Introduction: Community acquired pneumonia (CAP) may present as life-threatening infection with uncertain progression and outcome of treatment. Primary aim of the trial was determination of the cut-off value of serum interleukin-6 (IL-6) and procalcitonin (PCT) above which, 30-day mortality in hospitalized patients with CAP, could be predicted with high sensitivity and specificity. We investigated correlation between serum levels of IL-6 and PCT at admission and available scoring systems of CAP (pneumonia severity index-PSI, modified early warning score-MEWS and (Confusion, Urea nitrogen, respiratory rate, Blood pressure, ≥65 years of age-CURB65). Methods: This was prospective, non-randomized trial which included 101 patients with diagnosed CAP. PSI, MEWS and CURB65 were assessed on first day of hospitalization. IL-6 and PCT were also sampled on the first day of hospitalization. Results: Based on ROC curve analysis (AUC ± SE = 0.934 ± 0.035; 95%CI(0.864-1.0); P = 0.000) hospitalized CAP patients with elevated IL-6 level have 93.4% higher risk level for lethal outcome. Cut-off value of 20.2 pg/ml IL-6 shows sensitivity of 84% and specificity of 87% in mortality prediction. ROC curve analysis confirmed significant role of procalcitonin as a mortality predictor in CAP patients (AUC ± SE = 0.667 ± 0.062; 95%CI(0.546-0.789); P = 0.012). Patients with elevated PCT level have 66.7% higher risk level for lethal outcome. As a predictor of mortality at the cut-off value of 2.56 ng/ml PCT shows sensitivity of 76% and specificity of 61.8%. Conclusions: Both IL-6 and PCI are significant for prediction of 30-day mortality in hospitalized patients with CAP. Serum levels of IL6 correlate with major CAP scoring systems.
Background: EBUS guided trans-bronchial biopsy became routine in diagnosis of peripheral pulmonary lesions (PPL). Suction catheter-biopsy is a technique for obtaining a tissue sample from peripheral lung parenchyma. Aim of this study was to evaluate diagnostic efficiency, feasibility and safety of EBUS guided suction catheter-biopsy (SCB) in comparison to trans-bronchial biopsy (TBB) in diagnosis of PPL. The main intention was to demonstrate non-inferiority of the technique over trans-bronchial biopsy, especially when used under navigation of the EBUS.
Background: Owing to the nature of health data, their sharing and reuse for research are limited by legal, technical, and ethical implications. In this sense, to address that challenge and facilitate and promote the discovery of scientific knowledge, the Findable, Accessible, Interoperable, and Reusable (FAIR) principles help organizations to share research data in a secure, appropriate, and useful way for other researchers. Objective: The objective of this study was the FAIRification of existing health research data sets and applying a federated machine learning architecture on top of the FAIRified data sets of different health research performing organizations. The entire FAIR4Health solution was validated through the assessment of a federated model for real-time prediction of 30-day readmission risk in patients with chronic obstructive pulmonary disease (COPD). Methods: The application of the FAIR principles on health research data sets in 3 different health care settings enabled a retrospective multicenter study for the development of specific federated machine learning models for the early prediction of 30-day readmission risk in patients with COPD. This predictive model was generated upon the FAIR4Health platform. Finally, an observational prospective study with 30 days follow-up was conducted in 2 health care centers from different countries. The same inclusion and exclusion criteria were used in both retrospective and prospective studies. Results: Clinical validation was demonstrated through the implementation of federated machine learning models on top of the FAIRified data sets from different health research performing organizations. The federated model for predicting the 30-day hospital readmission risk was trained using retrospective data from 4.944 patients with COPD. The assessment of the predictive model was performed using the data of 100 recruited (22 from Spain and 78 from Serbia) out of 2070 observed (records viewed) patients during the observational prospective study, which was executed from April 2021 to September 2021. Significant accuracy (0.98) and precision (0.25) of the predictive model generated upon the FAIR4Health platform were observed. Therefore, the generated prediction of 30-day readmission risk was confirmed in 87% (87/100) of cases. Conclusions: Implementing a FAIR data policy in health research performing organizations to facilitate data sharing and reuse is relevant and needed, following the discovery, access, integration, and analysis of health research data. The FAIR4Health project proposes a technological solution in the health domain to facilitate alignment with the FAIR principles.
Mutation rate in domain of EGFR gene varies between populations of lung cancer patients. Primary aim of this study was to analyze clinical and pathological characteristics, and tumor, node, metastasis status and stage of diseases, in relation to mutation status. After histological confirmation of lung adenocarcinoma tissue obtained during bronchoscopy was consecutively sent for EGFR testing. Genomic DNA extraction was performed with the QIAamp DNA FFPE Tissue kit. Clinical data for multivariate analysis were extracted from hospital based-lung cancer registry. Among 360 tested patients, there was 67.8% males and 32.2% females, aged 61 ± 9.8 years. Majority of patients were smokers (57.0%) with Eastern Cooperative Oncology Group 1 performance status (92.2%). Mutation in EGFR gene was detected in 42 (11.7%) patients. Deletion in exon 19 was detected in 24 (6.7%) patients, mutation in exon 21 in 17 (4.7%), and mutation in exon 18 in one patient (0.3%). Patients were mostly diagnosed in stage IV adenocarcinoma (74.4%). Statistically significant differences were determined in relation to smoking (p < 0.001), T descriptor (size; p = 0.019) and gender (p = 0.002). Mutation rate in domain of EGFR gene in investigated lung cancer population is in range with reported data in Caucasian race. Smoking, T descriptor and gender were found to be related to the EGFR status.