Identifying the most important data for research in the field of infectious diseases: thinking on the basis of artificial intelligence.

OBJECTIVE: Clinical data on which artificial intelligence (AI) algorithms are trained and tested provide the basis to improve diagnosis or treatment of infectious diseases (ID). We aimed to identify important data for ID research to prioritise efforts being undertaken in AI programmes. METHODS: We searched for 1,000 articlesfrom high-impact ID journals on PubMed, selecting 288 of the latest articles from 10 top journals. We classified them into structured or unstructured data. Variables were homogenised and grouped into the following categories: epidemiology, admission, demographics, comorbidities, clinical manifestations, laboratory, microbiology, other diagnoses, treatment, outcomes and other non-categorizable variables. RESULTS: 4,488 individual variables were collected, from the 288 articles. 3,670 (81.8%) variables were classified as structured data whilst 818 (18.2%) as unstructured data. From the structured data, 2,319 (63.2%) variables were classified as direct-retrievable from electronic health records-whilst 1,351 (36.8%) were indirect. The most frequent unstructured data were related to clinical manifestations and were repeated across articles. Data on demographics, comorbidities and microbiology constituted the most frequent group of variables. CONCLUSIONS: This article identified that structured variables have comprised the most important data in research to generate knowledge in the field of ID. Extracting these data should be a priority when a medical centre intends to start an AI programme for ID. We also documented that the most important unstructured data in this field are those related to clinical manifestations. Such data could easily undergo some structuring with the use of semi-structured medical records focusing on a few symptoms.

[Technical and functional standards and implementation of a clinical information system in intensive care units]. / Estándares técnicos y funcionales, y proceso de implantación, de un sistema de información clínica en unidades de cuidados intensivos.

INTRODUCTION: Clinical Information Systems (CIS) are becoming a useful tool for managing patients and data in the ICU. However, the existing CIS differ in their capabilities and technical requirements. It is therefore essential for intensivists, as the end clients of these applications, to define the suitable minimum specifications required in order to be operative and helpful. OBJECTIVES: The Spanish Society of Intensive Care Medicine and Coronary Units, through its Organization and Management Workgroup, has designated a group of clinical and software experts to draft a document with the recommendable technical and operating requirements of these systems. METHODS: The group was formed by ten people supported by managers or engineers from the five principal industries producing CIS in Spain. The project involved the following phases: a) Completion of a check list. This step was considered necessary in order to establish the precise current situation of CIS applications. b) Discussion of the results by the group of experts in a meeting and in online format. RESULTS: The requirements were grouped into four sections: technical, functional, safety and data management. All requirements were classified as basic and optional in order to allow the end user to choose among different options according to the existing budget, though ensuring a minimal set of useful characteristics. A chronogram for the installation process was also proposed.

Clinical use and tolerability of voriconazole in the treatment of fungal infections in critically ill patients.

The clinical use and tolerability of voriconazole in daily practice for the treatment of fungal infection in critically ill patients was assessed in an open-label, non-comparative, observational study. All patients admitted to medical-surgical Intensive Care Units (ICUs) of 21 hospitals in Spain between February 2003 and January 2004, who were treated with voriconazole because of known or suspected fungal infection, were included. A total of 130 patients received voriconazole (6.2 cases per ICU). Fungal infections were classified as proven in 50 patients (38.5%) and probable in 38 (29.2%). The etiology was established in 103 patients, with Candida albicans and Aspergillus fumigatus as the most common pathogens. In 98 (75.4%) patients, voriconazole was initially administered intravenously. Fifty-three patients (40.8%) were treated with other antifungal agents prior to the use of voriconazole. In 21 patients (16.2%), voriconazole was administered in combination with other antifungal drugs. Clinical responses were cure and improvement in 65 (50%) patients, failure in 26 (20%), and undetermined in 39 (30%). The crude ICU mortality was 49.2%. According to multivariate analysis, ICU mortality was significantly associated with pneumonia (OR = 3.30, 95% CI 1.07-10.18) and infection caused by Aspergillus spp. (OR = 3.70, 95% Cl 1.12-12.28), whereas eradication of the causative microorganisms was inversely associated (OR = 0.13, 95% CI 0.05-0.34). Adverse events were recorded in 65 patients, probably or possibly related to the study drug in 21. In conclusion, in critically ill patients admitted to the ICU, the use of voriconazole was affective in 50% of cases. The drug was well tolerated and discontinuation of voriconazole treatment due to adverse events was not necessary.