An observational study in covid19, sponsored by University of Milano Bicocca. Completed at 8 sites in 2 countries. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2022-07-21.
Sponsored by University of Milano Bicocca · Observational
This is a multicenter observational retrospective cohort study that aims to study the morphological characteristics of the lung parenchyma of SARS-CoV2 positive patients identifiable in patterns through artificial intelligence techniques and their impact on patient outcome.
BACKGROUND:
In February, the first case of SARS-CoV2 positive patient was recorded in Lombardy (Italy), a virus capable of causing a severe form of acute respiratory failure called Coronavirus Disease 2019 (COVID-19).
Qualitative assessments of lung morphology have been identified to describe macroscopic characteristics of this infection upon admission and during the hospitalization of patients.
At the moment, there are no studies that have exhaustively described the parenchymal lung damage induced by SARS-CoV2 by quantitative analysis.
The hypothesis of this study is that specific morphological and quantitative alterations of the lung parenchyma assessed by means of CT scan in patients suffering from severe respiratory insufficiency induced by SARS-CoV2 may have an impact on the severity of the degree of alteration of the respiratory exchanges (oxygenation and clearance of the CO2) and have an impact on patient outcome.
The presence of characteristic lung morphological patterns assessed by CT scan could allow the recognition of specific patient clusters who can benefit from intensive treatment differently, making a significant contribution to stratifying the severity of patients and their risk of mortality.
This is an exploratory clinical descriptive study of lung CT images in a completely new patient population who are nucleic acid amplification test confirmed SARS-CoV2 positive.
SAMPLE SIZE (n. patients):
The study will collect all patients with the inclusion criteria; a total of 500 patients are expected to be collected.
About 80 patients will be enrolled for each local experimental center.
The following patient data will be analyzed:
The machine learning approach of lung CT scan analysis will aim at evaluating:
ETHICAL ASPECTS:
The lung CT scan images will be collected and anonymized. Images will be subsequently sent by University of Milano-Bicocca Institutional google drive account to the University of Pennsylvania, Department of Anesthesiology and Critical Care and the Department of Radiology in a deidentified format for advanced quantitative analysis taking advantage of artificial intelligence using deep learning algorithms.
The data will be collected in a pseudo-anonymous way through paper Case Report Form (CRF) and analyzed by the scientific coordinator of the project.
Given the retrospective nature of the study and in the presence of technical difficult in obtaining an informed consent of patients in this period of pandemic emergency, informed consent will be waived.
STATISTICAL ANALYSIS:
Continuous data will be expressed as mean ± standard deviation or median and interquartile range, according to data distribution that will be evaluated by the Shapiro-Wilk test. Categorical variables will be expressed as proportions (frequency).
The deep learning segmentation algorithm will segment the lung parenchyma from the entire CT lung. Lung volume, lung weight and opacity intensity distribution analysis will be applied. Second, clustering analysis to stratify the patients will be performed. Both an intensity and a spatial clustering algorithm will be tested. Third, a model will be trained to predict the injury progression using the images and all other patient data. Statistical significance will be considered in the presence of a p\<0.05 (two-tailed).
399 studies on the registry are indexed under Lung Injury; 50 are open to participants now.
This study's enrollment of 44 is below the median of 70 across 136 observational studies indexed under Lung Injury.
Browse Lung Injury studies →University of Milano Bicocca is the lead sponsor of 124 studies on the registry; 48 are open to participants now.
Counted across the registry records on this site, refreshed daily.
The goal is to collect as many lung CT scan images as possible in patients with COVID-19; according to the preliminary evaluation estimate, a total of 500 patients are expected to be collected.
Inclusion Criteria (COVID-19 cohort):
Inclusion criteria (ARDS cohort):
Exclusion criteria (ARDS cohort):
● Positive confirmation with nucleic acid amplification test or serology of SARS-CoV2 by naso-pharyngeal swab, bronchoaspirate sample or bronchoalveolar lavage
The study aims to collect the highest number possible of lung CT scan images performed in patients with COVID-19, in order to obtain a large sample size that will allow us to characterize the extent of lung injury, the presence of specific patterns of lung alteration, and their potential association with the outcome of patients - in view of assisting the medical staff in better understanding the grade of the severity impairment in these patients which might be potentially candidates to more intensive therapeutic strategies.
Other: Lung CT scan analysis in COVID-19 patients
This research project will evaluate the morphological characteristics of the lung by CT scan analysis in COVID-19 patients which will be identified as specific patterns using artificial intelligence technology and their impact on outcome.
A qualitative analysis of parenchymal lung damage induced by COVID-19
Describe the parenchymal lung damage induced by COVID-19 through a qualitative analysis with chest CT through artificial intelligence techniques.
Time frame: Until patient discharge from the hospital (approximately 6 months)
A quantitative analysis of parenchymal lung damage induced by COVID-19
Describe the parenchymal lung damage induced by COVID-19 through a quantitative analysis with chest CT through artificial intelligence techniques.
Time frame: Until patient discharge from the hospital (approximately 6 months)
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as intensive care mortality.
Time frame: Until patient discharge from the hospital (approximately 6 months)
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as hospital mortality.
Time frame: Until patient discharge from the hospital (approximately 6 months)
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure.
The potential impact of parenchymal morphological CT scans in patients with severe moderate respiratory failure assessed as days free from mechanical ventilation.
Time frame: Until patient discharge from the hospital (approximately 6 months)
Automated segmentation of lung scans of patients with COVID-19 and ARDS.
The hypothesis is that the uso of deep neural network models for lung segmentation in Acute Respiratory Distress Syndrome (ARDS) in animal models and Chronic Obstructive Pulmonary Disease (COPD) in patients that could be applied to self-segment the lungs of COVID-19 patients through a learning transfer mechanism with artificial intelligence.
Time frame: Until patient discharge from the hospital (approximately 6 months)
Knowledge of chest CT features in COVID-19 patients and their detail through the use of machine learning and other quantitative techniques.
Expand the knowledge of chest CT features in COVID-19 patients and their detail through the use of machine learning and other quantitative techniques comparing CT patterns of COVID-19 patients to those of patients with ARDS.
Time frame: Until patient discharge from the hospital (approximately 6 months)
The ability within which the analysis of artificial intelligence that uses deep learning models can be used to predict clinical outcomes
Determine the capacity within which the artificial intelligence analysis that uses deep learning models can be used to predict clinical outcomes from the analysis of the characteristics of the chest CT obtained within 7 days of hospital admission; combining quantitative CT data with clinical data.
Time frame: Until patient discharge from the hospital (approximately 6 months)
Plan to share: No
This study is completed, as verified in Jul 2022. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
University of Milano Bicocca