Dataset Information

Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan.

ABSTRACT:

Background

Automated analysis of lung computed tomography (CT) scans may help characterize subphenotypes of acute respiratory illness. We integrated lung CT features measured via deep learning with clinical and laboratory data in spontaneously breathing subjects to enhance the identification of COVID-19 subphenotypes.

Methods

This is a multicenter observational cohort study in spontaneously breathing patients with COVID-19 respiratory failure exposed to early lung CT within 7 days of admission. We explored lung CT images using deep learning approaches to quantitative and qualitative analyses; latent class analysis (LCA) by using clinical, laboratory and lung CT variables; regional differences between subphenotypes following 3D spatial trajectories.

Results

Complete datasets were available in 559 patients. LCA identified two subphenotypes (subphenotype 1 and 2). As compared with subphenotype 2 (n = 403), subphenotype 1 patients (n = 156) were older, had higher inflammatory biomarkers, and were more hypoxemic. Lungs in subphenotype 1 had a higher density gravitational gradient with a greater proportion of consolidated lungs as compared with subphenotype 2. In contrast, subphenotype 2 had a higher density submantellar-hilar gradient with a greater proportion of ground glass opacities as compared with subphenotype 1. Subphenotype 1 showed higher prevalence of comorbidities associated with endothelial dysfunction and higher 90-day mortality than subphenotype 2, even after adjustment for clinically meaningful variables.

Conclusions

Integrating lung-CT data in a LCA allowed us to identify two subphenotypes of COVID-19, with different clinical trajectories. These exploratory findings suggest a role of automated imaging characterization guided by machine learning in subphenotyping patients with respiratory failure.

Trial registration

ClinicalTrials.gov Identifier: NCT04395482. Registration date: 19/05/2020.

SUBMITTER: Rezoagli E

PROVIDER: S-EPMC11301830 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan.

Rezoagli Emanuele E Xin Yi Y Signori Davide D Sun Wenli W Gerard Sarah S Delucchi Kevin L KL Magliocca Aurora A Vitale Giovanni G Giacomini Matteo M Mussoni Linda L Montomoli Jonathan J Subert Matteo M Ponti Alessandra A Spadaro Savino S Poli Giancarla G Casola Francesco F Herrmann Jacob J Foti Giuseppe G Calfee Carolyn S CS Laffey John J Bellani Giacomo G Cereda Maurizio M

Critical care (London, England) 20240805 1

<h4>Background</h4>Automated analysis of lung computed tomography (CT) scans may help characterize subphenotypes of acute respiratory illness. We integrated lung CT features measured via deep learning with clinical and laboratory data in spontaneously breathing subjects to enhance the identification of COVID-19 subphenotypes.<h4>Methods</h4>This is a multicenter observational cohort study in spontaneously breathing patients with COVID-19 respiratory failure exposed to early lung CT within 7 days ...[more]

PMID: 39103945

Similar Datasets

Project description:BackgroundExcessive inspiratory effort could translate into self-inflicted lung injury, thus worsening clinical outcomes of spontaneously breathing patients with acute respiratory failure (ARF). Although esophageal manometry is a reliable method to estimate the magnitude of inspiratory effort, procedural issues significantly limit its use in daily clinical practice. The aim of this study is to describe the correlation between esophageal pressure swings (ΔPes) and nasal (ΔPnos) as a potential measure of inspiratory effort in spontaneously breathing patients with de novo ARF.MethodsFrom January 1, 2021, to September 1, 2021, 61 consecutive patients with ARF (83.6% related to COVID-19) admitted to the Respiratory Intensive Care Unit (RICU) of the University Hospital of Modena (Italy) and candidate to escalation of non-invasive respiratory support (NRS) were enrolled. Clinical features and tidal changes in esophageal and nasal pressure were recorded on admission and 24 h after starting NRS. Correlation between ΔPes and ΔPnos served as primary outcome. The effect of ΔPnos measurements on respiratory rate and ΔPes was also assessed.ResultsΔPes and ΔPnos were strongly correlated at admission (R2 = 0.88, p < 0.001) and 24 h apart (R2 = 0.94, p < 0.001). The nasal plug insertion and the mouth closure required for ΔPnos measurement did not result in significant change of respiratory rate and ΔPes. The correlation between measures at 24 h remained significant even after splitting the study population according to the type of NRS (high-flow nasal cannulas [R2 = 0.79, p < 0.001] or non-invasive ventilation [R2 = 0.95, p < 0.001]).ConclusionsIn a cohort of patients with ARF, nasal pressure swings did not alter respiratory mechanics in the short term and were highly correlated with esophageal pressure swings during spontaneous tidal breathing. ΔPnos might warrant further investigation as a measure of inspiratory effort in patients with ARF.Trial registrationNCT03826797 . Registered October 2016.

