilator-associated pneumonia.

Machine Learning and Multidrug-Resistant Gram-Negative Bacteria: An Interesting Combination for Current and Future Research

The dissemination of multidrug-resistant Gram-negative bacteria (MDR-GNB) is associated with increased morbidity and mortality in several countries. Machine learning (ML) is a branch of artificial intelligence that consists of conferring on computers the ability to learn from data. In this narrative review, we discuss three existing examples of the application of ML algorithms for assessing three different types of risk: (i) the risk of developing a MDR-GNB infection, (ii) the risk of MDR-GNB etiology in patients with an already clinically evident infection, and (iii) the risk of anticipating the emergence of MDR in GNB through the misuse of antibiotics. In the next few years, we expect to witness an increasingly large number of research studies perfecting the application of ML techniques in the field of MDR-GNB infections. Very importantly, this cannot be separated from the availability of a continuously refined and updated ethical framework allowing an appropriate use of the large datasets of medical data needed to build efficient ML-based support systems that could be shared through appropriate standard infrastructures.

Healthcare Associated Infections: An Interoperable Infrastructure for Multidrug Resistant Organism Surveillance

Prevention and surveillance of healthcare associated infections caused by multidrug resistant organisms (MDROs) has been given increasing attention in recent years and is nowadays a major priority for health care systems. The creation of automated regional, national and international surveillance networks plays a key role in this respect. A surveillance system has been designed for the Abruzzo region in Italy, focusing on the monitoring of the MDROs prevalence in patients, on the appropriateness of antibiotic prescription in hospitalized patients and on foreseeable interactions with other networks at national and international level. The system has been designed according to the Service Oriented Architecture (SOA) principles, and Healthcare Service Specification (HSSP) standards and Clinical Document Architecture Release 2 (CDAR2) have been adopted. A description is given with special reference to implementation state, specific design and implementation choices and next foreseeable steps. The first release will be delivered at the Complex Operating Unit of Infectious Diseases of the Local Health Authority of Pescara (Italy).

A whole-health-economy approach to antimicrobial stewardship: Analysis of current models and future direction

In a Policy Forum, Alison Holmes and colleagues discuss coordinated approaches to antimicrobial stewardship.