Noninvasive Support Research Articles

Predictive and Explainable Artificial Intelligence for Neuroimaging Applications

Background: The aim of this review is to highlight the new advance of predictive and explainable artificial intelligence for neuroimaging applications. Methods: Data came from 30 original studies in PubMed with the following search terms: “neuroimaging” (title) together with “machine learning” (title) or ”deep learning” (title). The 30 original studies were eligible according to the following criteria: the participants with the dependent variable of brain image or associated disease; the interventions/comparisons of artificial intelligence; the outcomes of accuracy, the area under the curve (AUC), and/or variable importance; the publication year of 2019 or later; and the publication language of English. Results: The performance outcomes reported were within 58–96 for accuracy (%), 66–97 for sensitivity (%), 76–98 for specificity (%), and 70–98 for the AUC (%). The support vector machine and the convolutional neural network registered the best performance (AUC 98%) for the classifications of low- vs. high-grade glioma and brain conditions, respectively. Likewise, the random forest delivered the best performance (root mean square error 1) for the regression of brain conditions. The following factors were discovered to be major predictors of brain image or associated disease: (demographic) age, education, sex; (health-related) alpha desynchronization, Alzheimer’s disease stage, CD4, depression, distress, mild behavioral impairment, RNA sequencing; (neuroimaging) abnormal amyloid-β, amplitude of low-frequency fluctuation, cortical thickness, functional connectivity, fractal dimension measure, gray matter volume, left amygdala activity, left hippocampal volume, plasma neurofilament light, right cerebellum, regional homogeneity, right middle occipital gyrus, surface area, sub-cortical volume. Conclusion: Predictive and explainable artificial intelligence provide an effective, non-invasive decision support system for neuroimaging applications.

Respiratory rate-oxygenation index on the 3rd day is the best predictor of treatment failure in COVID-19 patients.

Predictors of outcomes are essential to identifying severe COVID-19 cases and optimizing treatment and care settings. The respiratory rate-oxygenation (ROX) index, originally introduced for predicting the failure of non-invasive support in acute hypoxemic respiratory failure (AHRF), has not been extensively studied over time during hospitalization. This multicenter prospective observational study analyzed COVID-19-related AHRF patients admitted to eight Italian hospitals during the second pandemic wave. The study assessed the ROX index using receiver operator characteristic curves and areas under the curve with 95% confidence intervals to predict treatment failure, defined as endotracheal intubation (ETI) or death. A total of 227 patients (69.2% males) were enrolled, with a median arterial partial pressure of oxygen (PaO2)/fraction of inspired oxygen (FiO2) ratio at admission of 248 (interquartile range: 170-295). Nearly one-third (29.5%) required ETI or died during hospitalization. Those who experienced treatment failure were older (median age 70 versus 61 years, p<0.001), more likely to be current or former smokers (8.5% versus 6.4% and 42.4% versus 25.5%, p=0.039), had a higher prevalence of cardiovascular diseases (74.6% versus 46.3%, p<0.001), and had a lower PaO2/FiO2 ratio at presentation (median 229 versus 254, p=0.014). Gender, body mass index, and other comorbidities showed no significant differences. In patients who failed treatment, the ROX index was higher at presentation and worsened sharply by days 3 and 4. Conversely, in patients who survived without requiring ETI, the ROX index remained stable and reduced after 5-6 days. The ROX index's predictive ability improved notably by the third day of hospitalization, with the best cut-off value identified at 8.53 (sensitivity 75%, specificity 68%). Kaplan-Meier curves indicated that a ROX index of 8.53 or lower on days 1, 2, or 3 was associated with a higher risk of treatment failure. Thus, a single ROX index assessment on day 3 is more informative than its variability over time, with values of 8.53 or lower predicting non-invasive respiratory support failure in hospitalized COVID-19 patients.

Myocardial Ischemia after Severe Scorpion Envenomation: A Narrative Review.

