Deep learning reveals lung shape differences on baseline chest CT between mild and severe COVID-19: A multi-site retrospective study.

Severe COVID-19 can lead to extensive lung disease causing lung architectural distortion. In this study we employed machine learning and statistical atlas-based approaches to explore possible changes in lung shape among COVID-19 patients and evaluated whether the extent of these changes was associated with COVID-19 severity. On a large multi-institutional dataset (N = 3443), three different populations were defined; a) healthy (no COVID-19), b) mild COVID-19 (no ventilator required), c) severe COVID-19 (ventilator required), and the presence of lung shape differences between them were explored using baseline chest CT. Significant lung shape differences were observed along mediastinal surfaces of the lungs across all severity of COVID-19 disease. Additionally, differences were seen on basal surfaces of the lung when compared between healthy and severe COVID-19 patients. Finally, an AI model (a 3D residual convolutional network) characterizing these shape differences coupled with lung infiltrates (ground-glass opacities and consolidation regions) was found to be associated with COVID-19 severity.

An End-to-End Integrated Clinical and CT-Based Radiomics Nomogram for Predicting Disease Severity and Need for Ventilator Support in COVID-19 Patients: A Large Multisite Retrospective Study.

Objective: The disease COVID-19 has caused a widespread global pandemic with ~3. 93 million deaths worldwide. In this work, we present three models-radiomics (MRM), clinical (MCM), and combined clinical-radiomics (MRCM) nomogram to predict COVID-19-positive patients who will end up needing invasive mechanical ventilation from the baseline CT scans. Methods: We performed a retrospective multicohort study of individuals with COVID-19-positive findings for a total of 897 patients from two different institutions (Renmin Hospital of Wuhan University, D1 = 787, and University Hospitals, US D2 = 110). The patients from institution-1 were divided into 60% training, D 1 T ( N = 473 ) , and 40% test set D 1 V ( N = 314 ) . The patients from institution-2 were used for an independent validation test set D 2 V ( N = 110 ) . A U-Net-based neural network (CNN) was trained to automatically segment out the COVID consolidation regions on the CT scans. The segmented regions from the CT scans were used for extracting first- and higher-order radiomic textural features. The top radiomic and clinical features were selected using the least absolute shrinkage and selection operator (LASSO) with an optimal binomial regression model within D 1 T . Results: The three out of the top five features identified using D 1 T were higher-order textural features (GLCM, GLRLM, GLSZM), whereas the last two features included the total absolute infection size on the CT scan and the total intensity of the COVID consolidations. The radiomics model (MRM) was constructed using the radiomic score built using the coefficients obtained from the LASSO logistic model used within the linear regression (LR) classifier. The MRM yielded an area under the receiver operating characteristic curve (AUC) of 0.754 (0.709-0.799) on D 1 T , 0.836 on D 1 V , and 0.748 D 2 V . The top prognostic clinical factors identified in the analysis were dehydrogenase (LDH), age, and albumin (ALB). The clinical model had an AUC of 0.784 (0.743-0.825) on D 1 T , 0.813 on D 1 V , and 0.688 on D 2 V . Finally, the combined model, MRCM integrating radiomic score, age, LDH and ALB, yielded an AUC of 0.814 (0.774-0.853) on D 1 T , 0.847 on D 1 V , and 0.771 on D 2 V . The MRCM had an overall improvement in the performance of ~5.85% ( D 1 T : p = 0.0031; D 1 V p = 0.0165; D 2 V : p = 0.0369) over MCM. Conclusion: The novel integrated imaging and clinical model (MRCM) outperformed both models (MRM) and (MCM). Our results across multiple sites suggest that the integrated nomogram could help identify COVID-19 patients with more severe disease phenotype and potentially require mechanical ventilation.

Cardiogenic shock temporally associated with COVID-19 vaccination after prior COVID-19 infection: A case report.

