Search

Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are "black box" to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffers from poor generalization ability in the presence of dataset shifts. Here, we present a comparison between an explainable-by-design ("white box") model (Bayesian Network (BN)) versus a black box model (Random Forest), both studied with the aim of supporting clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic. [ABSTRACT FROM AUTHOR]

Sarcoidosis is a multisystem disease, which is diagnosed on a compatible clinical presentation, non-necrotizing granulomatous inflammation in one or more tissue samples, and exclusion of alternative causes of granulomatous disease. Considering its heterogeneity, numerous aspects of the disease remain to be elucidated. In this context, the identification and integration of biomarkers may hold significance in clinical practice, aiding in appropriate selection of patients for targeted clinical trials. This work aims to discuss and analyze how validated biomarkers are currently integrated in disease category definitions. Future studies are mandatory to unravel the diverse contributions of genetics, socioeconomic status, environmental exposures, and other sociodemographic variables to disease severity and phenotypic presentation. Furthermore, the implementation of transcriptomics, multidisciplinary approaches, and consideration of patients' perspectives, reporting innovative insights, could be pivotal for a better understanding of disease pathogenesis and the optimization of clinical assistance. [ABSTRACT FROM AUTHOR]

Background: Tracheal stenosis represents a fearsome complication that substantially impairs quality of life. The recent SARS-CoV-2 pandemic increased the number of patients requiring invasive ventilation through prolonged intubation or tracheostomy, increasing the risk of tracheal stenosis. Study design and methods: In this prospective, observational, multicenter study performed in Lombardy (Italy), we have exanimated 281 patients who underwent prolonged intubation (more than 7 days) or tracheostomy for severe COVID-19. Patients underwent CT scan and spirometry 2 months after hospital discharge and a subsequent clinical follow-up after an additional 6 months (overall 8 months of follow-up duration) to detect any tracheal lumen reduction above 1%. The last follow-up evaluation was completed on 31 August 2022. Results: In the study period, 24 patients (8.5%, CI 5.6–12.4) developed tracheal stenosis in a median time of 112 days and within a period of 200 days from intubation. Compared to patients without tracheal stenosis, tracheostomy was performed more frequently in patients that developed stenosis (75% vs 54%, p = 0.034). Tracheostomy and alcohol consumption (1 unit of alcohol per day) increased risk of developing tracheal stenosis of 2.6-fold (p = 0.047; IC 0.99–6.8) and 5.4-fold (p = 0.002; CI 1.9–16), respectively. Conclusions: In a large cohort of patients, the incidence of tracheal stenosis increased during pandemic, probably related to the increased use of prolonged intubation. Patients with histories of prolonged intubation should be monitored for at least 200 days from invasive ventilation in order to detect tracheal stenosis at early stage. Alcohol use and tracheostomy are risk factors for developing tracheal stenosis. [ABSTRACT FROM AUTHOR]

Interstitial lung diseases (ILDs) are a heterogeneous group of pulmonary disorders characterized by variable degrees of inflammation, interstitial thickening, and fibrosis leading to distortion of the pulmonary architecture and gas exchange impairment. Among them, idiopathic pulmonary fibrosis (IPF) displays the worst prognosis. The only therapeutic options consist of the two antifibrotic drugs, pirfenidone and nintedanib, which limit fibrosis progression but do not reverse the lung damage. The shift of the pathogenetic paradigm from inflammatory disease to epithelium-derived disease has definitively established the primary role of type II alveolar cells, which lose their epithelial phenotype and acquire a mesenchymal phenotype with production of collagen and extracellular matrix (EMC) deposition. Some predisposing environmental and genetic factors (e.g., smoke, pollution, gastroesophageal reflux, variants of telomere and surfactant genes) leading to accelerated senescence set a pro-fibrogentic microenvironment and contribute to the loss of regenerative properties of type II epithelial cells in response to pathogenic noxae. This review provides a complete overview of the different pathogenetic mechanisms leading to the development of IPF. Then, we summarize the currently approved therapies and the main clinical trials ongoing. Finally, we explore the potentialities offered by agents not only interfering with the processes of fibrosis but also restoring the physiological properties of alveolar regeneration, with a particular focus on potentialities and concerns about cell therapies based on mesenchymal stem cells (MSCs), whose anti-inflammatory and immunomodulant properties have been exploited in other fibrotic diseases, such as graft versus host disease (GVHD) and COVID-19-related ARDS. [ABSTRACT FROM AUTHOR]