Cause Of Acute Respiratory Failure Research Articles

The development and implementation of a low-cost mechanical ventilator in a low-middle-income country during the COVID-19 pandemic: The Unisabana-HERONS

BackgroundThe COVID-19 pandemic in Latin America generated the need to develop low-cost, fast-manufacturing mechanical ventilators. The Universidad de La Sabana and the Fundacion Neumologica Colombiana designed and manufactured the Unisabana-HERONS (USH) ventilator. Here, we present the preclinical and clinical study results to evaluate its effectiveness and safety characteristics in an animal model (Yorkshire Sow) and five patients with acute respiratory failure receiving mechanical ventilatory support for 24 h. MethodsThe effectiveness and safety outcomes included maintaining arterial blood gases and pulse oximetry saturation (SpO2), respiratory pressures and volumes (during continuous monitoring) in the range of ARDS and lung-protective strategy goals, and the occurrence of barotrauma. A significance level of 0.05 was used for statistical tests. This clinical trial was registered on Clinicaltrials.gov (NCT04497623) and approved by the ethics committee. ResultsAmong patients treated with the Unisabana-HERONS, the most frequent causes of acute respiratory failure were pneumonia in 3/5 (60 %) and ARDS in 2/5 (40 %). During the treatment, the ventilatory parameters related to lung protection protocols were kept within the safety range, and vital signs and blood gas were stable. The percentage of time that the respiratory pressures or volumes were out of safety range were plateau pressure >30 cm H2O: 0.00 %; driving pressure >15 cm H2O: 0.06 %; mechanical power >15 J/min: 0.00 %; and Tidal volume >8 mL/kg: 0.00 %. There were no adverse events related to the ventilator. The usability questionnaire retrieved a median score for all items between 9 and 10 (best score: 10), indicating great ease of use. ConclusionThe Unisabana-HERONS ventilator effectively provided adequate gas exchange and maintained the ventilatory parameters in the range of lung protection strategies in humans and an animal model. Furthermore, it is straightforward to use and is a low-cost medical device.

Garlic oil supplementation blocks inflammatory pyroptosis-related acute lung injury by suppressing the NF-κB/NLRP3 signaling pathway via H2S generation.

Acute lung injury (ALI) is a major cause of acute respiratory failure with a high morbidity and mortality rate, and effective therapeutic strategies for ALI remain limited. Inflammatory response is considered crucial for the pathogenesis of ALI. Garlic, a globally used cooking spice, reportedly exhibits excellent anti-inflammatory bioactivity. However, protective effects of garlic against ALI have never been reported. This study aimed to investigate the protective effects of garlic oil (GO) supplementation on lipopolysaccharide (LPS)-induced ALI models. Hematoxylin and eosin staining, pathology scores, lung myeloperoxidase (MPO) activity measurement, lung wet/dry (W/D) ratio detection, and bronchoalveolar lavage fluid (BALF) analysis were performed to investigate ALI histopathology. Real-time polymerase chain reaction, western blotting, and enzyme-linked immunosorbent assay were conducted to evaluate the expression levels of inflammatory factors, nuclear factor-κB (NF-κB), NLRP3, pyroptosis-related proteins, and H2S-producing enzymes. GO attenuated LPS-induced pulmonary pathological changes, lung W/D ratio, MPO activity, and inflammatory cytokines in the lungs and BALF. Additionally, GO suppressed LPS-induced NF-κB activation, NLRP3 inflammasome expression, and inflammatory-related pyroptosis. Mechanistically, GO promoted increased H2S production in lung tissues by enhancing the conversion of GO-rich polysulfide compounds or by increasing the expression of H2S-producing enzymes in vivo. Inhibition of endogenous or exogenous H2S production reversed the protective effects of GO on ALI and eliminated the inhibitory effects of GO on NF-κB, NLRP3, and pyroptotic signaling pathways. Overall, these findings indicate that GO has a critical anti-inflammatory effect and protects against LPS-induced ALI by suppressing the NF-κB/NLRP3 signaling pathway via H2S generation.

