Risk Stratification for ECMO Requirement in COVID-19 ICU Patients Using Quantitative Imaging Features in CT Scans on Admission

Lung Imaging and Artificial Intelligence in ARDS

Artificial intelligence (AI) can make intelligent decisions in a manner akin to that of the human mind. AI has the potential to improve clinical workflow, diagnosis, and prognosis, especially in radiology. Acute respiratory distress syndrome (ARDS) is a very diverse illness that is characterized by interstitial opacities, mostly in the dependent areas, decreased lung aeration with alveolar collapse, and inflammatory lung edema resulting in elevated lung weight. As a result, lung imaging is a crucial tool for evaluating the mechanical and morphological traits of ARDS patients. Compared to traditional chest radiography, sensitivity and specificity of lung computed tomography (CT) and ultrasound are higher. The state of the art in the application of AI is summarized in this narrative review which focuses on CT and ultrasound techniques in patients with ARDS. A total of eighteen items were retrieved. The primary goals of using AI for lung imaging were to evaluate the risk of developing ARDS, the measurement of alveolar recruitment, potential alternative diagnoses, and outcome. While the physician must still be present to guarantee a high standard of examination, AI could help the clinical team provide the best care possible.

Hemorrhage, Disseminated Intravascular Coagulopathy, and Thrombosis Complications Among Critically Ill Patients with COVID-19: An International COVID-19 Critical Care Consortium Study

OBJECTIVES

To determine the prevalence and outcomes associated with hemorrhage, disseminated intravascular coagulopathy, and thrombosis (HECTOR) complications in ICU patients with COVID-19.

DESIGN

Prospective, observational study.

SETTING

Two hundred twenty-nine ICUs across 32 countries.

PATIENTS

Adult patients (≥ 16 yr) admitted to participating ICUs for severe COVID-19 from January 1, 2020, to December 31, 2021.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

HECTOR complications occurred in 1,732 of 11,969 study eligible patients (14%). Acute thrombosis occurred in 1,249 patients (10%), including 712 (57%) with pulmonary embolism, 413 (33%) with myocardial ischemia, 93 (7.4%) with deep vein thrombosis, and 49 (3.9%) with ischemic strokes. Hemorrhagic complications were reported in 579 patients (4.8%), including 276 (48%) with gastrointestinal hemorrhage, 83 (14%) with hemorrhagic stroke, 77 (13%) with pulmonary hemorrhage, and 68 (12%) with hemorrhage associated with extracorporeal membrane oxygenation (ECMO) cannula site. Disseminated intravascular coagulation occurred in 11 patients (0.09%). Univariate analysis showed that diabetes, cardiac and kidney diseases, and ECMO use were risk factors for HECTOR. Among survivors, ICU stay was longer (median days 19 vs 12; p < 0.001) for patients with versus without HECTOR, but the hazard of ICU mortality was similar (hazard ratio [HR] 1.01; 95% CI 0.92-1.12; p = 0.784) overall, although this hazard was identified when non-ECMO patients were considered (HR 1.13; 95% CI 1.02-1.25; p = 0.015). Hemorrhagic complications were associated with an increased hazard of ICU mortality compared to patients without HECTOR complications (HR 1.26; 95% CI 1.09-1.45; p = 0.002), whereas thrombosis complications were associated with reduced hazard (HR 0.88; 95% CI 0.79-0.99, p = 0.03).

CONCLUSIONS

HECTOR events are frequent complications of severe COVID-19 in ICU patients. Patients receiving ECMO are at particular risk of hemorrhagic complications. Hemorrhagic, but not thrombotic complications, are associated with increased ICU mortality.

Prognostic models in COVID-19 infection that predict severity: a systematic review

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

Temporary mechanical circulatory support for COVID‐19 patients: A systematic review of literature

Objective

Myocardial damage occurs in up to 25% of coronavirus disease 2019 (COVID‐19) cases. While veno‐venous extracorporeal life support (V‐V ECLS) is used as respiratory support, mechanical circulatory support (MCS) may be required for severe cardiac dysfunction. This systematic review summarizes the available literature regarding MCS use rates, disease drivers for MCS initiation, and MCS outcomes in COVID‐19 patients.

Methods

PubMed/EMBASE were searched until October 14, 2021. Articles including adults receiving ECLS for COVID‐19 were included. The primary outcome was the rate of MCS use. Secondary outcomes included mortality at follow‐up, ECLS conversion rate, intubation‐to‐cannulation time, time on ECLS, cardiac diseases, use of inotropes, and vasopressors.

Results

Twenty‐eight observational studies (comprising both ECLS‐only populations and ECLS patients as part of larger populations) included 4218 COVID‐19 patients (females: 28.8%; median age: 54.3 years, 95%CI: 50.7–57.8) of whom 2774 (65.8%) required ECLS with the majority (92.7%) on V‐V ECLS, 4.7% on veno‐arterial ECLS and/or Impella, and 2.6% on other ECLS. Acute heart failure, cardiogenic shock, and cardiac arrest were reported in 7.8%, 9.7%, and 6.6% of patients, respectively. Vasopressors were used in 37.2%. Overall, 3.1% of patients required an ECLS change from V‐V ECLS to MCS for heart failure, myocarditis, or myocardial infarction. The median ECLS duration was 15.9 days (95%CI: 13.9–16.3), with an overall survival of 54.6% and 28.1% in V‐V ECLS and MCS patients. One study reported 61.1% survival with oxy‐right ventricular assist device.

