Integrated Clinical and CT Based Artificial Intelligence Nomogram for Predicting Severity and Need for Ventilator Support in COVID-19 Patients: A Multi-Site Study

Abstract

Almost 25% of COVID-19 patients end up in ICU needing critical mechanical ventilation support. There is currently no validated objective way to predict which patients will end up needing ventilator support, when the disease is mild and not progressed. N = 869 patients from two sites (D 1 : N = 822, D 2 : N = 47) with baseline clinical characteristics and chest CT scans were considered for this study. The entire dataset was randomly divided into 70% training, D 1 train (N = 606) and 30% test-set (D test : D 1 test (N = 216) + D 2 (N = 47)). An expert radiologist delineated ground-glass-opacities (GGOs) and consolidation regions on a subset of D 1 train , (D 1 train_sub , N = 88). These regions were automatically segmented and used along with their corresponding CT volumes to train an imaging AI predictor Manuscript

Exploring the clinical benefit of ventilation therapy across various patient groups with COVID-19 using real-world data

“…Nevertheless, there has not been much evidence on how much patients of different age groups with various underlying conditions actually benefitted from ventilation therapy based on real-world data. Some studies made endeavours to predict COVID-19 severity 20 , 21 or the need for mechanical ventilation 21 , 22 ; however, their approaches have not been investigated in the real-world to determine their outcomes.…”

Optimization of Ventilation Therapy Prioritization Strategies among Patients with COVID-19: Lessons Learned from Real-World Data of nearly 600,000 Hospitalized Patients

“…Nevertheless, there has not been much evidence on how much patients of different age groups with various underlying conditions actually benefitted from ventilation therapy based on real-world data. Some studies made endeavours to predict COVID-19 severity (20) or the need for mechanical ventilation (21); however, their approaches have not been investigated in the real-world to determine their outcomes.…”

Deep-learning-based hepatic fat assessment (DeHFt) on non-contrast chest CT and its association with disease severity in COVID-19 infections: A multi-site retrospective study

“…The third cohort used for the study was the Stony Brook University COVID-19 Positive Cases dataset (D3), 24 which contains non-contrast chest CTs from 169 patients who tested positive for COVID-19. Patients were categorised into two groups based on the disease severity 25 : severe (requiring invasive mechanical ventilation, extracorporeal membrane oxygenation, or death) vs non-severe (no invasive ventilator support (no respiratory distress, oxygen supplementation, non-invasive ventilation). Altogether, three different cohorts of patients—D1, N = 805 (465 severe and 340 non-severe); D2, N = 1917 (288 severe, 887 non-severe, and 742 non-diseased); D3, N = 169 (47 severe and 122 non-severe)—were used to explore the association between automated HS quantification by the DeHFt pipeline with clinical severity of COVID-19 infections, given the known associations between HS and COVID-19 outcomes.…”