Lung tissue expression of epithelial injury markers is associated with acute lung injury severity but does not discriminate sepsis from ARDS

BackgroundAcute respiratory distress syndrome (ARDS) is a common cause of respiratory failure in critically ill patients, and diffuse alveolar damage (DAD) is considered its histological hallmark. Sepsis is one of the most common aetiology of ARDS with the highest case-fatality rate. Identifying ARDS patients and differentiate them from other causes of acute respiratory failure remains a challenge. To address this, many studies have focused on identifying biomarkers that can help assess lung epithelial injury. However, there is scarce information available regarding the tissue expression of these markers. Evaluating the expression of elafin, RAGE, and SP-D in lung tissue offers a potential bridge between serological markers and the underlying histopathological changes. Therefore, we hypothesize that the expression of epithelial injury markers varies between sepsis and ARDS as well as according to its severity.MethodsWe compared the post-mortem lung tissue expression of the epithelial injury markers RAGE, SP-D, and elafin of patients that died of sepsis, ARDS, and controls that died from non-pulmonary causes. Lung tissue was collected during routine autopsy and protein expression was assessed by immunohistochemistry. We also assessed the lung injury by a semi-quantitative analysis.ResultsWe observed that all features of DAD were milder in septic group compared to ARDS group. Elafin tissue expression was increased and SP-D was decreased in the sepsis and ARDS groups. Severe ARDS expressed higher levels of elafin and RAGE, and they were negatively correlated with PaO2/FiO2 ratio, and positively correlated with bronchopneumonia percentage and hyaline membrane score. RAGE tissue expression was negatively correlated with mechanical ventilation duration in both ARDS and septic groups. In septic patients, elafin was positively correlated with ICU admission length, SP-D was positively correlated with serum lactate and RAGE was correlated with C-reactive protein.ConclusionsLung tissue expression of elafin and RAGE, but not SP-D, is associated with ARDS severity, but does not discriminate sepsis patients from ARDS patients.

Noninvasive respiratory support in the emergency department: Controversies and state-of-the-art recommendations.

Acute respiratory failure is a common reason for emergency department visits and hospital admissions. Diverse underlying physiologic abnormalities lead to unique aspects about the most common causes of acute respiratory failure: acute decompensated heart failure, acute exacerbation of chronic obstructive pulmonary disease, and acute de novo hypoxemic respiratory failure. Noninvasive respiratory support strategies are increasingly used methods to support work of breathing and improve gas exchange abnormalities to improve outcomes relative to conventional oxygen therapy or invasive mechanical ventilation. Noninvasive respiratory support includes noninvasive positive pressure ventilation and nasal high flow, each with unique physiologic mechanisms. This paper will review the physiology of respiratory failure and noninvasive respiratory support modalities and offer data and guideline-driven recommendations in the context of key clinical controversies.

The Age of Older Patients Requiring Prolonged Mechanical Ventilation Is Not the Sole Determinant of Their Long-Term Survival.

Background and Objectives: There are few data on the effects of prolonged mechanical ventilation on elderly patients. Our objective is to investigate the effects of prolonged mechanical ventilation on older patients' successful weaning and long-term survival. Methods: We examined how aging affected the course and results of elderly patients on prolonged mechanical ventilation by contrasting five age groups. Age, sex, cause of acute respiratory failure, comorbidities, discharge status, weaning status, and long-term survival outcomes were among the information we gathered. Results: Patients on prolonged mechanical ventilation who had undergone tracheostomy and had been successfully weaned had a greater one-year survival rate. The 1-year survival rate was poorer for older patients with four or more comorbidities. Regarding the 5-year survival rate, the risk of death was 45% lower in the successfully weaned patients than in the unsuccessfully weaned patients. The risk of death was 46% lower in patients undergoing tracheostomy than in those not undergoing tracheostomy. Older prolonged mechanical ventilation (PMV) patients with four or more comorbidities had an increased risk of death. Conclusions: When it comes to elderly patients on prolonged mechanical ventilation, there are other factors in addition to age that influence long-term survival. Long-term survival is likewise linked to successful weaning and undergoing tracheostomy.

