Articles

The pulmonary characteristics of <i>Staphylococcus </i><i>aure</i><i>u</i><i>s</i> (<i>S</i><i>.</i><i> </i><i>aureus</i>) co-infection with respiratory viruses, such as SARS-CoV-2 and influenza virus, are still unclear.<b> </b><b>Case series</b>: Two patients with methicillin-susceptible <i>S</i><i>.</i><i> </i><i>aureus</i><i> </i>(MSSA) infection in the lungs co-infected with either SARS-CoV-2 or influenza virus are reported. Case 1 was a 66-year-old woman who was admitted with SARS-CoV-2 infection. Her chest X-ray and computed tomography (CT) showed multiple cavity formations with infiltration shadows, and MSSA was detected from her sputum and blood, suggesting COVID-19-related bacterial pneumonia and pulmonary embolism. No catheters had been used, but she had skin eruptions and a history of SARS-CoV-2 vaccination. Ampicillin/sulbactam (ABPC/SBT) was administered, and she finally improved. Case 2 was an 87-year-old man with a history of atopic dermatitis who was admitted with moderate pneumonia, and influenza virus co-infection was found. He showed multiple cavitary shadows, and MSSA was isolated from both his sputum and blood. He was diagnosed with influenza-related bacterial pulmonary embolism. No catheters had been used, but he had a history of influenza vaccination. He was also treated by ABPC/SBT and finally improved. <b>Conclusions:</b> These cases suggest that MSSA showed affinity to the lungs when co-infected with either SARS-CoV-2 or influenza virus, and it presented as septic emboli without catheter use. We should consider MSSA infection when patients have SARS-CoV-2 or influenza virus co-infection, and multiple cavity formation and skin disorders are seen, even though they were vaccinated and no catheters were used.

Artificial intelligence systems have been previously used to predict post-operative complications in small studies and single institutions. Here we developed a robust artificial intelligence model that predicts the risk of having cardiac, pulmonary, thromboembolic, or septic complications after elective, non-cardiac, non-ambulatory surgery. We combined structured and unstructured electronic health record data from 3.5 million surgical encounters from 25 medical centers between 2009 and 2017. Our neural network model predicted postoperative comorbidities 15 to 80 times faster than classical models. As such, our model can be used to assess the risk of having a specific complication postoperatively in a fraction of a second. With our model, we believe clinicians will be able to identify high-risk surgical patients and use their good judgment to mitigate upcoming risks, ultimately improving patient outcomes [1].