Project description:BackgroundProne positioning in non-intubated spontaneously breathing patients is becoming widely applied in practice alongside noninvasive respiratory support. This systematic review and meta-analysis evaluates the effect, timing, and populations that might benefit from awake proning regarding oxygenation, mortality, and tracheal intubation compared with supine position in hypoxaemic acute respiratory failure.MethodsWe conducted a systematic literature search of PubMed/MEDLINE, Cochrane Library, Embase, CINAHL, and BMJ Best Practice until August 2021 (International Prospective Register of Systematic Reviews [PROSPERO] registration: CRD42021250322). Studies included comprise least-wise 20 adult patients with hypoxaemic respiratory failure secondary to acute respiratory distress syndrome or coronavirus disease (COVID-19). Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed, and study quality was assessed using the Newcastle-Ottawa Scale and the Cochrane risk-of-bias tool.ResultsFourteen studies fulfilled the selection criteria and 2352 patients were included; of those patients, 99% (n=2332/2352) had COVID-19. Amongst 1041 (44%) patients who were placed in the prone position, 1021 were SARS-CoV-2 positive. The meta-analysis revealed significant improvement in the PaO2/FiO2 ratio (mean difference -23.10; 95% confidence interval [CI]: -34.80 to 11.39; P=0.0001; I2=26%) after prone positioning. In patients with COVID-19, lower mortality was found in the group placed in the prone position (150/771 prone vs 391/1457 supine; odds ratio [OR] 0.51; 95% CI: 0.32-0.80; P=0.003; I2=48%), but the tracheal intubation rate was unchanged (284/824 prone vs 616/1271 supine; OR 0.72; 95% CI: 0.43-1.22; P=0.220; I2=75%). Overall proning was tolerated for a median of 4 h (inter-quartile range: 2-16).ConclusionsProne positioning can improve oxygenation amongst non-intubated patients with acute hypoxaemic respiratory failure when applied for at least 4 h over repeated daily episodes. Awake proning appears safe, but the effect on tracheal intubation rate and survival remains uncertain.

Project description:BackgroundIncidental respiratory disease-related findings are frequently observed on low-dose CT (LDCT) lung cancer screenings. This study analyzed data from the National Lung Screening Trial (NLST) to assess the relationship between such findings and respiratory disease mortality (RDM), excluding lung cancer.Research questionAre incidental respiratory findings on LDCT scanning associated with increased RDM?Study design and methodsSubjects in the NLST LDCT arm received three annual screens. Trial radiologists noted findings related to possible lung cancer, as well as respiratory-related incidental findings. Demographic characteristics, smoking history, and medical history were captured in a baseline questionnaire. Kaplan-Meier curves were used to assess cumulative RDM. Multivariate proportional hazards models were used to assess risk factors for RDM; in addition to incidental CT scan findings, variables included respiratory disease history (COPD/emphysema, and asthma), smoking history, and demographic factors (age, race, sex, and BMI).ResultsOf 26,722 subjects in the NLST LDCT arm, 25,002 received the baseline screen and a subsequent LDCT screen. Overall, 59% were male, 26.5% were aged ≥ 65 years at baseline, and 10.6% reported a history of COPD/emphysema. Emphysema on LDCT scanning was reported in 30.7% of subjects at baseline and in 44.2% at any screen. Of those with emphysema on baseline LDCT scanning, 18% reported a history of COPD/emphysema. Median mortality follow-up was 10.3 years. There were 3,639 deaths, and 708 were from respiratory diseases. Among subjects with no history of COPD/emphysema, 10-year cumulative RDM ranged from 3.9% for subjects with emphysema and reticular opacities to 1.1% for those with neither condition; the corresponding range among subjects with a COPD/emphysema history was 17.3% (both) to 3.7% (neither). Emphysema on LDCT imaging was associated with a significantly elevated RDM hazard ratio (2.27; 95% CI, 1.92-2.7) in the multivariate model. Reticular opacities (including honeycombing/fibrosis/scar) also had a significantly elevated hazard ratio (1.39; 95% CI, 1.19-1.62).InterpretationIncidental respiratory disease-related findings observed on NLST LDCT screens were frequent and associated with increased mortality from respiratory diseases.

Dataset Information

Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan.

Background

Methods

Results

Conclusions

Trial registration

Publications

Phenotyping COVID-19 respiratory failure in spontaneously breathing patients with AI on lung CT-scan.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets