pcMSC Modulates Immune Dysregulation in Patients With COVID-19-Induced Refractory Acute Lung Injury.

Background and Objectives: The novel coronavirus disease 2019 (COVID-19) has been a pandemic health issue in 30 January 2020. The mortality rate is as high as 50% in critically ill patients. Stem cell therapy is effective for those who are refractory to standard treatments. However, the immune responses that underlie stem cell therapy have not been well reported, particularly, in patients associated with moderate to severe acute respiratory distress syndrome (ARDS). Methods: On Days 0 and 4, an intravenous infusion of 2 × 107 placenta-derived mesenchymal stem cells (pcMSCs) (MatriPlax) were administered to five severe COVID-19 patients refractory to current standard therapies. Peripheral blood inflammatory markers and immune profiles were determined by multi-parameter flow cytometry and studied at Days 0, 4, and 8. Clinical outcomes were also observed. Results: None of the pc-MSC treated patients experienced 28-day mortality compared with the control group and showed a significant improvement in the PaO2/FiO2 ratio, Murray's lung injury scores, reduction in serum ferritin, lactate dehydrogenase (LDH), and C-reactive protein (CRP) levels. The cytokine profiles also showed a reduction in IL-1ß, IFN-γ, IL-2, and IL-6, and an increase in IL-13 and IL-5 type 2 cytokines within 7 days of therapy. Lymphopenia was also significantly improved after 7 days of treatment. Immune cell profiles showed an increase in the proportions of CD4+ T cells (namely, CD4+ naïve T cells and CD4+ memory T cell subtypes), Treg cells, CD19+ B cells (namely, CD19+ naïve B cells, CD27+ switched B cell subtypes) and dendritic cells, and a significant decrease in the proportion of CD14+ monocytes (namely, CD16- classical and CD16+ non-classical subtypes), and plasma/plasmablast cells. No adverse effects were seen at the serial follow-up visits for 2 months after initial therapy. Conclusion: pc-MSCs therapy suppressed hyper-inflammatory states of the innate immune response to COVID-19 infection by increasing Treg cells, decreasing monocytes and plasma/plasmablast cells, and promoting CD4+ T cells and CD19+ B cells toward adaptive immune responses in severely critically ill COVID-19 patients with moderate to severe ARDS, especially those who were refractory to current standard care and immunosuppressive therapies.

Using Transfer Learning Method to Develop an Artificial Intelligence Assisted Triaging for Endotracheal Tube Position on Chest X-ray.

Endotracheal tubes (ETTs) provide a vital connection between the ventilator and patient; however, improper placement can hinder ventilation efficiency or injure the patient. Chest X-ray (CXR) is the most common approach to confirming ETT placement; however, technicians require considerable expertise in the interpretation of CXRs, and formal reports are often delayed. In this study, we developed an artificial intelligence-based triage system to enable the automated assessment of ETT placement in CXRs. Three intensivists performed a review of 4293 CXRs obtained from 2568 ICU patients. The CXRs were labeled "CORRECT" or "INCORRECT" in accordance with ETT placement. A region of interest (ROI) was also cropped out, including the bilateral head of the clavicle, the carina, and the tip of the ETT. Transfer learning was used to train four pre-trained models (VGG16, INCEPTION_V3, RESNET, and DENSENET169) and two models developed in the current study (VGG16_Tensor Projection Layer and CNN_Tensor Projection Layer) with the aim of differentiating the placement of ETTs. Only VGG16 based on ROI images presented acceptable performance (AUROC = 92%, F1 score = 0.87). The results obtained in this study demonstrate the feasibility of using the transfer learning method in the development of AI models by which to assess the placement of ETTs in CXRs.