Myocardial ischemia after severe scorpion envenomation is rarely reported. The aim of this review was to elaborate on a review of myocardial ischemia after severe scorpion envenomation and to detail the mechanism of this myocardial hypoperfusion. We used the PubMed database and entered the following keywords in MeSH research: scorpion envenomation, myocardial ischemia, myocardial perfusion scintigraphy, echocardiography, and troponins. The literature analysis confirmed that severe scorpion envenomation can be complicated by temporary myocardial ischemia, based on electrocardiographic, histopathologic, echocardiographic, myocardial perfusion scintigraphy, and biological studies. The correlation between clinical manifestations, laboratory and electrocardiographic evidence of myocardial damage, echocardiographic studies, perfusion scintigraphy abnormalities, and histopathologic findings are suggestive of lesions of cardiac fibers secondary to myocardial ischemia. Myocardial hypoperfusion may be due to multiple factors. First, catecholamine storms can induce microvascular constriction. On the other hand, the release of catecholamines through a complex neurohormonal interaction with other neuropeptides and cytokine release can produce/induce major coronary microvascular constriction and/or microvascular injury, leading to microvascular acute coronary syndrome with Takotsubo cardiomyopathy. The management of severe scorpion envenomation with severe myocardial failure and pulmonary edema is based on oxygen with invasive or noninvasive ventilator support. Dobutamine improves cardiac function after scorpion envenomation. Antiplatelet therapy is not recommended. In conclusion, severe scorpion envenomation can be complicated by temporary myocardial ischemia, which can be due to multiple factors.

The effect of physiotherapy intervention on functional outcomes among COVID-19 patients: Clinical experimental study.

COVID-19 is a highly contagious virus that causes pneumonia, which quickly progresses to acute respiratory distress. In the case of COVID-19, physiotherapy is critical in non-invasive support management, postural changes, chest physiotherapy (CPT), and bed mobility. This study aims to look into the effects of physiotherapy intervention on functional outcome levels in COVID-19 patients in the acute stage. A total of 60 severe COVID-19 patients (54 males and 6 females) with a mean age of 50years were studied. The intervention group (n=30) had two daily physiotherapy sessions that included positioning, CPT, cardio exercises, breathing exercises, and early mobility, whereas the control group (n=30) received only standard medical care. Patients were tested twice at the baseline and discharge using peripheral oxygen saturation, respiratory rate (RR) test, dyspnea rate, two-min walk test, and spirometer scores, forced vital capacity (FVC) and forced expiratory volume in one second (FEV1). The two groups improved significantly between the baseline and discharge ratings. The intervention group, on the other hand, significantly improved all outcome indicators at discharge (p-value=0.00). This study found that physiotherapy management improved oxygen saturation, RR, dyspnea, and lung function tests in COVID-19 patients except in FVC (p-value=0.402) and FEV1(p-value=0.114). Physiotherapist interventions with COVID-19 patients increase respiratory function and treatment time.

Protective mechanical ventilation in critically ill patients after surgery

Purpose of review This review aims to provide an updated overview of lung protective strategies in critically ill patients after surgery, focusing on the utility of postoperative open-lung ventilation during the transition from the operating room to the intensive care unit. Recent findings Mechanically ventilated patients after surgery represent a challenge in the intensive care unit. Different protective strategies have been proposed to minimize the risk of ventilator-induced lung injury (VILI) and facilitate adequate weaning from mechanical ventilation. Fast-track extubation protocols, increasingly standard in the care of critically ill patients postsurgery, have demonstrated improvements in recovery and reductions in acute lung injury, primarily based on retrospective studies. Open-lung ventilation strategies, such as individualization of positive-end expiratory pressure based on driving pressure and postoperative noninvasive ventilation support with high-flow nasal cannula, are becoming standard of care in high-risk surgical patients after major abdominal or thoracic surgeries. Summary Mechanical ventilation in surgical patients should adhere to lung protective strategies (i.e., individualizing positive end expiratory pressure and prioritize alveolar recruitment) during the transition from the operating room to the intensive care unit.

Assessment of right ventricular sequelae by speckle tracking echocardiography in recovered COVID-19 patients

Background TTE is the main modality used to assess RV function, but conventional TTE parameters have limited diagnostic value because they may fail to detect early abnormalities in RV systolic function. Due to its ability to detect subclinical impairment of cardiac function, 2D STE has been widely used to investigate RV function. In this study, we aimed to investigate whether there are sequelae of RV function in recovered COVID-19 patients with pulmonary involvement. Methods This is a prospective observational cohort study of 57 healthy volunteers and 54 patients. Participants had no history of chronic illness and no evidence of respiratory or cardiac symptoms. The patients had been hospitalised with COVID-19 with pulmonary involvement but did not require intensive care unit follow-up or non-invasive mechanical ventilation support. TTE was performed. Demographic and clinical characteristics and laboratory test results were collected. Results LVEF, TAPSE, St and FAC were significantly lower in the patient group. LV-LS 3-chamber, LV-GLS, RV-FWS, RV-GLS were significantly lower in the patient group. Conclusions RV-LS and LV-GLS were shown to decrease in the patient group. Although no obvious pathological values were observed in RV parameters on conventional echocardiography, TAPSE, St and FAC values were lower in the patient group.

