Time to Endoscopic Vacuum Therapy: Lessons Learned after 150 Robotic-Assisted Minimally Invasive Esophagectomies at a German High-Volume Center

INTRODUCTION: For treatment of Esophagectomy Complications Consensus Group (ECCG) type II leak, self-expanding metal stents (SEMS) can be placed, or endoscopic vacuum therapy (EVT) can be applied;however, there are no prospective data concerning the optimal endoscopic treatment strategy. The aim of the study was to report outcomes of treatment strategies for patients with an ECCG type II anastomotic leak after robotic-assisted minimally invasive esophagectomy (RAMIE). METHOD(S): All patients who developed an ECCG type II anastomotic leak since the introduction of RAMIE at our high-volume center (>200 cases/y) were included in the analysis. Time to EVT, duration of EVT, and follow-up treatment were analyzed for all patients. RESULT(S): Since 2017, a total of 157 patients have undergone a RAMIE at our clinic. Twenty-three patients developed an ECCG type II anastomotic leak (14.6% leak rate). Successful completion was achieved in 21 of 23 of patients (91%). Two patients were deceased before the completion of endoscopic therapy: 1 of unrelated COVID-19 pneumonia and 1 of sepsis with unknown focus. Mean duration of EVT was12 days (range 4 to 28 days), mean of 2 endoscopic sponge changes (range 0 to 5). Anastomotic leak was diagnosed at a mean of 9 days postoperative (range 2 to 19 days). Placement of a SEMS was performed in 5 patients (24%) after completion of EVT. No patient needed conversion to operative therapy;however, pre-emptive EVT was performed after surgical revision in 3 patients (37.5%) with an ECCG type III leak. CONCLUSION(S): EVT has been shown to be a safe and successful treatment option for anastomotic leak after robotic-assisted esophagectomy with success rate of 91% in our cohort. No additional surgical revision was performed in any patient.

A Case of Pulmonary Cryptococcosis After Severe COVID-19 Pneumonia T. Roesch

Introduction / Case Presentation:46yo female with a history of CKD, atrial flutter, bioprosthetic valve with mitral ring, and recent COVID-19 pneumonia who presented to the emergency department (ED) with shortness of breath, fevers, and fatigue. Three months prior, she had been diagnosed with severe COVID-19 pneumonia, for which she received dexamethasone, remdesivir, tocilizumab, anakinra, and IVIG. She was discharged to a nursing facility with a prolonged steroid taper, ending 1 month prior to admission.In the ED, the patient had a chest x-ray that demonstrated bibasilar atelectasis and opacification, and a CT chest revealed right lower lobe consolidation and surrounding ground glass opacities. A respiratory pathogen PCR swab was negative. Sputum culture was negative for bacterial and fungal growth. Blood cultures did not grow any organisms. Given recent immunosuppression and imaging findings, a serum Cryptococcal antigen was drawn, which was positive with a titer of 1:128. A transthoracic needle biopsy of the patient's right lower lung was then performed. The specimen did not grow any bacteria or fungi and AFB stain on the tissue was negative. Pathology demonstrated a collection of histiocytes, neutrophils, and necrotic debris. PAS, GMS, and mucicarmine stains were positive for fungal organisms consistent with Cryptococcus species. Discussion: Cryptococcosis is a fungal infection due predominately to one of two encapsulated yeasts, Cryptococcus neoformans or Cryptococcus gattii. C. neoformans is found in soil worldwide, and infection typically begins with spore inhalation. Clinically significant disease is seen mostly in immunocompromised patients.Corticosteroids and interleukin inhibitors, such as anakinra (IL-1) and tocilizumab (IL-6), are used in the treatment of COVID-19. These medications have been associated with increased risk for opportunistic infections, including invasive fungal infections. The diagnosis of pulmonary cryptococcosis may be challenging, as symptoms are often nonspecific and may radiographically resemble bacterial pneumonia, malignancy, or other infections. Serum cryptococcal antigen detection tests may be helpful in establishing the diagnosis, as well as histopathology showing narrow-based budding yeast. Conclusion: Patients with prior COVID-19 infection commonly return to healthcare settings with sequelae of their previous coronavirus infection. In our case, it was the prior treatment of COVID-19, which included immunomodulating therapy, that lead to a secondary pulmonary cryptococcal infection. When evaluating pulmonary processes that evolve after an acute infection with COVID-19, it is important to keep a broad differential, including uncommon and/or opportunistic infectious etiologies, particularly when a patient has received prolonged courses of steroids and tocilizumab.