Impact of Respiratory Bacterial Codetection on Outcomes in Ventilated Infants With Bronchiolitis.

Viral bronchiolitis is a common cause of acute respiratory failure requiring intubation for infants. Bacterial respiratory tract infections can occur with bronchiolitis, although their prevalence and impact on outcomes are unclear, especially with increased use of noninvasive respiratory support. This was a single-center retrospective cohort study of children <2 years old requiring intubation in the emergency department for bronchiolitis from 2012 to 2017 who had viral testing plus a lower respiratory culture obtained. We evaluated the impact of bacterial codetection (positive respiratory culture plus moderate or many polymorphonuclear neutrophils on Gram stain) on mechanical ventilation (MV) duration and intensive care unit length of stay using multivariable gamma regression. Of 149 patients enrolled, 52% had bacterial codetection. In adjusted analysis, patients with codetection had shorter MV duration [adjusted relative risk (aRR) 0.819, 95% confidence interval (CI): 0.69-0.98; marginal mean duration of 5.31 days (4.71-5.99) compared to 6.48 days (5.72-7.35) without codetection]. Patients with codetection had a shorter intensive care unit stay [aRR 0.806 (0.69-0.94); marginal mean length of stay 6.9 days (6.21-7.68) vs. 8.57 days (7.68-9.56) without codetection]. The association between codetection and duration of ventilation appears confined to those receiving earlier antibiotics (less than the median time) rather than later antibiotics [aRR 0.738 (0.56-0.95) for earlier vs. aRR 0.92 (0.70-1.18) for later]. Respiratory bacterial codetection is common and associated with shorter MV duration in infants requiring early intubation for bronchiolitis. Early antibiotics may contribute to these outcomes, but further multicenter studies are needed to understand the role of codetection and antibiotics on bronchiolitis outcomes.

Evaluation of risk factors and clinical outcomes of acute respiratory failure from post renal transplant recipients: A five-year data of a single center

Acute Respiratory Failure (ARF) requiring Intensive Care Unit (ICU) admission is a common complication following renal transplant and is a diagnostic and therapeutic challenge. This study aimed to evaluate etiological factors and clinical outcomes of ARF following a renal transplant. This was a retrospective observational study. Data was recruited from last five –years’ records of Renal Transplant Unit of Dow University of Health Sciences, Karachi, Pakistan. Patients who developed ARF after renal transplantation whether requiring hospitalization (both in ICU or in ward) were included and their severity, etiologic diagnosis, and clinical outcomes were evaluated. During past five years (June 2017 till June 2023) a total of 450 kidney allografts were done and 35 patients (7.8%) developed ARF. Out of which 15 patients were shifted to the ICU. Mortality of female patients was higher as compared to males (26.1% versus 20.4%). Hypertension was found to be the most common comorbidity whereas glomerulonephritis was the most common cause of End Stage Renal Disease (ESRD). Acute rejection was observed in 20.89% (n = 94) of recipients. Bacterial pneumonia was the most common cause of ARF, one patient needed on mechanical ventilation whereas two patients were dialysis dependent survivors. ARF following renal transplant is associated with higher mortality and loss of graft function because of compromised immunity. Anti-bacterial prophylaxis and early intensive management appears to help in improving the outcome while integrating the graft function.

Multiplex Polymerase Chain Reaction Assay to Detect Nasopharyngeal Viruses in Immunocompromised Patients With Acute Respiratory Failure