Accuracy and Interpretation of Transcutaneous Carbon Dioxide Monitoring in Critically Ill Children.

Transcutaneous carbon dioxide (Tc co2 ) monitoring can noninvasively assess ventilation by estimating carbon dioxide ( CO2 ) levels in the blood. We aimed to evaluate the accuracy of Tc co2 monitoring in critically ill children by comparing it to the partial pressure of arterial carbon dioxide (Pa co2 ). In addition, we sought to determine the variation between Tc co2 and Pa co2 acceptable to clinicians to modify patient care and to determine which patient-level factors may affect the accuracy of Tc co2 measurements. Retrospective observational cohort study. Single, quaternary care PICU from July 1, 2012, to August 1, 2020. Included participants were admitted to the PICU and received noninvasive ventilation support (i.e., continuous or bilevel positive airway pressure), conventional mechanical ventilation, or high-frequency oscillatory or percussive ventilation with Tc co2 measurements obtained within 15 minutes of Pa co2 measurement. None. Three thousand four hundred seven paired arterial blood gas and Tc co2 measurements were obtained from 264 patients. Bland-Altman analysis revealed a bias of -4.4 mm Hg (95% CI, -27 to 18.3 mm Hg) for Tc co2 levels against Pa co2 levels on the first measurement pair for each patient, which fell within the acceptable range of ±5 mm Hg stated by surveyed clinicians, albeit with wide limits of agreement. The sensitivity and specificity of Tc co2 to diagnose hypercarbia were 93% and 71%, respectively. Vasoactive-Infusion Score (VIS), age, and self-identified Black/African American race confounded the relationship between Tc co2 with Pa co2 but percent fluid overload, weight-for-age, probe location, and severity of illness were not significantly associated with Tc co2 accuracy. Tc co2 monitoring may be a useful adjunct to monitor ventilation in children with respiratory failure, but providers must be aware of the limitations to its accuracy.

Comparison of clinical characteristics and severity of COVID-19 with or without viral co-infection in hospitalized children

BackgroundCo-infection with other pathogens can alter the severity and clinical outcomes of viral infections. However, the information regarding viral co-infections in pediatric coronavirus disease 2019 (COVID-19) cases is still limited. MethodsThis is a nationwide, retrospective cohort study using the data from the COVID-19 Registry Japan. The pediatric (<18 years), laboratory confirmed, hospitalized COVID-19 patients in the Omicron variant of concern predominant period (January 2022 to January 2024) were included. Co-infection was investigated by multiplex PCR. We compared clinical characteristics, symptoms, severity, and outcomes between children with and without co-infection. ResultsAmong 245 hospitalized pediatric COVID-19 patients, 78 (31.8 %) had co-infections. The patient backgrounds of the “co-infection” and “SARS-CoV-2 alone” groups were similar, although age distribution was different, with a lower number of patients over 12 years in the co-infection group (n = 2, 2.6 % vs. n = 29, 17.4 %; P < 0.001). Among the patients with co-infection, the most common pathogen was enterovirus/rhinovirus (51.3 %), followed by parainfluenza virus (23.1 %) and adenovirus (12.8 %). Patients with co-infection more commonly had respiratory symptoms, including SpO2 < 96 %, shortness of breath, runny nose, and wheezing. Requirement of non-invasive oxygen support was higher in the co-infection group (n = 27, 34.6 % vs. n = 28, 16.8 %, P = 0.006). By multivariable logistic regression analysis, co-infection and presence of any comorbidity were identified as significant risk factors for necessity of oxygen therapy (odds ratio [95 % confidence interval] 2.44 [1.29–4.63] and 3.99 [2.07–7.82], respectively). ConclusionsViral co-infection may increase the risk of respiratory distress in pediatric COVID-19 patients.