The introduction of coronavirus 2019 (COVID-19) vaccination has been an integral force in stopping the spread of COVID-19 across the globe. While reported side effects of vaccination have predominantly been mild, in the last year reports have emerged of myocarditis following the BNT162b2 (Pfizer-BioNtech) and mRNA-1273 (Moderna) vaccinations. The adolescent and young adult population have been the population most reported, with over 1000 cases under review by the Centers for Disease Control (CDC) since April 2021. Here we report a case of a previously healthy 21-year-old male who developed Multisystem Inflammatory Syndrome in Adults (MIS-A) and following the second dose of the Pfizer-BioNtech vaccine. The young male initially presented with fever, leukocytosis with high neutrophil-lymphocyte ratio, severe cardiac illness, and positive COVID-19 nucleocapsid serology, consistent with MIS-A diagnosis. His case was complicated by cardiogenic shock, requiring brief venoarterial extracorporeal membrane oxygenation (VA-ECMO) support. While this report does not detract from the overwhelming benefit of vaccination from COVID-19, clinicians should be aware of this possible relationship in the future.

A novel cause of emergent hyperammonemia: Cryptococcal fungemia and meningitis.

Among etiologies of hyperammonemic emergencies, infection must be considered in certain clinical contexts, particularly among immunocompromised individuals. Although Cryptococcus neoformans is known to be urease-producing, to our knowledge it has not previously been described as a cause of hyperammonemia in patients. We report an immunocompromised man with acute on chronic kidney disease with hyperammonemic crisis due to Cryptococcal meningitis and fungemia. It is important to be aware of C. neoformans as a possible cause of hyperammonemia.

COVID-19 infection triggering Thrombotic Thrombocytopenic Purpura.

We present a 62-year-old gentleman with history of Crohn's disease, G6PD deficiency, who presented with immune-mediated thrombotic thrombocytopenia purpura (iTTP) one week after the diagnosis of COVID-19 infection. He was admitted with worsening dyspnea, acute renal failure, and profound thrombocytopenia with marked schistocytosis on peripheral smear. ADAMTS13 level was severely deficient. He was treated with oral prednisone, plasma exchange and rituximab with complete clinical resolution. Given the temporal association of this recurrent episode of iTTP with COVID-19 infection and no other discernible cause, COVID-19 infection was the most likely trigger.

Integrated Clinical and CT Based Artificial Intelligence Nomogram for Predicting Severity and Need for Ventilator Support in COVID-19 Patients: A Multi-Site Study.

Almost 25% of COVID-19 patients end up in ICU needing critical mechanical ventilation support. There is currently no validated objective way to predict which patients will end up needing ventilator support, when the disease is mild and not progressed. N = 869 patients from two sites (D1: N = 822, D2: N = 47) with baseline clinical characteristics and chest CT scans were considered for this study. The entire dataset was randomly divided into 70% training, D1train (N = 606) and 30% test-set (Dtest: D1test (N = 216) + D2 (N = 47)). An expert radiologist delineated ground-glass-opacities (GGOs) and consolidation regions on a subset of D1train, (D1train_sub, N = 88). These regions were automatically segmented and used along with their corresponding CT volumes to train an imaging AI predictor (AIP) on D1train to predict the need of mechanical ventilators for COVID-19 patients. Finally, top five prognostic clinical factors selected using univariate analysis were integrated with AIP to construct an integrated clinical and AI imaging nomogram (ClAIN). Univariate analysis identified lactate dehydrogenase, prothrombin time, aspartate aminotransferase, %lymphocytes, albumin as top five prognostic clinical features. AIP yielded an AUC of 0.81 on Dtest and was independently prognostic irrespective of other clinical parameters on multivariable analysis (p<0.001). ClAIN improved the performance over AIP yielding an AUC of 0.84 (p = 0.04) on Dtest. ClAIN outperformed AIP in predicting which COVID-19 patients ended up needing a ventilator. Our results across multiple sites suggest that ClAIN could help identify COVID-19 with severe disease more precisely and likely to end up on a life-saving mechanical ventilation.

