ULD-NUIG at Social Media Mining for Health Applications (#SMM4H) Shared Task 2021

In this paper, we present the ULD-NUIG team's system, designed as part of Social Media Mining for Health Applications (#SMM4H) Shared Task 2021. We participate in two tasks out of eight, namely "Classification of tweets self-reporting potential cases of COVID-19" (Task 5) and "Classification of COVID19 tweets containing symptoms" (Task 6). The team conduct a series of experiments to explore the challenges of both the tasks. We used a multilingual pre-trained BERT model for Task 5 and Generative Morphemes with Attention (GenMA) model for Task 6. In the experiments, we find that, GenMA, developed for Task 6, gives better results on both validation and test data-set. The submitted systems achieve F-1 score 0.53 for Task 5 and 0.84 for Task 6 on test data-set. © 2021 Association for Computational Linguistics.

Vision Transformer for Plant Disease Detection: PlantViT

With the COVID-19 pandemic outbreak, most countries have limited their grain exports, which has resulted in acute food shortages and price escalation in many countries. An increase in agriculture production is important to control price escalation and reduce the number of people suffering from acute hunger. But crop loss due to pests and plant diseases has also been rising worldwide, inspite of various smart agriculture solutions to control the damage. Out of several approaches, computer vision-based food security systems have shown promising performance, and some pilot projects have also been successfully implemented to issue advisories to farmers based on image-based farm condition monitoring. Several image processing, machine learning, and deep learning techniques have been proposed by researchers for automatic disease detection and identification. Although recent deep learning solutions are quite promising, most of them are either inspired by ILSVRC architectures with high memory and computational requirements, or light convolutional neural network (CNN) based models that have a limited degree of generalization. Thus, building a lightweight and compact CNN based model is a challenging task. In this paper, a transformer-based automatic disease detection model “PlantViT" has been proposed, which is a hybrid model of a CNN and a Vision Transformer. The aim is to identify plant diseases from images of leaves by developing a Vision Transformer-based deep learning technique. The model takes the capabilities of CNNs and the Vision Transformer. The Vision Transformer is based on a multi-head attention module. The experiment has been evaluated on two large-scale open-source plant disease detection datasets: PlantVillage and Embrapa. Experimental results show that the proposed model can achieve 98.61% and 87.87% accuracy on the PlantVillage and Embrapa datasets, respectively. The PlantViT can obtain significant improvement over the current state-of-the-art methods in plant disease detection. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A RARE PRESENTATION OF THORACIC AORTIC ANEURYSM RUPTURE

TOPIC: Signs and Symptoms of Chest Diseases TYPE: Medical Student/Resident Case Reports INTRODUCTION: Thoracic aortic aneurysm (TAA) is an uncommon clinical condition, commonly associated with atherosclerosis. It is mostly asymptomatic but aneurysm exceeding 6 cm are at risk of yearly rate of rupture or dissection of at least 6.9% and a death rate of 11.8%. We present to you a case of TAA with rupture presenting with cough, hemoptysis and pneumonitis. CASE PRESENTATION: Patient is a 68 years male who presented to the ED with cough, hemoptysis, chest discomfort for 2-3 days. He had intermittent episodes of fever. COVID test was negative 3 days ago. Past medical history was significant for HTN, Asthma, COPD, Diabetes mellitus, tobacco use disorder. Patient was afebrile with BP of 137/73, HR 72, RR 16, O2 saturation of 89% in room air. Physical examination including chest was unremarkable. Initial workup including CBC was remarkable for WBC of 12500, Hgb of 10.5, INR 0.8, PTT 24, Troponin <0.02. CXR showed findings worrisome for underlying pneumonitis in the left upper lobe. Presumptive diagnosis of community-acquired pneumonia was made, patient was treated with ceftriaxone and azithromycin but symptoms continued to persist despite the treatment. For further evaluation, CT CTA chest was performed which revealed features suggestive of ruptured thoracic aortic aneurysm. Further, angiogram revealed rupture above the level of the celiac artery. Patient then underwent endovascular thoracic stent graft placement. Patient could not be extubated following the procedure due to advanced COPD and was then transferred to ICU for close monitoring. He was subsequently extubated in the next few days and was discharged in stable condition. No complications were noted in follow-up CT angiography. DISCUSSION: Thoracic aortic aneurysm (TAA) is commonly associated with atherosclerosis but can also occur in genetic disease (Marfan syndrome, Ehler Danlos syndrome, Loeys-Dietzs syndrome, familial thoracic aortic aneurysm syndrome, aneurysms osteoarthritis syndrome), patient with bicuspid aortic valve, infection (tuberculosis, syphilis, mycotic infections), giant cell arteritis, cystic medial necrosis, trauma, familial TAA. It is present in 5.6/100,000 people. Hemoptysis is a unique symptom of TAA rupture that has been a reported due to erosion of the trachea by aneurysm or rupture of the aneurysm into lung parenchyma. Rupture risk is high in population with aneurysm size > 5 cm, smokers, COPD, advanced age, hypertension. Thoracic endovascular stent graft surgery, under epidural anesthesia, is the preferred surgical treatment especially in old TAA patients as in our case because of low morbidity, mortality and hospital stay. CONCLUSIONS: Rupture of TAAs is still very rare, but should remain on the differential for a patient with cough, hemoptysis with features of pneumonitis as it is associated with very high morbidity and mortality rates. REFERENCE #1: CL F, Esk, MK ari. Thoracic endovascular aneurysm Repair (TEVAR) for Ruptured THORACIC aortic aneurysms. Published May 2, 2017 REFERENCE #2: Inam, H., Zahid, I., Khan, S.D. et al. Hemoptysis secondary to rupture of infected aortic aneurysm– a case report. J Cardiothorac Surg 14, 144 (2019). https://doi.org/10.1186/s13019-019-0959-y REFERENCE #3: Sun D, Mehta S. Hemoptysis caused by erosion of thoracic aortic aneurysm. CMAJ. 2010;182(4):E186. doi:10.1503/cmaj.090447 DISCLOSURES: No relevant relationships by Luna Khanal, source=Web Response No relevant relationships by Adarsha Ojha, source=Web Response