The Effect of Two Different Nasal Interfaces Used in Post-Extubation Non-Invasive Respiratory Support on Extubation Success in Newborns

Background: Non-invasive ventilation support is frequently used in newborns after extubation. The efficiency of non-invasive ventilation support is associated to type of nasal interface used. We aimed to investigate the effect of nasal interface type in our study on extubation success. Materials and Methods: We retrospectively evaluated a total of 105 term and preterm patients who were extubated to non-invasive ventilation. We divided the patients into two groups according to nasal interface type: RAM cannula or short binasal prongs (SBPs). We examined extubation failure between the two groups. Results: While 63 of the patients were in RAM cannula group, 42 of them were in SBPs group, and the demographic characteristics of the patients were similar. There was no statistically significant differen-ce in the extubation failure rates between the groups (RAM; %44.4 vs SBPs; %38.1, p=0.518). The Ram cannula group had a higher beginning median positive end-expiratory pressure value (7.0 vs 6.5 cmH2O, p=0.038; respectively) and a lower median respiratory rate (60 vs 62/minute, p=0.032; res-pectively) than the SBPs group. Conclusions: We believe that the easy-to-use RAM cannula can be used in selected patients, especially by setting the PEEP value approximately 1 cmH2O higher.

May Recovered COVID-19 Patients Have Impaired Myocardial Work?

Background: The aim of this study was to investigate whether there are sequelae in left ventricular (LV) systolic function by comparing LV function in fully recovered COVID-19 patients with pulmonary involvement and healthy controls without COVID-19 by conventional echocardiography and myocardial work. Materials and Methods: 55 healthy volunteers and 61 patients hospitalized with COVID-19 with pulmonary in-volvement were included. Patients did not need non-invasive or invasive mechanical ventilation support during hospitalization. Patients were included in the study if they were asymptomatic for at least six months after recov-ery from COVID-19. Transthoracic echocardiography (TTE) was performed. Demographic and clinical characteris-tics and laboratory test results were collected. Clinical characteristics, blood tests, TTE, speckle-tracking echocar-diography (STE) and myocardial work results were compared. Results: No statistically significant differences were found in the longitudinal strain parameters of the LV among the study groups. The patient group exhibited notably reduced levels of global work index (GWI), global con-structed work (GCW), and global work efficiency (GWE). The patient group exhibited a notably elevated global wasted work (GWW). Conclusions: The group of fully recovered asymptomatic COVID-19 patients with pulmonary involvement showed significantly lower values for GWI, GCW, and GWE, while GWW showed a significantly higher value. Myocardial work parameters may be useful in determining myocardial sequelae.

Development of a mechanical characterisation device for intracranial aneurysms: Calibration on polymeric phantom arteries

Intracranial aneurysm is a major health issue related to biomechanical arterial wall degradation. Currently, no method allows predicting rupture risk based on in vivo quantitative mechanical data. This work is part of a large-scale project aimed at providing clinicians with a non-invasive patient-specific decision support tool, based on the in vivo mechanical characterisation of the aneurysm wall. Thus, the primary objective of the project was to develop a deformation device prototype (DDP) of the artery wall and to calibrate it on polymeric phantom arteries. The deformations induced on the phantom arteries were quantified experimentally using a Digital Image Correlation (DIC) system. The results indicated that the DIC system was able to measure the small displacements generated by the DDP. We also observed that the flow mimicking the blood flow did not significantly disturb the measurements of the artery wall displacement caused by the DDP. Finally, a limit displacement value generated by the DDP was evaluated. This value corresponds to the lowest displacement value detectable by the clinical imaging system that will be tested on animals in the future (Spectral Photon Counting CT).

Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) in the neonatal intensive care unit (NICU): an Australian NICU experience