Conclusion

MCS use for cardiocirculatory compromise has been reported in 7.3% of COVID‐19 patients requiring ECLS, which is a lower percentage compared to the incidence of any severe cardiocirculatory complication. Based on the poor survival rates, further investigations are warranted to establish the most appropriated indications and timing for MCS in COVID‐19.

The Year in Extracorporeal Membrane Oxygenation: Selected Highlights From 2021

This review summarizes the extracorporeal membrane oxygenation (ECMO) or extracorporeal life support literature published in 2021. This Selected Highlights article is not intended to be an exhaustive review of the literature, but rather a summarizing of key themes that developed in the ECMO literature during 2021. The primary topics presented include the following: ECMO for coronavirus disease 2019, extracorporeal cardiopulmonary resuscitation, periprocedural cardiopulmonary support with ECMO, and anticoagulation for ECMO.

Sequential Organ Failure Assessment Outperforms Quantitative Chest CT Imaging Parameters for Mortality Prediction in COVID-19 ARDS

(1) Background: Respiratory insufficiency with acute respiratory distress syndrome (ARDS) and multi-organ dysfunction leads to high mortality in COVID-19 patients. In times of limited intensive care unit (ICU) resources, chest CTs became an important tool for the assessment of lung involvement and for patient triage despite uncertainties about the predictive diagnostic value. This study evaluated chest CT-based imaging parameters for their potential to predict in-hospital mortality compared to clinical scores. (2) Methods: 89 COVID-19 ICU ARDS patients requiring mechanical ventilation or continuous positive airway pressure mask ventilation were included in this single center retrospective study. AI-based lung injury assessment and measurements indicating pulmonary hypertension (PA-to-AA ratio) on admission CT, oxygenation indices, lung compliance and sequential organ failure assessment (SOFA) scores on ICU admission were assessed for their diagnostic performance to predict in-hospital mortality. (3) Results: CT severity scores and PA-to-AA ratios were not significantly associated with in-hospital mortality, whereas the SOFA score showed a significant association (p < 0.001). In ROC analysis, the SOFA score resulted in an area under the curve (AUC) for in-hospital mortality of 0.74 (95%-CI 0.63–0.85), whereas CT severity scores (0.53, 95%-CI 0.40–0.67) and PA-to-AA ratios (0.46, 95%-CI 0.34–0.58) did not yield sufficient AUCs. These results were consistent for the subgroup of more critically ill patients with moderate and severe ARDS on admission (oxygenation index <200, n = 53) with an AUC for SOFA score of 0.77 (95%-CI 0.64–0.89), compared to 0.55 (95%-CI 0.39–0.72) for CT severity scores and 0.51 (95%-CI 0.35–0.67) for PA-to-AA ratios. (4) Conclusions: Severe COVID-19 disease is not limited to lung (vessel) injury but leads to a multi-organ involvement. The findings of this study suggest that risk stratification should not solely be based on chest CT parameters but needs to include multi-organ failure assessment for COVID-19 ICU ARDS patients for optimized future patient management and resource allocation.

[Integration of structured reporting into the routine radiological workflow]

Klinisches/methodisches Problem

Strukturierte Befundung ist seit Jahren eines der meist diskutierten Themen in der Radiologie. Aktuell herrscht ein Mangel an nutzerfreundlichen Softwarelösungen, welche in die bestehende IT-Infrastruktur der Kliniken und Praxen integriert sind und effiziente Dateneingaben erlauben.

Radiologische Standardverfahren

Radiologische Befunde werden meist als Freitext über Spracherkennungssysteme diktiert oder per Tastatur eingegeben. Zudem werden Textbausteine für die Erstellung von Normalbefunden verwendet und bei Bedarf durch Freitextinhalte ergänzt.

Methodische Innovationen

Softwarebasierte Befundungssysteme können Spracherkennungssysteme mit radiologischen Befundvorlagen in Form von interaktiven Entscheidungsbäumen vereinen. Eine technische Integration in RIS(Radiologieinformationssystem)-, PACS(„picture archiving and communication system“)- und AV(„advanced visualization“)-Systeme über Programmierschnittstellen und Interoperabilitätsstandards ermöglicht effiziente Prozesse und die Generierung maschinenlesbarer Befunddaten.

Leistungsfähigkeit

Strukturierte, semantisch annotierte klinische Daten, die über ein strukturiertes Befundungssystem erhoben werden, stehen unmittelbar für epidemiologische Datenauswertungen und kontinuierliches KI(Künstliche Intelligenz)-Training zur Verfügung.

Bewertung

Der Einsatz der strukturierten Befundung in der radiologischen Routinediagnostik ist mit einer initialen Umstellungsphase verbunden. Eine erfolgreiche Implementierung setzt eine enge Verzahnung der technischen Infrastruktur mehrerer Systeme voraus.

Empfehlung für die Praxis

Durch die Nutzung einer hybriden, softwarebasierten Befundungslösung können radiologische Befunde mit unterschiedlichen Stufen der Struktur generiert werden. Klinische Fragestellungen oder Informationen können aus klinischen Subsystemen semiautomatisch übertragen werden, um vermeidbare Fehler zu eliminieren und die Produktivität zu erhöhen.