Ultrasound (US) is acoustic energy that interacts with human tissues, thus, producing bioeffects that may be hazardous, especially in sensitive organs (i.e., brain, eye, heart, lung, and digestive tract) and embryos/fetuses. Two basic mechanisms of US interaction with biological systems have been identified: thermal and non-thermal. As a result, thermal and mechanical indexes have been developed to provide a means of assessing the potential for biological effects from exposure to diagnostic US. The main aims of this paper were to describe the models and assumptions used to estimate the “safety” of acoustic outputs and indices and to summarize the current state of knowledge about US-induced effects on living systems deriving from in vitro models and in vivo experiments on animals. This review work has made it possible to highlight the limits associated with the use of the estimated safety values of thermal and mechanical indices relating above all to the use of new US technologies, such as contrast-enhanced ultrasound (CEUS) and acoustic radiation force impulse (ARFI) shear wave elastography (SWE). US for diagnostic and research purposes has been officially declared safe, and no harmful biological effects in humans have yet been demonstrated with new imaging modalities; however, physicians should be adequately informed on the potential risks of biological effects. US exposure, according to the ALARA (As Low As Reasonably Achievable) principle, should be as low as reasonably possible.

Introduction: Obstructive sleep apnea syndrome has become an important public health concern. Polysomnography is traditionally considered an established and effective diagnostic tool providing information on the severity of obstructive sleep apnea syndrome and the degree of sleep fragmentation. However, the numerous steps in the polysomnography test to diagnose obstructive sleep apnea syndrome are costly and time consuming. This study aimed to test the efficacy and clinical applicability of different machine learning methods based on demographic information and questionnaire data to predict obstructive sleep apnea syndrome severity. Materials and methods: We collected data about demographic characteristics, spirometry values, gas exchange (PaO₂, PaCO₂) and symptoms (Epworth Sleepiness Scale, snoring, etc.) of 313 patients with previous diagnosis of obstructive sleep apnea syndrome. After principal component analysis, we selected 19 variables which were used for further preprocessing and to eventually train seven types of classification models and five types of regression models to evaluate the prediction ability of obstructive sleep apnea syndrome severity, represented either by class or by apnea–hypopnea index. All models are trained with an increasing number of features and the results are validated through stratified 10-fold cross validation. Results: Comparative results show the superiority of support vector machine and random forest models for classification, while support vector machine and linear regression are better suited to predict apnea–hypopnea index. Also, a limited number of features are enough to achieve the maximum predictive accuracy. The best average classification accuracy on test sets is 44.7 percent, with the same average sensitivity (recall). In only 5.7 percent of cases, a severe obstructive sleep apnea syndrome (class 4) is misclassified as mild (class 2). Regression results show a minimum achieved root mean squared error of 22.17. Conclusion: The problem of predicting apnea–hypopnea index or severity classes for obstructive sleep apnea syndrome is very difficult when using only data collected prior to polysomnography test. The results achieved with the available data suggest the use of machine learning methods as tools for providing patients with a priority level for polysomnography test, but they still cannot be used for automated diagnosis.

Background and objectives: A new phenotype with overlapping characteristics between asthma and chronic obstructive pulmonary disease (COPD) called asthma–COPD overlap syndrome (ACOS) is emerging among inflammation diseases. To date, there is no agreement on specific criteria to define this syndrome, and the current guidelines are insufficient to classify the analogy and differences between overlap and COPD or asthma phenotypes. It would be necessary to identify new biomarkers able to identify these diseases clearly. Thus, the aim of this study was to identify a serum and supernatant of sputum microRNA (miRNA) expression profile of miRNA-145 and miRNA-338 in patients with asthma (n=13), COPD (n=31), and ACOS (n=8) and controls (n=7). Methods: The expression was evaluated using quantitative real-time polymerase chain reaction (qRT-PCR). For statistical analysis, the ANOVA test, Kruskal–Wallis test, Mann–Whitney U-test, and Spearman’s rank correlation were used. Results: The main finding of this work is that the expression of miRNA-338 is higher in the supernatant of different obstructive diseases than in peripheral blood, while miRNA-145 is higher only in the supernatant of asthma patients. The expression of both selected miRNAs is higher in the supernatant of asthma and COPD patients than in controls. Conclusion: Differences in sputum miRNA expression profile were observed between patients with ACOS and asthma or COPD, which underline the potential role of miRNA as a biomarker that is able to discriminate patients with ACOS, asthma, and COPD.

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease, which rapidly leads to chronic respiratory failure requiring mechanical ventilation. Currently, forced vital capacity (FVC) < 50% is considered as physiologic marker for admitting patients to Noninvasive Positive Pressure Ventilation (NPPV) intervention, although it has been recently shown the median survival of patients with baseline FVC < 75% much shorter than median survival of patients with baseline FVC > 75%, independently by any treatment.