In immunocompromised patients with acute respiratory failure (ARF), the clinical significance of respiratory virus detection in the nasopharynx remains uncertain. Is viral detection in nasopharyngeal swabs associated with causes and outcomes of ARF in immunocompromised patients? This preplanned post hoc analysis of a randomized controlled trial enrolled immunocompromised patients admitted to 32 ICUs for ARF between May 2016 and December 2017. Nasopharyngeal swabs sampled at inclusion were assessed for 23 respiratory pathogens using multiplex polymerase chain reaction (PCR) assay. Causes of ARF were established by managing physicians and were reviewed by three expert investigators masked to the multiplex PCR assay results. Associations between virus detection in nasopharyngeal swabs, causes of ARF, and composite outcome of day 28 mortality, invasive mechanical ventilation (IMV), or both were assessed. Among the 510 sampled patients, the multiplex PCR assay results were positive in 103 patients (20.2%), and a virus was detected in 102 samples: rhinoviruses or enteroviruses in 35.5%, coronaviruses in 10.9%, and flu-like viruses (influenza virus, parainfluenza virus, respiratory syncytial virus, human metapneumovirus) in 52.7%. The cause of ARF varied significantly according to the results of the multiplex PCR assay, especially the proportion of viral pneumonia: 50.0%with flu-like viruses, 14.0%with other viruses, and 3.6%when no virus was detected (P< .001). No difference was found in the composite outcome of day 28 mortality, IMV, or both according to positive assay findings (54.9%vs54.7%; P= .965). In a pre-established subgroup analysis, flu-like virus detection was associated with a higher rate of day 28 mortality, IMV, or both among recipients of allogeneic hematopoietic stem cell transplantation compared with those without detected virus. In immunocompromised patients with ARF, the results of nasopharyngeal multiplex PCR assays are not associated with IMV or mortality. A final diagnosis of viral pneumonia is retained in one-third of patients with positive assay results and in one-half of the patients with a flu-like virus.

Etiologies and Outcome of Patients with Solid Tumors Admitted to ICU with Acute Respiratory Failure: A Secondary Analysis of the EFRAIM Study.

Acute respiratory failure (ARF) remains the most frequent reason for ICU admission in patients who are immunocompromised. This study reports etiologies and outcomes of ARF in subjects with solid tumors. This study was a post hoc analysis of the EFRAIM study, a prospective multinational cohort study that included 1611 subjects who were immunocompromised and with ARF admitted to the ICU. Subjects with solid tumors admitted to the ICU with ARF were included in the analysis. Among the subjects from the EFRAIM cohort, 529 subjects with solid tumors (32.8%) were included in the analysis. At ICU admission, the median (interquartile range) Sequential Organ Failure Assessment score was 5 (3-9). The types of solid tumor were mostly lung cancer (n = 111, 21%), breast cancer (n = 52, 9.8%), and digestive cancer (n = 47, 8.9%). A majority, 379 subjects (71.6%) were full code at ICU admission. The ARF was caused by bacterial or viral infection (n = 220, 41.6%), extrapulmonary sepsis (n = 62, 11.7%), or related to cancer or treatment toxicity (n = 83, 15.7%), or fungal infection (n = 23, 4.3%). For 63 subjects (11.9%), the ARF etiology remained unknown after an extensive diagnostic workup. The hospital mortality rate was 45.7% (n = 232/508). Hospital mortality was independently associated with chronic cardiac failure (odds ratio 1.78, 95% CI 1.09-2.92; P = .02), lung cancer (odds ratio 2.50, 95% CI 1.51-4.19; P < .001), day 1 Sequential Organ Failure Assessment score (odds ratio 1.97, 95% CI 1.32-2.96; P < .001). ARF etiologies other than infectious, related to cancer, or treatment toxicity were associated with better outcomes (odds ratio 0.32, 95% CI 0.16-0.61; P < .001). Infectious diseases remained the most frequent cause of ARF in subjects with solid tumors admitted to the ICU. Hospital mortality was related to severity at ICU admission, previous comorbidities, and ARF etiologies related to non-malignant causes or pulmonary embolism. Lung tumor was also independently associated with higher mortality.

A Study of Outcome of Noninvasive Ventilatory Support in Acute Respiratory Failure

