Predicting 30-Day Readmission Risk for Patients With Chronic Obstructive Pulmonary Disease Through a Federated Machine Learning Architecture on Findable, Accessible, Interoperable, and Reusable (FAIR) Data: Development and Validation Study.

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.

FAIR4Health: Findable, Accessible, Interoperable and Reusable data to foster Health Research.

Due to the nature of health data, its sharing and reuse for research are limited by ethical, legal and technical barriers. The FAIR4Health project facilitated and promoted the application of FAIR principles in health research data, derived from the publicly funded health research initiatives to make them Findable, Accessible, Interoperable, and Reusable (FAIR). To confirm the feasibility of the FAIR4Health solution, we performed two pathfinder case studies to carry out federated machine learning algorithms on FAIRified datasets from five health research organizations. The case studies demonstrated the potential impact of the developed FAIR4Health solution on health outcomes and social care research. Finally, we promoted the FAIRified data to share and reuse in the European Union Health Research community, defining an effective EU-wide strategy for the use of FAIR principles in health research and preparing the ground for a roadmap for health research institutions. This scientific report presents a general overview of the FAIR4Health solution: from the FAIRification workflow design to translate raw data/metadata to FAIR data/metadata in the health research domain to the FAIR4Health demonstrators' performance.

Attitudes Toward Organ Donation and Transplantation Among Transplant-Related Health Care Workers and the Local Population of Montenegro.

OBJECTIVES: The aim of this research was to determine the attitudes of transplant-related health care workers and the local population of Montenegro toward organ donation and transplantation. MATERIALS AND METHODS: Our study included 200 transplant-related health care professionals (from the Clinical Center of Montenegro, the only transplant hospital in the country) and 200 volunteers from Podgorica (the capital of Montenegro). Their attitudes were evaluated using an anonymous, self-administered, multiple-choice questionnaire. RESULTS: Most health care workers would donate their organs only on specific occasions (43.6%), whereas the general population was divided between willingness to donate only on specific occasions and the need to consider the decision of donating (34.6% each). Both groups of respondents predominantly claimed that they would donate their organs to any potential recipient, regardless of sensory or physical disability. A positive opinion regarding the promotion of organ donation, as well as the need for legal regulation of the transplant process, was noted in both groups of responders. CONCLUSIONS: There is a need to increase the generosity of the Montenegrin population and its health care workers regarding organ donation at all times and not exclusively on specific occasions.

N-Terminal Prohormone of Brain Natriuretic Peptide (NT-proBNP) as a Diagnostic Biomarker of Left Ventricular Systolic Dysfunction in Patients with Acute Exacerbation of Chronic Obstructive Pulmonary Disease (AECOPD).

INTRODUCTION: Left ventricular systolic dysfunction (LVSD) and cardiac decompensation often accompany AECOPD. Differentiation between the two is difficult and mainly relies on clinical and echocardiographic diagnostic procedures. The value of biomarkers, such as NT-proBNP, as diagnostic tools is still insufficiently investigated. The main goals of this trial were to investigate the value of NT-proBNP as a diagnostic tool for LVSD in AECOPD patients and determine its cut-off value which could reliably diagnose LVSD during AECOPD. PATIENTS AND METHODS: This trial prospectively enrolled 209 patients with AECOPD. The patients were divided into four groups-AECOPD plus chronic pulmonary heart disease (CPHD) with or without left ventricular compromise (LVSD), and AECOPD patients without CPHD with or without LVSD. NT-proBNP was measured within first 48 h of hospitalization. RESULTS: Majority of patients were male (61%) active smokers (41.6%), average age of 68 years. High quality of echocardiography was obtained in 63.3 and 22.5% of the patients had LVSD. Average value of NT-proBNP in patients with LVSD was 3303.2 vs. 1092.5 pg/mL in patients without LVSD. Significant differences in NT-proBNP value (p = 0.0001) were determined between observed patient groups. At the cut-off value of 1505 pg/mL, sensitivity, specificity, and positive and negative predictive values are 76.6, 83.3, 57.1, and 92.47%, respectively. CONCLUSION: At the cut-off value of 1505 pg/mL NT-proBNP could be used as a diagnostic marker for LVSD in acute exacerbation of COPD.

Current Practice of Airway Stenting in the Adult Population in Europe: A Survey of the European Association of Bronchology and Interventional Pulmonology (EABIP).

BACKGROUND: Airway stenting (AS) commenced in Europe circa 1987 with the first placement of a dedicated silicone airway stent. Subsequently, over the last 3 decades, AS was spread throughout Europe, using different insertion techniques and different types of stents. OBJECTIVES: This study is an international survey conducted by the European Association of Bronchology and Interventional Pulmonology (EABIP) focusing on AS practice within 26 European countries. METHODS: A questionnaire was sent to all EABIP National Delegates in February 2015. National delegates were responsible for obtaining precise and objective data regarding the current AS practice in their country. The deadline for data collection was February 2016. RESULTS: France, Germany, and the UK are the 3 leading countries in terms of number of centres performing AS. These 3 nations represent the highest ranked nations within Europe in terms of gross national income. Overall, pulmonologists perform AS exclusively in 5 countries and predominately in 12. AS is performed almost exclusively in public hospitals. AS performed under general anaesthesia is the rule for the majority of institutions, and local anaesthesia is an alternative in 9 countries. Rigid bronchoscopy techniques are predominant in 20 countries. Amongst commercially available stents, both Dumon and Ultraflex are by far the most commonly deployed. Finally, 11 countries reported that AS is an economically viable activity, while 10 claimed that it is not. CONCLUSION: This EABIP survey demonstrates that there is significant heterogeneity in AS practice within Europe. Therapeutic bronchoscopy training and economic issues/reimbursement for procedures are likely to be the primary reasons explaining these findings.