ABSTRACT
Today, the whole world is fighting the war against Coronavirus. The spread of the virus has been observed in almost all the parts of the world. Covid-19 also known as SARS-Cov-2 was initially observed in China which rapidly multiplied all over the world. The disease is said to spread by cough, normal cold, sneezing or when a person is in close contact with someone who is already infected. Therefore, the spread of the virus can occur when there is direct contact with an infected person or with the objects touched by the infected person. Hence, it is important to detect the contiguous spread of the virus and control it by taking appropriate measures. Several deep learning models have been used in detecting many diseases like Malaria disease, Lung infection, Parkinson's disease etc. Likewise, CNN model along with other transfer techniques is best proven to detect whether a person is infected with covid positive or not. The dataset consists of 1000 images of covid positive and normal x-rays. The proposed model has been trained and tested on the image dataset with the help of transfer learning models in order to improve the performance of the model. The models VGG-16, ResNet-50, Inception v3 and Xception have achieved an overall accuracy of 93%,82%,96% and 92% respectively. The performance of all the 4 architectures are analyzed, understood and hence presented in this paper. It is hence important to classify and detect covid positive infection and contribute towards making the world Covid-free. © 2023 Author(s).
ABSTRACT
SESSION TITLE: Unique Uses of Pulmonary Function Tests SESSION TYPE: Rapid Fire Original Inv PRESENTED ON: 10/19/2022 11:15 am - 12:15 pm PURPOSE: Coronavirus disease 2019 (COVID-19) is a highly transmissible respiratory disease that causes global pandemic. It is known to cause impairment of lung function leading to morbidity and mortality. Long term data for lung function tests in these populations is still limited. METHODS: A retrospective chart review of patients with COVID-19 pneumonia who had initial and follow up spirometry tests from August 2020 to December 2021 in a pulmonary clinic in Corpus Christi, Texas was performed. Baseline characteristic and spirometry parameters including age, gender, race, body mass index, comorbidities, pre/post bronchodilator FEV1, FVC, lung volume, DLCO and 6-minute walk test were collected. T test analysis was performed to compare the data between initial and follow up pulmonary function tests. RESULTS: A total of 29 patients were enrolled.The mean COVID diagnosis to PFT interval was 126 days. Mean follow up duration was 309 days. Mean (SD) age was 58 (10) years. Forty-eight percent of the participants were male gender. Majority of our participants were hispanic (72%) followed by caucasian (21%) and others (7%). Average BMI (SD) was 34.6 (7.5) kg/m². Restrictive lung defect pattern was found in 55.2% on initial pulmonary function test in the clinic which dropped to 41.4% in the follow up test with supportive management. Initial and follow up prebronchodilator percent predicted mean(SD) of FVC were 65 (20) and 72 (20) respectively with a mean difference of 6.3 (p=0.002, 95% CI 2.54-10.10). Initial and follow up prebronchodilator percent predicted mean(SD) of FEV1 were 71 (23) and 78 (21) respectively with a mean difference of 6.7 (p=0.003, 95% CI 2.46-10.90). Moreover, mean(SD) of DLCO and TLC showed significant improvement during follow-up visit [DLCO-69 (24) and 77 (20), mean difference of 7.6 (p=0.016, 95% CI 1.58-13.59), TLC-64 (17) and 71 (14) respectively, mean difference of 7(p=0.005, 95%CI 2.32-11.76)]. CONCLUSIONS: We found improvement of many parameters of pulmonary function test in post COVID-19 patients during follow-up with supportive care. CLINICAL IMPLICATIONS: Regular follow up can be a useful tool to understand the prognosis of post COVID-19 pneumonia sequelae. DISCLOSURES: No relevant relationships by Asad Chohan No relevant relationships by Saiara Choudhury No relevant relationships by Pahnwat Taweesedt No relevant relationships by Abhay Vakil
ABSTRACT
SESSION TITLE: COVID-19 Case Report Posters 1 SESSION TYPE: Case Report Posters PRESENTED ON: 10/17/2022 12:15 pm - 01:15 pm INTRODUCTION: COVID-19 infection with concurrent myasthenia gravis (MG) presents a unique diagnostic challenge for the clinician. We report the case of a patient presenting with respiratory failure secondary to COVID-19 Pneumonia and being diagnosed with MG. CASE PRESENTATION: Patient is a 72-year-old male without any significant medical history presented with progressively worsening shortness of breath, associated dysphagia and fatigue for 1-week duration. Laboratory data and imaging findings were suggestive of COVID-19 pneumonia. Patient's respiratory status deteriorated requiring mechanical ventilation. His oxygenation improved with steroid and anti-viral therapy. However, he was unable to be liberated from the ventilator secondary to neuromuscular weakness. Further work up confirmed MG. Patient was treated with high-dose steroids, pyridostigmine and intravenous immunoglobulin therapy. Patient was unable to be extubated and required a tracheostomy placement. DISCUSSION: Observational studies have suggested the rate of MG exacerbation to be 10-15% in COVID-19 infection. Mortality was found to be significantly higher in these patients compared to patients without MG. Several case reports have also shown exacerbation of previously asymptomatic MG with COVID-19 infection. Studies have indicated underlying MG to be an independent prognostic risk factor in COVID-19 infection. Treatment involves achieving symptomatic improvement with use of pyridostigmine, corticosteroids and long-term steroid sparing agents, in addition to administering usual treatment for COVID-19 infection. CONCLUSIONS: Our patient presents as a case of COVID 19 infection complicated with a possibly induced or previously undiagnosed case of MG complicating the clinical course. During evaluation of patients with respiratory failure secondary to COVID-19 infection, history focused on symptoms that may indicate underlying neuromuscular diseases should be obtained for early diagnosis and proper management. Given the high co-existence, it is important for clinicians to be aware of the association and treatment strategies in such patients. Reference #1: Galassi G, Marchioni A. Myasthenia gravis at the crossroad of COVID-19: focus on immunological and respiratory interplay. Acta Neurol Belg. 2021;121(3):633-642. doi:10.1007/s13760-021-01612-6 Reference #2: Sriwastava S, Tandon M, Kataria S, Daimee M, Sultan S. New onset of ocular myasthenia gravis in a patient with COVID-19: a novel case report and literature review. J Neurol. 2021;268(8):2690-2696. doi:10.1007/s00415-020-10263-1 Reference #3: Rodrigues CL, de Freitas HC, Lima PRO, et al. Myasthenia gravis exacerbation and myasthenic crisis associated with COVID-19: case series and literature review. Neurol Sci. 2022;43(4):2271-2276. doi:10.1007/s10072-021-05823-w DISCLOSURES: No relevant relationships by Asad Chohan No relevant relationships by Saiara Choudhury No relevant relationships by Rahul Dadhwal No relevant relationships by Rene Franco No relevant relationships by Ahsan Syed No relevant relationships by Pahnwat Taweesedt No relevant relationships by Abhay Vakil