Introduction: Noninvasive ventilation (NIV) is often used in acute respiratory failure to prevent endotracheal intubation and its complications. Various factors influence favorable outcome for NIV. Aim: To assess the outcome of NIV in acute respiratory failure and to determine predictors of positive outcome. Patients and Methods: This was an observational study of 4 years where 110 patients with acute respiratory failure requiring NIV were included. Data of history, examination, investigations, and clinical outcome of all patients were recorded. The outcome was divided in two categories depending upon whether patients improved or required invasive ventilation. Results: Of 110 patients, there were 78 men with a mean age of 64.24 years and 32 women with a mean age of 56.59 years. The causes of acute respiratory failure were acute exacerbation of chronic obstructive pulmonary disease (COPD) (61.81%), bronchial asthma (9.09), pneumonia (22.72%), tuberculosis (2.72%), interstitial lung disease (1.81%), and pulmonary artery hypertension (0.9%). Among them, 81 (74%) patients improved. Patients who had acute respiratory failure due to COPD (P 3 days (P = 0.001). Conclusions: COPD patients with acute respiratory failure respond well to NIV. Improvement in pH, PCO2, and PO2 within or at 24 h of NIV predicts successful outcome. Requirement of prolonged NIV leads to poor outcome.

Mechanical ventilation in neuromuscular disorders- A review

Neuromuscular disorders (NMD) are a group of disorders characterised by weakness of muscles and may have a slow and progressing alveolar hypoventilation leading to the ventilatory failure. It may necessitate initiation of mechanical ventilation. Noninvasive ventilation is the method of choice. Invasive mechanical ventilation is indicated when noninvasive mechanical ventilation fails. Tracheostomy is the airway of choice for invasive mechanical ventilation. Endotracheal intubation is used only as an emergency airway or when reversible causes of acute respiratory failure are being considered. This article details ventilation in patients with neuromuscular disorders.

Evaluation of the Causes of Acute Respiratory Failure in Pregnant Women Admitted to Shahid Sayyad Shirazi Hospital before COVID-19 Pandemic

Introduction: Acute respiratory failure (ARF) is rare in pregnancy and occurs in less than 0.1% of pregnancies, it is one of the most common admissions of pregnant women to the intensive care unit and one of the leading causes of maternal mortality. The aim of this study was evaluation of the causes of ARF in pregnant women admitted to Shahid Sayyad Shirazi Hospital from 2014 to 2019.&#x0D; Material and Methods: This was a retrospective cross-sectional descriptive-analytical in pregnant women with respiratory disorders chief complaints. All cases of pregnant women admitted (1226 cases) were reviewed. Data were analyzed using SPSS version 26.&#x0D; Results: In total, 75 patients were enrolled in the study and their records were reviewed. The mean age of patients was 28.47 ± 5.06 years. Fifteen patients (25%) had ARF. The results showed that 13.3% of pregnant women with ARF needed to use mechanical ventilation (P=0.038). Also, women with history of chronic lung disease (CLD) are at higher risk for ARF (46.7% vs. 33.3%, P&lt;0.001). Only 1.7% of mothers without symptoms of ARF were infected, but 46.7% of mothers with symptoms of ARF were infected (P&lt;0.001).&#x0D; Conclusion: The results of the study showed that infectious causes (influenza) and underlying CLD including asthma were major causes of ARF in pregnant women. Thus, more careful attention is needed to control the underlying disease, and planning for easier access to the influenza vaccine can play an effective role in reducing the incidence of pulmonary infections.

The role of diaphragmatic thickness measurement in weaning prediction and its comparison with rapid shallow breathing index: a single-center experience.

BackgroundAcute respiratory failure (ARF) is commonly managed with invasive mechanical ventilation (IMV). The majority of the time that a patient spends on IMV is in the process of weaning. Prediction of the weaning outcome is of paramount importance, as untimely/delayed extubation is associated with a high risk of mortality. Diaphragmatic ultrasonography is a promising tool in the intensive care unit, and its utility in predicting the success of weaning remains understudied.MethodsIn this prospective-observational study, we recruited 54 ARF patients on IMV, along with 50 healthy controls. During a spontaneous breathing trial, all subjects underwent diaphragmatic ultrasonography along with a rapid shallow breathing index (RSBI) assessment. ResultsThe mean age was 41.8±17.0 and 37.6±10.5 years among the cases and control group, respectively. Demographic variables were broadly similar in the two groups. The most common cause of ARF was obstructive airway disease. The average duration of IMV was 5.41±2.81 days. Out of 54 subjects, 45 were successfully weaned, while nine patients failed weaning. Age, body mass index, and severity of disease were similar in the successful and failed weaning patients. The sensitivity in predicting successful weaning of percent change in diaphragmatic thickness (Δtdi%) >29.71% was high (93.33%), while specificity was 66.67%. The sensitivity and specificity of mean diaphragmatic thickness (tdi) end-expiratory >0.178 cm was 60.00% and 77.78%, respectively. RSBI at 1 minute of <93.75 had an equally high sensitivity (93.33%) but a lower specificity (22.22%). Similar results were also found for RSBI measured at 5 minutes.ConclusionsDuring the weaning assessment, the purpose is to minimize both premature as well as delayed extubation. We found that diaphragmatic ultrasonography, in particular Δtdi%, is better than RSBI in predicting weaning outcomes.