SINUS PAUSE SECONDARY TO ACUTE COVID-19 INFECTION

TOPIC: Cardiovascular Disease TYPE: Medical Student/Resident Case Reports INTRODUCTION: Sinus pause/arrest most commonly occurs in medication toxicity, cardiac ischemia, infiltrative or fibrotic disease of SA node, structural heart disease, PE, sleep apnea, electrolyte disturbance (hyperkalemia), Lyme disease. We present to you a case of sinus pause/arrest in a patient with COVID-19 infection. CASE PRESENTATION: Patient is a 59 year male who presented to hospital with complaints of chest pain and dyspnea. Past medical history was significant for recent COVID-19 infection one week ago. Vital signs and physical examination on presentation were normal. Initial workup including CBC, INR, PTT, CMP, troponin and EKG were normal. Chest x-ray was remarkable for reticular nodular infiltrate in the right perihilar lung field. Patient was started on IV antibiotic for suspected pneumonia. On day 1, patient started experiencing skipped heartbeats. Cardiac telemetry demonstrated multiple sinus pauses with greatest pause duration of about 5 seconds. EKG showed normal sinus rhythm without any significant ST/T wave changes, Recent transthoracic echocardiogram was normal. Upon literature review, it was noted that there were cases of severe COVID-19 infection affecting the electrical system of the heart, resulting in sinus pauses. Hence, after ruling out some of the common differential diagnosis for sinus pauses including medications, ischemia, inflammatory, infiltrative or fibrotic disease of the SA node, structural heart disease, PE, OSA (obstructive sleep apnea), electrolyte disturbance (especially hyperkalemia), Lyme disease, patient's sinus pauses were attributed to underlying COVID-19 infection. Patient was discharged with 30 days cardiac event monitor which showed sinus rhythm with no significant pauses. DISCUSSION: SA nodal dysfunction typically results from either abnormality in impulse generation by the P cells or abnormalities in conduction across perinodal transitional (T cells). Hypoxemia, cytokine storm, direct viral infiltration, myocardial inflammation are thought to be responsible for sinus pause in COVID-19 disease, although exact mechanism is not known. Patients are symptomatic when longer episodes of sinus arrest occur resulting in dizziness, syncope, and death. Asymptomatic patients with SA nodal pauses or arrest often do not require treatment. Symptomatic patients are treated with a permanent pacemaker placement. CONCLUSIONS: Moderate to severe COVID-19 infection could be an uncommon cause of sinus pauses. However, before attributing COVID-19 as a cause of sinus pauses, common differential diagnosis for sinus pauses including medications toxicity (digoxin, antiarrhythmics-procainamide, quinidine), cardiac ischemia, infiltrative or fibrotic disease of SA node, structural heart disease, PE, sleep apnea, electrolyte disturbance and Lyme disease should be ruled out. REFERENCE #1: Peigh, Graham, et al. 'Novel Coronavirus 19 (COVID-19) Associated Sinus Node Dysfunction: A Case Series'. European Heart Journal - Case Reports, vol. 4, no. FI1, Oct. 2020, pp. 1–6. Silverchair, doi:10.1093/ehjcr/ytaa132. REFERENCE #2: Clerkin KJ, Fried JA, Raikhelkar J, Sayer G, Griffin JM, Masoumi A, Jain SS, Burkhoff D, Kumaraiah D, Rabbani L, Schwartz A, Uriel N. Coronavirus disease 2019 (COVID-19) and cardiovascular disease. Circulation 2020;doi: 10.1161/CIRCULATIONAHA.120.046941 REFERENCE #3: Zheng YY, Ma YT, Zhang JY, Xie X. COVID-19 and the cardiovascular system. Nat Rev Cardiol 2020;17:259–260. DISCLOSURES: No relevant relationships by Luna Khanal, source=Web Response No relevant relationships by Adarsha Ojha, source=Web Response

COVID-19 monitoring application for better human life

COVID-19 –a panic –a threat to human has changed the total world’s normal flow of life. In this disease patient having mild cough and cold but if not identified at early stage and properly treated the patient would be died. So early state diagnosis is very crucial in this virus infection. In this paper a monitoring system model has been proposed with automated instant messaging, alarm generating and call facility. As we know COVID-19 patient has certain kind of symptoms like- high temperature, cold cough, loss of sense of smell, low oxygen saturation level along with that presence of diabetes, renal infection, pneumonia, hypertension, cardiovascular disease and obesity will influence the risk more. The application will measure oxygen saturation level, blood pressure and taking input for symptoms related questions and identifying the risk will either provide suggestions to patients and if oxygen saturation level is less then will send automated message to local COVID control units, police station and hospitals for arrangement of beds so the process for migrating the patient would be easy. © 2021 Institute of Physics Publishing. All rights reserved.