BackgroundPreterm infants often require non-invasive breathing support while their lungs and control of respiration are still developing. Non-invasive neurally adjusted ventilatory assist (NIV-NAVA) is an emerging technology that allows infants to breathe spontaneously while receiving support breaths proportional to their effort. This study describes the first Australian Neonatal Intensive Care Unit (NICU) experience of NIV-NAVA.MethodsRetrospective cohort study of infants admitted to a major tertiary NICU between October 2017 and April 2021 supported with NIV-NAVA. Infants were divided into three groups based on the indication to initiate NIV-NAVA (post-extubation; apnoea; escalation). Successful application of NIV-NAVA was based on the need for re-intubation within 48 h of application.ResultsThere were 169 NIV-NAVA episodes in 122 infants (82 post-extubation; 21 apnoea; 66 escalation). The median (range) gestational age at birth was 25 + 5 weeks (23 + 1 to 43 + 3 weeks) and median (range) birthweight was 963 g (365–4320 g). At NIV-NAVA application, mean (SD) age was 17 days (18.2), and median (range) weight was 850 g (501–4310 g). Infants did not require intubation within 48 h in 145/169 (85.2%) episodes [72/82 (87.8%) extubation; 21/21 (100%) apnoea; 52/66 (78.8%) escalation).ConclusionNIV-NAVA was successfully integrated for the three main indications (escalation; post-extubation; apnoea). Prospective clinical trials are still required to establish its effectiveness versus other modes of non-invasive support.

Extubated, Rehabilitation-Focused Extracorporeal Membrane Oxygenation for Pediatric Coronavirus Disease 2019: A Case Series.

During the coronavirus 2019 (COVID-19) pandemic, children suffered severe lung injury resulting in acute respiratory distress syndrome requiring support with extracorporeal membrane oxygenation (ECMO). In this case series, we described our center's experience employing a rehabilitation-focused ECMO strategy including extubation during ECMO support in four pediatric patients with acute COVID-19 pneumonia hospitalized from September 2021 to January 2022. All four patients tolerated extubation within 30 days of ECMO initiation and achieved mobility while on ECMO support. Duration of ECMO support was 35-152 days and hospital lengths of stay were 52-167 days. Three of four patients survived. Two of three survivors had normal functional status at discharge except for ongoing respiratory support. The third survivor had significant motor deficits due to critical illness polyneuropathy and was supported with daytime oxygen and nocturnal noninvasive support. Overall, these patients demonstrated good outcomes and tolerance of a rehabilitation-focused ECMO strategy.

Implementation of a palliative care service in a tertiary hospital in a developing country: Methods, strategies and results.

e24056 Background: In Rio de Janeiro, only 11 palliative care facilities exist, creating challenges in meeting the complex needs of patients with metastatic cancer. Our study aims to implement a palliative care service within an existing oncology practice. This approach holds promise as a model that could guide similar practices in low- and middle-income countries, offering a blueprint for the implementation of palliative care services on a broader scale. Methods: This descriptive study spans from February to December 2023, involving the monitoring of 176 patients. Eligible patients met criteria such as a FAST scale for dementia syndrome ≥ 7A, stage IV disease, ranking 5 stroke, terminal organic failure, uncontrolled symptoms, or requiring end-of-life care. The PC team, denoted as “Continued Care”, comprises a medical leader, 3 routine doctors, and 1 nurse. Activities undertaken by the team encompass consults requested by internal medicine and intensive care unit (ICU) teams, outpatient care, continuous education, and daily monitoring of patients with advance care plan (ACP). Results: Among 176 patients initially enrolled, outcomes were completed for 171 patients. Remarkably, 80% of those receiving PC assistance had an ACP in place, with 78% opting for exclusive non-invasive support. The overall death rate was 38%. Notably, among patients enrolled in the PC program, the ICU death rate was 31%. Conclusions: Institutional PC policies associated with the integration of a dedicated team into the hospital's routine, and investments in disseminating knowledge about irreversible illness processes and comfort strategies, emerge as a pivotal component in establishing a comprehensive and integrated model of PC services. This approach appears to surpass the effectiveness of traditional consult or sectorized model, emphasizing the importance of an institutionalized and holistic framework for delivering quality PC.

Comparison of clinical features of cystic fibrosis patients eligible but not on CFTR modulators to ineligible for CFTR modulators.

