SARS-CoV-2 Infection: Modulator of Pulmonary Embolism Paradigm

Immunothrombosis biomarkers as potential predictive factors of acute respiratory distress syndrome in moderate-to-critical COVID-19: A single-center, retrospective cohort study

BACKGROUND

Immunothrombosis, a process of inflammation and coagulation, is involved in sepsis-induced acute respiratory distress syndrome formation (ARDS). However, the clinical correlation between immunothrombosis biomarkers (including tissue factor [TF] and von Willebrand factor [vWF]) and coronavirus disease 2019 (COVID-19)-related ARDS is unknown. This study investigated ARDS development following moderate-to-critical COVID-19 and examined immunothrombosis biomarkers as ARDS predictors.

METHODS

This retrospective cohort study included patients with moderate-to-critical COVID-19 (n = 165) admitted to a northern teaching hospital during the 2021 pandemic in Taiwan, who had no COVID-19 vaccinations. Immunothrombosis biomarkers were compared between COVID-19 patients with and without ARDS (no-ARDS) and a control group consisting of 100 healthy individuals.

RESULTS

The study included 58 ARDS and 107 no-ARDS patients. In multivariable analysis, TF (aOR=1.031, 95% CI: 1.009-1.053, p = 0.006); and vWF (aOR=1.053, 95% CI: 1.002-1.105, p = 0.041) were significantly associated with ARDS episodes, after adjusting for other confounding factors. vWF and TF predicted ARDS with the area under the curve of 0.870 (95% CI: 0.796-0.945). Further mechanical ventilation analysis found TF to be correlated significantly with pCO₂ and ventilatory ratio.

CONCLUSIONS

TF and vWF levels potentially predicted ARDS development within 7 days of admission for COVID-19 after adjusting for traditional risk factors. TF correlated with ventilation impairment in COVID-19 ARDS but further prospective studies are needed.

Procoagulant Microvesicles in COVID-19 Patients: Possible Modulators of Inflammation and Prothrombotic Tendency

Background

The hypercoagulability and thrombotic tendency in coronavirus disease 2019 (COVID-19) is multifactorial, driven mainly by inflammation, and endothelial dysfunction. Elevated levels of procoagulant microvesicles (MVs) and tissue factor–bearing microvesicles (TF-bearing MVs) have been observed in many diseases with thrombotic tendency. The current study aimed to measure the levels of procoagulant MVs and TF-bearing MVs in patients with COVID-19 and healthy controls and to correlate their levels with platelet counts, D-Dimer levels, and other proposed calculated inflammatory markers.

Materials and Methods

Forty ICU-admitted patients with COVID-19 and 37 healthy controls were recruited in the study. Levels of procoagulant MVs and TF-bearing MVs in the plasma of the study population were measured using enzyme linked immunosorbent assay.

Results

COVID-19 patients had significantly elevated levels of procoagulant MVs and TF-bearing MVs as compared with healthy controls (P<0.001). Procoagulant MVs significantly correlated with TF-bearing MVs, D-dimer levels, and platelet count, but not with calculated inflammatory markers (neutrophil/lymphocyte ratio, platelet/lymphocyte ratio, and platelet/neutrophil ratio).

Conclusion

Elevated levels of procoagulant MVs and TF-bearing MVs in patients with COVID-19 are suggested to be (i) early potential markers to predict the severity of COVID-19 (ii) a novel circulatory biomarker to evaluate the procoagulant activity and severity of COVID-19.

How artificial intelligence improves radiological interpretation in suspected pulmonary embolism

Objectives

To evaluate and compare the diagnostic performances of a commercialized artificial intelligence (AI) algorithm for diagnosing pulmonary embolism (PE) on CT pulmonary angiogram (CTPA) with those of emergency radiologists in routine clinical practice.

Methods

This was an IRB-approved retrospective multicentric study including patients with suspected PE from September to December 2019 (i.e., during a preliminary evaluation period of an approved AI algorithm). CTPA quality and conclusions by emergency radiologists were retrieved from radiological reports. The gold standard was a retrospective review of CTPA, radiological and clinical reports, AI outputs, and patient outcomes. Diagnostic performance metrics for AI and radiologists were assessed in the entire cohort and depending on CTPA quality.

Results

Overall, 1202 patients were included (median age: 66.2 years). PE prevalence was 15.8% (190/1202). The AI algorithm detected 219 suspicious PEs, of which 176 were true PEs, including 19 true PEs missed by radiologists. In the cohort, the highest sensitivity and negative predictive values (NPVs) were obtained with AI (92.6% versus 90% and 98.6% versus 98.1%, respectively), while the highest specificity and positive predictive value (PPV) were found with radiologists (99.1% versus 95.8% and 95% versus 80.4%, respectively). Accuracy, specificity, and PPV were significantly higher for radiologists except in subcohorts with poor-to-average injection quality. Radiologists positively evaluated the AI algorithm to improve their diagnostic comfort (55/79 [69.6%]).

Conclusion

Instead of replacing radiologists, AI for PE detection appears to be a safety net in emergency radiology practice due to high sensitivity and NPV, thereby increasing the self-confidence of radiologists.

Key Points

• Both the AI algorithm and emergency radiologists showed excellent performance in diagnosing PE on CTPA (sensitivity and specificity ≥ 90%; accuracy ≥ 95%).

• The AI algorithm for PE detection can help increase the sensitivity and NPV of emergency radiologists in clinical practice, especially in cases of poor-to-moderate injection quality.

• Emergency radiologists recommended the use of AI for PE detection in satisfaction surveys to increase their confidence and comfort in their final diagnosis.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-08645-2.