Dataset Information

Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity.

ABSTRACT: The pandemic of COVID-19 led to a dramatic situation in hospitals, where staff had to deal with a huge number of patients in respiratory distress. To alleviate the workload of radiologists, we implemented an artificial intelligence (AI) - based analysis named CACOVID-CT, to automatically assess disease severity on chest CT scans obtained from those patients. We retrospectively studied CT scans obtained from 476 patients admitted at the University Hospital of Liege with a COVID-19 disease. We quantified the percentage of COVID-19 affected lung area (% AA) and the CT severity score (total CT-SS). These quantitative measurements were used to investigate the overall prognosis and patient outcome: hospital length of stay (LOS), ICU admission, ICU LOS, mechanical ventilation, and in-hospital death. Both CT-SS and % AA were highly correlated with the hospital LOS, the risk of ICU admission, the risk of mechanical ventilation and the risk of in-hospital death. Thus, CAD4COVID-CT analysis proved to be a useful tool in detecting patients with higher hospitalization severity risk. It will help for management of the patients flow. The software measured the extent of lung damage with great efficiency, thus relieving the workload of radiologists.

SUBMITTER: Guiot J

PROVIDER: S-EPMC9465374 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity.

Guiot Julien J Maes Nathalie N Winandy Marie M Henket Monique M Ernst Benoit B Thys Marie M Frix Anne-Noelle AN Morimont Philippe P Rousseau Anne-Françoise AF Canivet Perrine P Louis Renaud R Misset Benoît B Meunier Paul P Charbonnier Jean-Paul JP Lambermont Bernard B

Frontiers in medicine 20220829

The pandemic of COVID-19 led to a dramatic situation in hospitals, where staff had to deal with a huge number of patients in respiratory distress. To alleviate the workload of radiologists, we implemented an artificial intelligence (AI) - based analysis named CACOVID-CT, to automatically assess disease severity on chest CT scans obtained from those patients. We retrospectively studied CT scans obtained from 476 patients admitted at the University Hospital of Liege with a COVID-19 disease. We qua ...[more]

PMID: 36106317

Similar Datasets

Project description:IntroductionAvoidable hospitalizations are considered preventable given effective and timely primary care management and are an important indicator of health system performance. The ability to predict avoidable hospitalizations at the population level represents a significant advantage for health system decision-makers that could facilitate proactive intervention for ambulatory care-sensitive conditions (ACSCs). The aim of this study is to develop and validate the Avoidable Hospitalization Population Risk Tool (AvHPoRT) that will predict the 5-year risk of first avoidable hospitalization for seven ACSCs using self-reported, routinely collected population health survey data.Methods and analysisThe derivation cohort will consist of respondents to the first 3 cycles (2000/01, 2003/04, 2005/06) of the Canadian Community Health Survey (CCHS) who are 18-74 years of age at survey administration and a hold-out data set will be used for external validation. Outcome information on avoidable hospitalizations for 5 years following the CCHS interview will be assessed through data linkage to the Discharge Abstract Database (1999/2000-2017/2018) for an estimated sample size of 394,600. Candidate predictor variables will include demographic characteristics, socioeconomic status, self-perceived health measures, health behaviors, chronic conditions, and area-based measures. Sex-specific algorithms will be developed using Weibull accelerated failure time survival models. The model will be validated both using split set cross-validation and external temporal validation split using cycles 2000-2006 compared to 2007-2012. We will assess measures of overall predictive performance (Nagelkerke R2), calibration (calibration plots), and discrimination (Harrell's concordance statistic). Development of the model will be informed by the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement.Ethics and disseminationThis study was approved by the University of Toronto Research Ethics Board. The predictive algorithm and findings from this work will be disseminated at scientific meetings and in peer-reviewed publications.