Correlación entre el aumento del dímero D en sangre con el espacio muerto en pacientes con COVID-19 y síndrome de dificultad respiratoria aguda

IntroductionSince December 2019, a number of cases of CoV2/COVID-19 severe acute respiratory syndrome (SARS) pneumonia in Wuhan China have been identified as a cause of acute respiratory failure and have spread around the world at high speed. Due to the large number of cases and the need to better understand this condition, tools are required to grade the intensity and vital prognosis of patients. The objective of this study is to determine the relationship between the dead space measured by volumetric capnography or ventilatory ratio and the increase in D-dimer levels in patients diagnosed with COVID-19 pneumonia and who meet the Berlin criteria for Acute Respiratory Distress Syndrome (ARDS). Materials and methodsA single-centre observational study of a prospective cohort on the use of D-dimer and the correlation with dead space. Adults older than 18 years with a diagnosis of pneumonia due to COVID-19 and ARDS hospitalized in the intensive care units of Hospital Santa Clara in Bogotá, Colombia, from August 2020 to July 2021 were included. ResultsThe study included 67 patients, all with a confirmed SARS-CoV-2 diagnosis, no association was found between D-dimer and dead space on day 1 and 3 of hospitalization in the ICU. ConclusionsD-dimer was not correlated with increased dead space in our study and was not associated with relevant outcomes in patients with ARDS.

Use of high flow nasal cannula in patients with acute respiratory failure in general wards under intensivists supervision: a single center observational study

BackgroundFew data exist on high flow nasal cannula (HFNC) use in patients with acute respiratory failure (ARF) admitted to general wards.Rationale and objectivesTo retrospectively evaluate feasibility and safety of HFNC in general wards under the intensivist-supervision and after specific training.MethodsPatients with ARF (dyspnea, respiratory rate-RR > 25/min, 150 < PaO2/FiO2 < 300 mmHg during oxygen therapy) admitted to nine wards of an academic hospital were included. Gas-exchange, RR, and comfort were assessed before HFNC and after 2 and 24 h of application.Results150 patients (81 male, age 74 [60–80] years, SOFA 4 [2–4]), 123 with de-novo ARF underwent HFNC with flow 60 L/min [50–60], FiO2 50% [36–50] and temperature 34 °C [31–37]. HFNC was applied a total of 1399 days, with a median duration of 7 [3–11] days. No major adverse events or deaths were reported. HFNC did not affect gas exchange but reduced RR (25–22/min at 2–24 h, p < 0.001), and improved Dyspnea Borg Scale (3–1, p < 0.001) and comfort (3–4, p < 0.001) after 24 h. HFNC failed in 20 patients (19.2%): 3 (2.9%) for intolerance, 14 (13.4%) escalated to NIV/CPAP in the ward, 3 (2.9%) transferred to ICU. Among these, one continued HFNC, while the other 2 were intubated and they both died. Predictors of HFNC failure were higher Charlson’s Comorbidity Index (OR 1.29 [1.07–1.55]; p = 0.004), higher APACHE II Score (OR 1.59 [1.09–4.17]; p = 0.003), and cardiac failure as cause of ARF (OR 5.26 [1.36–20.46]; p = 0.02).ConclusionIn patients with mild-moderate ARF admitted to general wards, the use of HFNC after an initial training and daily supervision by intensivists was feasible and seemed safe. HFNC was effective in improving comfort, dyspnea, and respiratory rate without effects on gas exchanges.Trial registration This is a single-centre, noninterventional, retrospective analysis of clinical data.

Using Artificial Intelligence to Establish Chest X-Ray Image Recognition Model to Assist Crucial Diagnosis in Elder Patients With Dyspnea.

Pneumonia and pulmonary edema are the most common causes of acute respiratory failure in emergency and intensive care. Airway maintenance and heart function preservation are two foundations for resuscitation. Laboratory examinations have been utilized for clinicians to early differentiate pneumonia and pulmonary edema; however, none can provide results as prompt as radiology examinations, such as portable chest X-ray (CXR), which can quickly deliver results without mobilizing patients. However, similar features between pneumonia and pulmonary edema are found in CXR. It remains challenging for Emergency Department (ED) physicians to make immediate decisions as radiologists cannot be on-site all the time and provide support. Thus, Accurate interpretation of images remains challenging in the emergency setting. References have shown that deep convolutional neural networks (CNN) have a high sensitivity in CXR readings. In this retrospective study, we collected the CXR images of patients over 65 hospitalized with pneumonia or pulmonary edema diagnosis between 2016 and 2020. After using the ICD-10 codes to select qualified patient records and removing the duplicated ones, we used keywords to label the image reports found in the electronic medical record (EMR) system. After that, we categorized their CXR images into five categories: positive correlation, negative correlation, no correlation, low correlation, and high correlation. Subcategorization was also performed to better differentiate characteristics. We applied six experiments includes the crop interference and non-interference categories by GoogLeNet and applied three times of validations. In our best model, the F1 scores for pneumonia and pulmonary edema are 0.835 and 0.829, respectively; accuracy rate: 83.2%, Recall rate: 83.2%, positive predictive value: 83.3%, and F1 Score: 0.832. After the validation, the best accuracy rate of our model can reach up to 73%. The model has a high negative predictive value of excluding pulmonary edema, meaning the CXR shows no sign of pulmonary edema. At the time, there was a high positive predictive value in pneumonia. In that way, we could use it as a clinical decision support (CDS) system to rule out pulmonary edema and rule in pneumonia contributing to the critical care of the elderly.

Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure.

When patients develop acute respiratory failure (ARF), accurately identifying the underlying etiology is essential for determining the best treatment. However, differentiating between common medical diagnoses can be challenging in clinical practice. Machine learning models could improve medical diagnosis by aiding in the diagnostic evaluation of these patients. Machine learning models were trained to predict the common causes of ARF (pneumonia, heart failure, and/or chronic obstructive pulmonary disease [COPD]). Models were trained using chest radiographs and clinical data from the electronic health record (EHR) and applied to an internal and external cohort. The internal cohort of 1618 patients included 508 (31%) with pneumonia, 363 (22%) with heart failure, and 137 (8%) with COPD based on physician chart review. A model combining chest radiographs and EHR data outperformed models based on each modality alone. Models had similar or better performance compared to a randomly selected physician reviewer. For pneumonia, the combined model area under the receiver operating characteristic curve (AUROC) was 0.79 (0.77-0.79), image model AUROC was 0.74 (0.72-0.75), and EHR model AUROC was 0.74 (0.70-0.76). For heart failure, combined: 0.83 (0.77-0.84), image: 0.80 (0.71-0.81), and EHR: 0.79 (0.75-0.82). For COPD, combined: AUROC = 0.88 (0.83-0.91), image: 0.83 (0.77-0.89), and EHR: 0.80 (0.76-0.84). In the external cohort, performance was consistent for heart failure and increased for COPD, but declined slightly for pneumonia. Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of ARF. Further work is needed to determine how these models could act as a diagnostic aid to clinicians in clinical settings.

Treatment Outcomes of Infectious and Non-infectious Acute Exacerbation of Myositis-Related Interstitial Lung Disease.

