Assessing the Severity of COVID-19 Lung Injury in Rheumatic Diseases Versus the General Population Using Deep Learning-Derived Chest Radiograph Scores

Risk factors and outcomes for repeat COVID-19 infection among patients with systemic autoimmune rheumatic diseases: A case-control study

OBJECTIVE

To investigate risk factors and outcomes of repeat COVID-19 infections among patients with systemic autoimmune rheumatic diseases (SARDs).

METHODS

We performed a case-control study investigating repeat COVID-19 infection within the Mass General Brigham Health Care System. We systematically identified all SARD patients with confirmed COVID-19 (15/Mar/2020 to 17/Oct/2022). Cases had confirmed repeat COVID-19 infections >60 days apart (index date: repeat COVID-19 date). Controls were matched to cases (up to 3:1) by calendar date of first infection and duration between first COVID-19 infection and index dates. We collected demographics, lifestyle, comorbidities, SARD features, and COVID-19 characteristics at initial infection and index date by medical record review. We used conditional logistic regression to identify associations with repeat COVID-19 infection, adjusting for potential confounders. We described the severity of repeat COVID-19 infection among cases.

RESULTS

Among 2203 SARD patients with COVID-19, we identified 76 cases with repeat COVID-19 infection (80.3 % female) and matched to 207 matched controls (77.8 % female) with no repeat infection. At first infection, cases were younger (mean 49.5 vs. 60.3 years, p < 0.0001), less likely to have hypertension (32.9 % vs. 45.9 %, p = 0.050), and less likely to have been hospitalized for COVID-19 (13.2 % vs. 24.6 %, p = 0.037) than controls. At index date, cases were more likely than controls to be rituximab users (18.4 % vs. 6.3 %, p = 0.0021). In the multivariable model, younger age (OR 0.67 per 10 years, 95 %CI 0.54-0.82), rituximab use vs. non-use (OR 3.38, 95 %CI 1.26-9.08), and methotrexate use vs. non-use (OR 2.24, 95 %CI 1.08-4.61) were each associated with repeat COVID-19 infection. Among those with repeat COVID-19 infection, 5/76 (6.6 %) were hospitalized and there were no deaths.

CONCLUSION

Younger age, rituximab, and methotrexate were each associated with repeat COVID-19 infection risk among patients with SARDs. Reassuringly, there were no deaths, and the hospitalization rate was low among those with repeat COVID-19 infection.

A Hybrid Decision Tree and Deep Learning Approach Combining Medical Imaging and Electronic Medical Records to Predict Intubation Among Hospitalized Patients With COVID-19: Algorithm Development and Validation

BACKGROUND

Early prediction of the need for invasive mechanical ventilation (IMV) in patients hospitalized with COVID-19 symptoms can help in the allocation of resources appropriately and improve patient outcomes by appropriately monitoring and treating patients at the greatest risk of respiratory failure. To help with the complexity of deciding whether a patient needs IMV, machine learning algorithms may help bring more prognostic value in a timely and systematic manner. Chest radiographs (CXRs) and electronic medical records (EMRs), typically obtained early in patients admitted with COVID-19, are the keys to deciding whether they need IMV.

OBJECTIVE

We aimed to evaluate the use of a machine learning model to predict the need for intubation within 24 hours by using a combination of CXR and EMR data in an end-to-end automated pipeline. We included historical data from 2481 hospitalizations at The Mount Sinai Hospital in New York City.

METHODS

CXRs were first resized, rescaled, and normalized. Then lungs were segmented from the CXRs by using a U-Net algorithm. After splitting them into a training and a test set, the training set images were augmented. The augmented images were used to train an image classifier to predict the probability of intubation with a prediction window of 24 hours by retraining a pretrained DenseNet model by using transfer learning, 10-fold cross-validation, and grid search. Then, in the final fusion model, we trained a random forest algorithm via 10-fold cross-validation by combining the probability score from the image classifier with 41 longitudinal variables in the EMR. Variables in the EMR included clinical and laboratory data routinely collected in the inpatient setting. The final fusion model gave a prediction likelihood for the need of intubation within 24 hours as well.

RESULTS

At a prediction probability threshold of 0.5, the fusion model provided 78.9% (95% CI 59%-96%) sensitivity, 83% (95% CI 76%-89%) specificity, 0.509 (95% CI 0.34-0.67) F1-score, 0.874 (95% CI 0.80-0.94) area under the receiver operating characteristic curve (AUROC), and 0.497 (95% CI 0.32-0.65) area under the precision recall curve (AUPRC) on the holdout set. Compared to the image classifier alone, which had an AUROC of 0.577 (95% CI 0.44-0.73) and an AUPRC of 0.206 (95% CI 0.08-0.38), the fusion model showed significant improvement (P<.001). The most important predictor variables were respiratory rate, C-reactive protein, oxygen saturation, and lactate dehydrogenase. The imaging probability score ranked 15th in overall feature importance.

CONCLUSIONS

We show that, when linked with EMR data, an automated deep learning image classifier improved performance in identifying hospitalized patients with severe COVID-19 at risk for intubation. With additional prospective and external validation, such a model may assist risk assessment and optimize clinical decision-making in choosing the best care plan during the critical stages of COVID-19.

Acute and postacute COVID-19 outcomes for patients with rheumatoid arthritis: lessons learned and emerging directions 3 years into the pandemic

PURPOSE OF REVIEW

To summarize the findings of studies investigating patients with rheumatoid arthritis (RA) and risk of acute and postacute COVID-19 outcomes 3 years into the pandemic.

RECENT FINDINGS

Most studies early in the pandemic included all patients with systemic autoimmune rheumatic diseases (SARDs), not only those with RA, due to limited sample size. Many of these studies found that patients with SARDs were at higher risk of COVID-19 infection and severe outcomes, including hospitalization, hyperinflammation, mechanical ventilation, and death. Studies performed later were able to focus on RA and found similar associations, while also identifying RA-specific factors such as immunosuppressive medications, disease activity/severity, and interstitial lung disease as risk factors for severe COVID-19. After COVID-19 vaccination, the risks for COVID-19 infection and severity were reduced for patients with RA, but a gap between the general population persisted, and some patients with RA are susceptible to breakthrough infection after vaccination. Preexposure prophylaxis, effective treatments, and changes in viral variants have also contributed to improved COVID-19 outcomes throughout the pandemic. Emerging data suggest that patients with RA may be at risk for postacute sequelae of COVID-19 (PASC).

SUMMARY

Although COVID-19 outcomes have improved over the pandemic for patients with RA, some experience poor acute and postacute outcomes after COVID-19. Clinicians and patients should remain vigilant about risk mitigation for infection and consider early treatment for RA patients with COVID-19. Future studies are needed to investigate clinical outcomes and mechanisms of PASC among patients with RA.