ABSTRACT
Lung transplantation (LT) quickly emerged as an accepted therapy for respiratory failure due to COVID. Since March 2020, progress had been made in therapeutics, vaccines, and other preventive measures. Variants with milder disease also emerged over the course of the pandemic. We aimed to examine patient demographics, illness severity, and frequency of listing and LT for respiratory failure due to COVID over time in the U.S. We retrospectively queried the OPTN database, administered by UNOS. We included all adults aged 18 years and older who were listed for LT from March 2020 to June 2022 with primary diagnoses of COVID-19 (1616 (COVID 19-ARDS), 1617 (COVID-19 pulmonary fibrosis) or ARDS (402). We included those with a diagnosis of ARDS to avoid unintentional exclusion of patients with respiratory failure due to COVID-19, particularly at the onset of the pandemic. 536 patients were listed, with 431 patients (80%) undergoing LT, between March 2020 to June 2022 for primary diagnoses of COVID ARDS, COVID-pulmonary fibrosis, and ARDS. The listed patients were median age of 51 years-old, mostly male (72%), and were most commonly Caucasian (53%). They were most frequently listed for double lung transplant (83%) and were in the ICU (77%) with 51% on ECMO and 35% on MV at the time of listing. Nine percent on the wait list (WL) died prior to LT. Out of 57 patients (10%) with other outcome, 45% remained on WL while 42% were removed from WL for clinical improvement. Over the course of the pandemic, increasingly, patients were outside of the ICU with decreased rates of MV and ECMO at the time of listing and transplant. LT continued to be performed for respiratory failure due to COVID-19 as of June 2022. There had been no official guidelines delineating the usage of the diagnoses COVID ARDS vs. COVID-pulmonary fibrosis. However, it appears that patients listed for COVID ARDS had a significantly higher median LAS score;were younger;were more likely to be in the ICU, and on MV and ECMO at time of listing and transplant. [ FROM AUTHOR] Copyright of Journal of Heart & Lung Transplantation is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
Background: Revised guidelines clarify indications for extracorporeal membrane oxygenation (ECMO) support in patients with COVID-19-related acute respiratory distress syndrome (ARDS). Commercially available ECMO analytics software records granular perfusion data continuously throughout the run. To date, electronic-medical record (EMR) clinical data has not been integrated with ECMO perfusion data and analyzed with machine learning-based algorithms to improve patient care. Methods: Retrospective chart review was performed on all SARS-CoV2 positive patients cannulated to veno-venous ECMO at an urban highvolume regional referral center from March 1st, 2020, through December 31st, 2021. Categorical data including patient demographics, clinical outcomes, and laboratory data (complete blood count, basic metabolic panel, arterial blood gas, lactate, anticoagulation assays) and vital signs (pulse, arterial line blood pressure, oxygen saturation) were collected for the entirety of the ECMO run. Time-series perfusion data (arterial flow normalized to body surface area (BSA), sweep gas, delta pressures normalized to arterial flow) were captured every 60-120 seconds. We constructed a predictive long-short term memory (LSTM) predictive model that integrated clinical and time-series data using an extended machine learning (ML) framework with neural network. Primary outcome was successful ECMO decannulation. Data were truncated to discrete and relative timepoints (7, 14, 21 days, or percent of the run). Receiver operating characteristic (ROC) curves show the model's diagnostic accuracy. Results: 42 patients were included in the analysis (30 male, 12 female). Mean age was 43.9 (SD=11.5) years old, and mean duration of ECMO run was 36.2 (SD=30.1) days. 24 patients were successfully decannulated and 4 are currently supported on ECMO. When provided the complete data, the LSTM model showed an area under the ROC curve >0.95, demonstrating strong diagnostic accuracy in predicting successful ECMO decannulation (Figure 1A). When data were truncated to only the first two weeks of the ECMO run, the area under the ROC curve was 0.93 (Fig. 1B). Patterns of arterial flow normalized to BSA and sweep gas normalized to flow also appear different in patients with divergent clinical outcomes (Fig 2). Conclusion: Characterizing key determinants of ECMO support may offer intensive care unit healthcare teams potentially lifesaving information in real-time. Our machine-learning model successfully integrates clinical and perfusion data from the mind's eye of a clinician managing the care of a patient supported with ECMO. We have identified critical variables with the most meaningful impact on the mechanics of ECMO support. Our model may also help predict patient outcomes into and offer clinicians opportunities for interventions to improve care. (Figure Presented).