Project description:ImportanceA comprehensive understanding of the benefits of COVID-19 vaccination requires consideration of disease attenuation, determined as whether people who develop COVID-19 despite vaccination have lower disease severity than unvaccinated people.ObjectiveTo evaluate the association between vaccination with mRNA COVID-19 vaccines-mRNA-1273 (Moderna) and BNT162b2 (Pfizer-BioNTech)-and COVID-19 hospitalization, and, among patients hospitalized with COVID-19, the association with progression to critical disease.Design, setting, and participantsA US 21-site case-control analysis of 4513 adults hospitalized between March 11 and August 15, 2021, with 28-day outcome data on death and mechanical ventilation available for patients enrolled through July 14, 2021. Date of final follow-up was August 8, 2021.ExposuresCOVID-19 vaccination.Main outcomes and measuresAssociations were evaluated between prior vaccination and (1) hospitalization for COVID-19, in which case patients were those hospitalized for COVID-19 and control patients were those hospitalized for an alternative diagnosis; and (2) disease progression among patients hospitalized for COVID-19, in which cases and controls were COVID-19 patients with and without progression to death or mechanical ventilation, respectively. Associations were measured with multivariable logistic regression.ResultsAmong 4513 patients (median age, 59 years [IQR, 45-69]; 2202 [48.8%] women; 23.0% non-Hispanic Black individuals, 15.9% Hispanic individuals, and 20.1% with an immunocompromising condition), 1983 were case patients with COVID-19 and 2530 were controls without COVID-19. Unvaccinated patients accounted for 84.2% (1669/1983) of COVID-19 hospitalizations. Hospitalization for COVID-19 was significantly associated with decreased likelihood of vaccination (cases, 15.8%; controls, 54.8%; adjusted OR, 0.15; 95% CI, 0.13-0.18), including for sequenced SARS-CoV-2 Alpha (8.7% vs 51.7%; aOR, 0.10; 95% CI, 0.06-0.16) and Delta variants (21.9% vs 61.8%; aOR, 0.14; 95% CI, 0.10-0.21). This association was stronger for immunocompetent patients (11.2% vs 53.5%; aOR, 0.10; 95% CI, 0.09-0.13) than immunocompromised patients (40.1% vs 58.8%; aOR, 0.49; 95% CI, 0.35-0.69) (P < .001) and weaker at more than 120 days since vaccination with BNT162b2 (5.8% vs 11.5%; aOR, 0.36; 95% CI, 0.27-0.49) than with mRNA-1273 (1.9% vs 8.3%; aOR, 0.15; 95% CI, 0.09-0.23) (P < .001). Among 1197 patients hospitalized with COVID-19, death or invasive mechanical ventilation by day 28 was associated with decreased likelihood of vaccination (12.0% vs 24.7%; aOR, 0.33; 95% CI, 0.19-0.58).Conclusions and relevanceVaccination with an mRNA COVID-19 vaccine was significantly less likely among patients with COVID-19 hospitalization and disease progression to death or mechanical ventilation. These findings are consistent with risk reduction among vaccine breakthrough infections compared with absence of vaccination.

Project description:Using RNA-seq and high-resolution mass spectrometry we performed a comprehensive systems analysis on 128 plasma and leukocyte samples from hospitalized patients with or without COVID-19 (n=102 and 26 respectively) and with differing degrees of disease severity. We generated abundance measurements for over 17,000 transcripts, proteins, metabolites, and lipids and compiled them with clinical data into a curated relational database. This resource offers the unique opportunity to perform systems analysis and cross-ome correlations to both molecules and patient outcomes. In total 219 molecular features were mapped with high significance to COVID-19 status and severity, including those involved in processes such as complement system activation, dysregulated lipid transport, and B cell activation. In one example, we detected a trio of covarying molecules – citrate, plasmenyl-phosphatidylcholines, and gelsolin (GSN) – that offer both pathophysiological insight and potential novel therapeutic targets. Further, our data revealed in some cases, and supported in others, that several biological processes were dysregulated in COVID-19 patients including vessel damage, platelet activation and degranulation, blood coagulation, and acute phase response. For example, we observed that the coagulation-related protein, cellular fibronectin (cFN), was highly increased within COVID-19 patients and provide new evidence that the upregulated proteoform stems from endothelial cells, consistent with endothelial injury as a major activator of the coagulation cascade. The abundance of prothrombin, which is cleaved to form thrombin during clotting, was significantly reduced and correlated with severity and might help to explain the hyper coagulative environment of SARS-CoV-2 infection. From transcriptomic analysis of leukocytes, we concluded that COVID-19 patients with acute respiratory distress syndrome (ARDS) demonstrated a phenotype that overlapped with, but was distinct from, that found in patients with non-COVID-19-ARDS. To aid in the global efforts toward elucidation of disease pathophysiology and therapeutic development, we created a web-based tool with interactive visualizations allowing for easy navigation of this systems-level compendium of biomolecule abundance in relation to COVID-19 status and severity. Finally, we leveraged these multi-omic data to predict COVID-19 patient outcomes with machine learning, which highlighted the predictive power of these expansive molecular measurements beyond the standardized clinical estimate of 10-year survival Charlson score.

Dataset Information

Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity.

Publications

Automatized lung disease quantification in patients with COVID-19 as a predictive tool to assess hospitalization severity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets