Severe COVID-19 pneumonia leads to post-COVID-19 lung abnormalities on follow-up CT scans ☆

Purpose To investigate the association of the maximal severity of pneumonia on CT scans obtained within 6-week of diagnosis with the subsequent development of post-COVID-19 lung abnormalities (Co-LA). Methods COVID-19 patients diagnosed at our hospital between March 2020 and September 2021 were studied retrospectively. The patients were included if they had (1) at least one chest CT scan available within 6-week of diagnosis;and (2) at least one follow-up chest CT scan available ≥6 months after diagnosis, which were evaluated by two independent radiologists. Pneumonia Severity Categories were assigned on CT at diagnosis according to the CT patterns of pneumonia and extent as: 1) no pneumonia (Estimated Extent, 0%);2) non-extensive pneumonia (GGO and OP, <40%);and 3) extensive pneumonia (extensive OP and DAD, >40%). Co-LA on follow-up CT scans, categorized using a 3-point Co-LA Score (0, No Co-LA;1, Indeterminate Co-LA;and 2, Co-LA). Results Out of 132 patients, 42 patients (32%) developed Co-LA on their follow-up CT scans 6-24 months post diagnosis. The severity of COVID-19 pneumonia was associated with Co-LA: In 47 patients with extensive pneumonia, 33 patients (70%) developed Co-LA, of whom 18 (55%) developed fibrotic Co-LA. In 52 with non-extensive pneumonia, 9 (17%) developed Co-LA: In 33 with no pneumonia, none (0%) developed Co-LA. Conclusions Higher severity of pneumonia at diagnosis was associated with the increased risk of development of Co-LA after 6-24 months of SARS-CoV-2 infection.

Severe COVID-19 pneumonia leads to post-COVID-19 lung abnormalities on follow-up CT scans.

Purpose: To investigate the association of the maximal severity of pneumonia on CT scans obtained within 6-week of diagnosis with the subsequent development of post-COVID-19 lung abnormalities (Co-LA). Methods: COVID-19 patients diagnosed at our hospital between March 2020 and September 2021 were studied retrospectively. The patients were included if they had (1) at least one chest CT scan available within 6-week of diagnosis; and (2) at least one follow-up chest CT scan available ≥ 6 months after diagnosis, which were evaluated by two independent radiologists. Pneumonia Severity Categories were assigned on CT at diagnosis according to the CT patterns of pneumonia and extent as: 1) no pneumonia (Estimated Extent, 0%); 2) non-extensive pneumonia (GGO and OP, <40%); and 3) extensive pneumonia (extensive OP and DAD, >40%). Co-LA on follow-up CT scans, categorized using a 3-point Co-LA Score (0, No Co-LA; 1, Indeterminate Co-LA; and 2, Co-LA). Results: Out of 132 patients, 42 patients (32%) developed Co-LA on their follow-up CT scans 6-24 months post diagnosis. The severity of COVID-19 pneumonia was associated with Co-LA: In 47 patients with extensive pneumonia, 33 patients (70%) developed Co-LA, of whom 18 (55%) developed fibrotic Co-LA. In 52 with non-extensive pneumonia, 9 (17%) developed Co-LA: In 33 with no pneumonia, none (0%) developed Co-LA. Conclusions: Higher severity of pneumonia at diagnosis was associated with the increased risk of development of Co-LA after 6-24 months of SARS-CoV-2 infection.

COVID-19 Vaccination reduced pneumonia severity.

Purpose: To investigate the effect of vaccinations and boosters on the severity of COVID-19 pneumonia on CT scans during the period of Delta and Omicron variants. Methods: Retrospectively studied were 303 patients diagnosed with COVID-19 between July 2021 and February 2022, who had obtained at least one CT scan within 6 weeks around the COVID-19 diagnosis (-2 to +4 weeks). The severity of pneumonia was evaluated with a 6-point scale Pneumonia Score. The association between demographic and clinical data and vaccination status (booster/additional vaccination, complete vaccination and un-vaccination) and the difference between Pneumonia Scores by vaccination status were investigated. Results: Of 303 patients (59.4 ± 16.3 years; 178 females), 62 (20 %) were in the booster/additional vaccination group, 117 (39 %) in the complete vaccination group, and 124 (41 %) in the unvaccinated group. Interobserver agreement of the Pneumonia Score was high (weighted kappa score = 0.875). Patients in the booster/additionally vaccinated group tended to be older (P = 0.0085) and have more underlying comorbidities (P < 0.0001), and the Pneumonia Scores were lower in the booster/additionally vaccinated [median 2 (IQR 0-4)] and completely vaccinated groups [median 3 (IQR 1-4)] than those in the unvaccinated group [median 4 (IQR 2-4)], respectively (P < 0.0001 and P < 0.0001, respectively). A multivariable linear analysis adjusted for confounding factors confirmed the difference. Conclusion: Vaccinated patients, with or without booster/additional vaccination, had milder COVID-19 pneumonia on CT scans than unvaccinated patients during the period of Delta and Omicron variants. This study supports the efficacy of the vaccine against COVID-19 from a radiological perspective.

Machine Learning and Prediction of All-Cause Mortality in COPD.

BACKGROUND: COPD is a leading cause of mortality. RESEARCH QUESTION: We hypothesized that applying machine learning to clinical and quantitative CT imaging features would improve mortality prediction in COPD. STUDY DESIGN AND METHODS: We selected 30 clinical, spirometric, and imaging features as inputs for a random survival forest. We used top features in a Cox regression to create a machine learning mortality prediction (MLMP) in COPD model and also assessed the performance of other statistical and machine learning models. We trained the models in subjects with moderate to severe COPD from a subset of subjects in Genetic Epidemiology of COPD (COPDGene) and tested prediction performance in the remainder of individuals with moderate to severe COPD in COPDGene and Evaluation of COPD Longitudinally to Identify Predictive Surrogate Endpoints (ECLIPSE). We compared our model with the BMI, airflow obstruction, dyspnea, exercise capacity (BODE) index; BODE modifications; and the age, dyspnea, and airflow obstruction index. RESULTS: We included 2,632 participants from COPDGene and 1,268 participants from ECLIPSE. The top predictors of mortality were 6-min walk distance, FEV1 % predicted, and age. The top imaging predictor was pulmonary artery-to-aorta ratio. The MLMP-COPD model resulted in a C index ≥ 0.7 in both COPDGene and ECLIPSE (6.4- and 7.2-year median follow-ups, respectively), significantly better than all tested mortality indexes (P < .05). The MLMP-COPD model had fewer predictors but similar performance to that of other models. The group with the highest BODE scores (7-10) had 64% mortality, whereas the highest mortality group defined by the MLMP-COPD model had 77% mortality (P = .012). INTERPRETATION: An MLMP-COPD model outperformed four existing models for predicting all-cause mortality across two COPD cohorts. Performance of machine learning was similar to that of traditional statistical methods. The model is available online at: https://cdnm.shinyapps.io/cgmortalityapp/.