IntroductionAlthough respiratory infections are common causes of acute respiratory failure (ARF) in patients with myositis-interstitial lung disease (ILD), limited data are available regarding the treatment outcomes by the etiologies of acute exacerbation (AE) of myositis-related ILD (infectious vs. non-infectious). Our study aimed to investigate the treatment outcomes of AE in patients with myositis-related ILD focused on the infectious etiology.MethodsA single center-based retrospective cohort was performed at Hanyang University Hospital between January 2000 and December 2018. A total of 36 patients with AE of myositis-related ILD were consecutively included. The exposure was the etiologies of AE in myositis-related ILD, and the outcome was in-hospital mortality. The infectious etiology was defined as confirmation of bacteria, virus, or fungus in samples obtained from the respiratory tract.ResultsAmong the 36 patients, 17 were diagnosed with infectious AE. The overall in-hospital mortality rate of AE was 47.2%. Although the mortality rate in patients with infectious AE was lower (41.2%) than in those with non-infectious AE (52.6%), this difference was not statistically significant (p = 0.724). A survival analysis showed no significant difference in mortality between patients with infectious AE versus those with non-infectious AE [risk ratio = 0.78, 95% CI = 0.38–1.59].ConclusionOur study showed that infectious AE is an important cause of mortality in patients with myositis-related ILD, showing a similar risk of mortality as non-infectious AE.

Role of chest ultrasonography in the diagnosis of the causes of acute respiratory failure

Role of chest ultrasonography in the diagnosis of the causes of acute respiratory failure

EVALUATE THE UTILITY OF LUNG ULTRASOUND AS A DIAGNOSTIC TOOL IN PATIENTS WITH ACUTE RESPIRATORY FAILURE.

OBJECTIVES To evaluate the utility of the lung ultrasound using the BLUE protocol as a diagnostic tool and analyze all clinical,investigational data of patients and compare the provisional diagnosis made using the lung ultrasound with the final diagnosis.METHODS An observational study to evaluate the utility of lung ultrasound using the BLUE protocol as a diagnostic tool in patients with acute respiratory failure admitted to our Respiratory Intensive Care Unit during a period of August 2014 to December 2015 where 100 patients were included in the study.Three items were assessed:lung sliding, artifacts (horizontal A lines or vertical B lines indicating interstitial syndrome), alveolar consolidation, and / or pleural effusion.Venous scan to screen for deep venous thrombosis was done wherever required.Ultrasound equipment used was GE-LOGIQe.It has both the convex and the ECHO probes.The diagnosis obtained by the thoracic ultrasonography with limited echocardiography was compared with clinical diagnosis arrived by the ICU team at the end of the hospital stay.RESULTSThe mean age of the patients was 65.1±15.08 years.While the mean age in our study was almost similar to that seen in the BLUE protocol (68 years),the difference seen in gender distribution was owed mainly to the large sample size of the previous studies.In our study, Pneumonia was observed in 34% patients with A profile plus PLAPS being the most common finding followed by B' profile and A/B profile.Exacerbations due to COPD/Asthma/ILD accounted for 32% of the total patients in our study with A profile without PLAPS being the commonest pattern on lung ultrasound in patients of COPD/Asthma followed by B profile in patients of ILD. Lung ultrasound does not diagnose COPD/Asthma exacerbations, but rather by ruling out other causes of acute respiratory failure it arrives at the possible diagnosis of COPD/Asthma exacerbations. Pulmonary odema was observed in 23% of patients with B profile without PLAPS being the commonest finding.9% patients had pneumothorax and A' profile with a posterolateral lung point was present in all the cases.Absence of sliding is not specific as it can be present in other conditions also.The presence of lung point is a very specific finding for the diagnosis of pneumothorax. Both the patients of Pulmonary embolism had A profile with deep vein thrombosis on venous scan.Regardless of the initial profile (A or B),the lower limb Doppler ultrasonography should be done. CONCLUSION Majority of our patients presenting with acute respiratory failure in the RICU were males,mostly elderly,in the age group of 60 years and above with significant comorbidities.Our study has demonstrated the excellent diagnostic yield of lung ultrasound using the BLUE protocol as a diagnostic tool for the evaluation of patients with acute respiratory failure.The results obtained in our study were similar and comparable with the studies done in developed countries and this modality can be used with ease and confidence in the evaluation of acute respiratory failure in the Indian settings by non radiologists ICU physicians