An Analysis on Ensemble Learning Optimized Medical Image Classification With Deep Convolutional Neural Networks

Novel and high-performance medical image classification pipelines are heavily utilizing ensemble learning strategies. The idea of ensemble learning is to assemble diverse models or multiple predictions and, thus, boost prediction performance. However, it is still an open question to what extent as well as which ensemble learning strategies are beneficial in deep learning based medical image classification pipelines. In this work, we proposed a reproducible medical image classification pipeline for analyzing the performance impact of the following ensemble learning techniques: Augmenting, Stacking, and Bagging. The pipeline consists of state-of-the-art preprocessing and image augmentation methods as well as 9 deep convolution neural network architectures. It was applied on four popular medical imaging datasets with varying complexity. Furthermore, 12 pooling functions for combining multiple predictions were analyzed, ranging from simple statistical functions like unweighted averaging up to more complex learning-based functions like support vector machines. Our results revealed that Stacking achieved the largest performance gain of up to 13% F1-score increase. Augmenting showed consistent improvement capabilities by up to 4% and is also applicable to single model based pipelines. Cross-validation based Bagging demonstrated significant performance gain close to Stacking, which resulted in an F1-score increase up to +11%. Furthermore, we demonstrated that simple statistical pooling functions are equal or often even better than more complex pooling functions. We concluded that the integration of ensemble learning techniques is a powerful method for any medical image classification pipeline to improve robustness and boost performance.

VAPING CAN BREAK YOUR HEART

TOPIC: Critical Care TYPE: Medical Student/Resident Case Reports INTRODUCTION: Electronic cigarette or vaping product use-associated lung injury (EVALI) is potentially life-threatening disease that has become increasingly recognized over the last years. However, the extra-pulmonary manifestations of this disease are not as well described. We present a patient who simultaneously developed acute EVALI and stress induced cardiomyopathy. CASE PRESENTATION: A 35-year-old female with a recent heavy vaping history presented to hospital via EMS due to disorganized behavior. Her past medical history was notable for polysubstance abuse and an extensive neuropsychiatric history. Her vital signs were notable for sinus tachycardia, hypotension and hypoxia with an oxyhemoglobin saturation 65%. Her physical exam was notable for cyanosis, rales to pulmonary auscultation and use of accessory muscles. She was intubated and started on empiric antibiotics for community acquired pneumonia, and vasopressors. A computer tomography pulmonary angiography (CTPE) was negative for acute pulmonary embolism but showed scattered bilateral airspace opacities with dependent consolidations (fig 1.). Relevant laboratory on admission included procalcitonin 28.17, WBC count 12.9 and troponin 1.58. SARs-COV-2, serum blood cultures, legionella antigen, streptococci pneumoniae antigen and HIV were negative. Urine toxicology was positive for cannabinoids. Bronchoalveolar lavage later demonstrated 50,000 TNC with neutrophil predominance. EKG showed sinus tachycardia and nonspecific ST depression. Echocardiogram revealed severe diffuse hypokinesis with left ventricular ejection fraction (LVEF) of 13%. During her ICU course she continued on mechanical ventilation with lung protective strategy, systemic glucocorticoids and antibiotics. Vasopressors were subsequently weaned off. Repeated echocardiogram on ICU day five demonstrated a recovered LVEF at 55%. Patient's hypoxemia improved, and she was successfully extubated on ICU day eight. DISCUSSION: Pulmonary injury is the most well described clinical manifestation of EVALI, however a large majority of these patients also present with gastrointestinal symptoms and malaise, suggesting a systemic disease process. Our patient had newly reduced LVEF suggestive of stress induced cardiomyopathy which consequently improved with standard and supportive care. CONCLUSIONS: It is important to maintain a high index of suspicion of secondary organ damage, as prompt diagnosis and treatment of EVALI associated cardiac dysfunction can have an impact in short- and long-term prognosis. REFERENCE #1: Kligerman S, Raptis C, Larsen B, Henry TS, Caporale A, Tazelaar H, Schiebler ML, Wehrli FW, Klein JS, Kanne J. Radiologic, Pathologic, Clinical, and Physiologic Findings of Electronic Cigarette or Vaping Product Use-associated Lung Injury (EVALI): Evolving Knowledge and Remaining Questions. Radiology. 2020 Mar;294(3):491-505. doi: 10.1148/radiol.2020192585. Epub 2020 Jan 28. PMID: 31990264. DISCLOSURES: No relevant relationships by David barounis, source=Web Response No relevant relationships by Xavier Fonseca, source=Web Response No relevant relationships by Dana Mueller, source=Web Response