LVAD Vasculitis Case Series: Suggestion of a New Fatal LVAD-Related Phenomenon.

Left ventricular assist devices (LVADs) are surgically implanted mechanical devices indicated for patients with advanced heart failure and are known to come with several complications. Here we present a case series, and review 1 documented report, of LVAD vasculitis, a presumed new LVAD immune/humoral related phenomenon. (Level of Difficulty: Advanced.).

A Multicenter Survey of House Staff Knowledge About Sepsis and the "Surviving Sepsis Campaign Guidelines for Management of Severe Sepsis and Septic Shock".

BACKGROUND: We aimed to assess the knowledge, attitudes, and perceptions of resident physicians regarding sepsis in general and the Surviving Sepsis Campaign Guidelines in particular. METHODS: After institutional review board approval, we surveyed internal medicine (IM) and emergency medicine (EM) house staff from 3 separate institutions. House staff were notified of the survey via e-mail from their residency director or chief resident. The survey was Internet-based (using http://www.surveymonkey.com ), voluntary, and anonymous. The Surviving Sepsis Campaign Guidelines were used to develop the survey. The survey was open between December 2015 and April 2016. No incentives for participation were given. Reminder e-mails were sent approximately every 3 to 4 weeks to all eligible participants. Comparisons of responses were evaluated using the N-1 2-proportion test. RESULTS: A total of 133 responses were received. These included 84 from IM house staff, 27 from EM house staff, and 22 who selected "other." Eighty (101/126) percent reported managing at least 1 patient with sepsis in the preceding 30 days, 85% (97/114) rated their knowledge of the Surviving Sepsis Guidelines as "very familiar" or at least "somewhat familiar," and 84% (91/108) believed their training in the diagnosis and management of sepsis was "excellent" or at least "good." However, 43% (47/108) reported not receiving any feedback on their treatment of patients with sepsis in the last 30 days, while 24% (26/108) received feedback once. Both IM and EM house staff received comparable rates of feedback (62% vs 48%, respectively; P = .21). For the 3 questions that directly tested knowledge of the guidelines, the scores of the IM and EM house staff were similar. Notably, <20% of both groups correctly identified diagnostic criteria for sepsis. CONCLUSION: Additional education of IM and EM house staff on the Surviving Sepsis Campaign Guidelines is warranted, along with more consistent feedback regarding their diagnosis and management of sepsis.

Culture-negative group B streptococcal pericarditis: A case report and literature review of the diagnostic use of polymerase chain reaction.

Although conventional microbiology cultures may be negative, polymerase chain reaction (PCR) can effectively identify both typical and atypical microorganisms. With careful interpretation, PCR could become the gold-standard diagnostic test for culture-negative bacterial pericarditis.

Medical management of tumor lysis syndrome, postprocedural pain, and venous thromboembolism following interventional radiology procedures.

The rapid expansion of minimally invasive image-guided procedures has led to their extensive use in the interdisciplinary management of patients with vascular, hepatobiliary, genitourinary, and oncologic diseases. Given the increased availability and breadth of these procedures, it is important for physicians to be aware of common complications and their management. In this article, the authors describe management of select common complications from interventional radiology procedures including tumor lysis syndrome, acute on chronic postprocedural pain, and venous thromboembolism. These complications are discussed in detail and their medical management is outlined according to generally accepted practice and evidence from the literature.

Occult Plasmodium vivax infection diagnosed by a polymerase chain reaction-based detection system: a case report.

After a trip to Zambia, a previously healthy adult traveler presented with a prolonged illness characterized by low-grade fevers and fatigue. Although malaria smears and antibody tests results for Plasmodium species were negative, a diagnosis of malaria was ultimately determined by polymerase chain reaction (PCR) amplification and species-specific nucleic acid hybridization techniques. The patient was successfully treated and cured. Clinical use of PCR technology may facilitate the identification of cases of smear-negative malaria, which up to the present time, have been difficult to diagnose.