Cystic fibrosis transmembrane conductance regulator (CFTR) modulator drugs target the underlying defect and improve CFTR function. They are a part of standard care in many countries, but not all patients are eligible for these drugs due to age and genotype. Here, we aimed to determine the characteristics of non-eligible patients for CFTR modulators in the CF registry of Turkey (CFRT) to highlight their clinical needs. This retrospective cohort study included CF patient data from the CFRT in 2021. The decision of eligibility for the CFTR modulator was determined according to the 'Vertex treatment-Finder' on the Vertex® website. Demographic and clinical characteristics of patients were compared between eligible (group 1) and ineligible (group 2) groups for CFTR modulators. Among the study population (N = 1527), 873 (57.2%) were in group 1 and 654 (42.8%) were in group 2. There was no statistical difference between groups regarding sex, meconium ileus history, diagnoses via newborn screening, FEV1 z-score, CF-associated complications, organ transplant history, and death. Patients in group 2 had a higher incidence of pancreatic insufficiency (87.7% vs. 83.2%, p = .010), lower median height z-scores (-0.87 vs. -0.55, p < .001), lower median body mass index z-scores (-0.65 vs. -0.50, p < .001), longer days receiving antibiotics due to pulmonary exacerbation (0 [interquartile range, IQR: 0-2] vs. 0 [IQR: 0-7], p = 0.001), and more non-invasive ventilation support (2.6% vs. 0.9%, p = 0.008) than patients in group 1. The ineligible group had worse clinical outcomes than the eligible group. This highlights their need for life-changing drugs to improve clinical outcomes.

Effect of immediate initiation of invasive ventilation on mortality in acute hypoxemic respiratory failure: a target trial emulation

PurposeInvasive ventilation is a fundamental treatment in intensive care but its precise timing is difficult to determine. This study aims at assessing the effect of initiating invasive ventilation versus waiting, in patients with hypoxemic respiratory failure without immediate reason for intubation on one-year mortality.MethodsEmulation of a target trial to estimate the benefit of immediately initiating invasive ventilation in hypoxemic respiratory failure, versus waiting, among patients within the first 48-h of hypoxemia. The eligible population included non-intubated patients with SpO2/FiO2 ≤ 200 and SpO2 ≤ 97%. The target trial was emulated using a single-center database (MIMIC-IV) which contains granular information about clinical status. The hourly probability to receive mechanical ventilation was continuously estimated. The hazard ratios for the primary outcome, one-year mortality, and the secondary outcome, 30-day mortality, were estimated using weighted Cox models with stabilized inverse probability weights used to adjust for measured confounding.Results2996 Patients fulfilled the inclusion criteria of whom 792 were intubated within 48 h. Among the non-invasive support devices, the use of oxygen through facemask was the most common (75%). Compared to patients with the same probability of intubation but who were not intubated, intubation decreased the hazard of dying for the first year after ICU admission HR 0.81 (95% CI 0.68–0.96, p = 0.018). Intubation was associated with a 30-day mortality HR of 0.80 (95% CI 0.64–0.99, p = 0.046).ConclusionThe initiation of mechanical ventilation in patients with acute hypoxemic respiratory failure reduced the hazard of dying in this emulation of a target trial.

Non-Invasive Ventilation Support during Hospitalization for SARS-CoV-2 and the Risk of Venous Thromboembolism.

Background/Objectives: Although SARS-CoV-2 infection is a significant risk factor for venous thromboembolism (VTE), data on the impact of the use of non-invasive ventilation support (NIVS) to mitigate the risk of VTE during hospitalization are scarce. Methods: Data for 1471 SARS-CoV-2 patients, hospitalized in a single hub during the first pandemic wave, were collected from clinical records, including symptom duration and type, information on lung abnormalities on chest computed tomography (CT), laboratory parameters and the use of NIVS. Determining VTE occurrence during hospital stays was the main endpoint. Results: Patients with VTE (1.8%) had an increased prevalence of obesity (26% vs. 11%), diabetes (41% vs. 21%), higher CHA2DS2VASC score (4, IQR 2-5 vs. 3, IQR 1-4, age- and sex-adjusted, p = 0.021) and cough (65% vs. 44%) and experienced significantly higher rates of NIVS (44% vs. 8%). Using a stepwise multivariate logistic regression model, the prevalence of electrocardiogram abnormalities (odds ratio (OR) 2.722, 95% confidence interval (CI) 1.039-7.133, p = 0.042), cough (OR 3.019, 95% CI 1.265-7.202, p = 0.013), CHA2DS2-VASC score > 3 (OR 3.404, 95% CI 1.362-8.513, p = 0.009) and the use of NIVS (OR 15.530, 95% CI 6.244-38.627, p < 0.001) were independently associated with a risk of VTE during hospitalization. NIVS remained an independent risk factor for VTE even after adjustment for the period of admission within the pandemic wave. Conclusions: Our study suggests that NIVS is a risk factor for VTE during hospitalization in SARS-CoV-2 patients. Future studies should assess the optimal prophylactic strategy against VTE in patients with a SARS-CoV-2 infection candidate to non-invasive ventilatory support.

Artificial intelligence in colonoscopy: from detection to diagnosis.

This study reviews the recent progress of artificial intelligence for colonoscopy from detection to diagnosis. The source of data was 27 original studies in PubMed. The search terms were "colonoscopy" (title) and "deep learning" (abstract). The eligibility criteria were: (1) the dependent variable of gastrointestinal disease; (2) the interventions of deep learning for classification, detection and/or segmentation for colonoscopy; (3) the outcomes of accuracy, sensitivity, specificity, area under the curve (AUC), precision, F1, intersection of union (IOU), Dice and/or inference frames per second (FPS); (3) the publication year of 2021 or later; (4) the publication language of English. Based on the results of this study, different deep learning methods would be appropriate for different tasks for colonoscopy, e.g., Efficientnet with neural architecture search (AUC 99.8%) in the case of classification, You Only Look Once with the instance tracking head (F1 96.3%) in the case of detection, and Unet with dense-dilation-residual blocks (Dice 97.3%) in the case of segmentation. Their performance measures reported varied within 74.0-95.0% for accuracy, 60.0-93.0% for sensitivity, 60.0-100.0% for specificity, 71.0-99.8% for the AUC, 70.1-93.3% for precision, 81.0-96.3% for F1, 57.2-89.5% for the IOU, 75.1-97.3% for Dice and 66-182 for FPS. In conclusion, artificial intelligence provides an effective, non-invasive decision support system for colonoscopy from detection to diagnosis.

Surfactant Therapy in Respiratory Distress Syndrome

Respiratory distress syndrome (RDS) is the leading cause of neonatal respiratory morbidity and mortality. Advancements in neonatal care, along with extended insurance coverage, have resulted in increased utilization of surfactant replacement therapy (SRT) for RDS. This has contributed to a decrease in neonatal mortality. The primary mode of respiratory support in infants with RDS has dramatically changed over the last decades, transitioning from invasive to noninvasive support. Therefore, less invasive surfactant therapy has emerged as a widely adopted approach for SRT, establishing itself as a standard method in preterm infants’ care. This review addresses pulmonary surfactant, from its discovery to application in newborns with RDS. It also reviews the history of guidelines of SRT and health insurance issues. Future studies should evaluate various emerging noninvasive respiratory support modalities along with SRT for the respiratory management of neonates, given the lack of sufficient evidence regarding these approaches.

New Insight into Laryngo-Tracheal Surgery: High-Flow Oxygen Therapy to Prevent Early Complications after Surgery.

Early post-operative airway management after laryngo-tracheal surgery is crucial. Acute respiratory failure due to glottis' edema may occur, requiring reintubation. This can prolong ventilatory assistance, jeopardizing anastomosis. To date, only judicious steroid administration and fluid management are available to avoid more invasive procedures. High-flow oxygen therapy (HFOT) is a noninvasive O2 support method providing humidification, warmed air, and Positive End-Expiratory Pressure (AIRVO2). No data about HFOT use to prevent early complications after laryngo-tracheal surgery are reported in the literature. Between September 2020 and September 2022, 107 consecutive patients who underwent laryngo-tracheal surgery received HFOT (Group A). Data and long-term results were compared with those of 80 patients operated between September 2018 and August 2020 (Group B), when HFOT was not available. All patients were operated in a single center. No pre- or post-operative settings changed, except for HFOT introduction. We analyzed and compared the risk for "delayed" reintubation (unexpected reintubation within the first 24-48 h after extubating/laryngeal mask removal) in the two groups. No patients reported HFOT-related adverse events. The control group (B) presented "delayed" reintubation in 37% (p = 0.027), intensive care unit admission in 67% (p = 0.005) and longer hospital stay (p = 0.001) compared to the HFOT group (A). The minor complications' rate was 3% in both group and overall mortality was 0%. Re-stenosis was described in 4.6% of the HFOT group, without a statistically significant difference (p = 0.7006). Our study is the first to investigate HFOT use in patients undergoing laryngo-tracheal surgery, potentially representing a consistent innovation in the peri-operative management of these patients. With the limitation of a retrospective series, we would suggest HFOT use for preventing post-operative reintubation rate, possibly reducing ICU admissions and hospital stays.