ABSTRACT
Aim and objective: During the recent COVID-19 pandemic various vaccines have been developed and approved for emergency use, including adenovirus vector-based ChAdOx1 nCov-19. There are few reports of serious adverse events following immunization (AEFI). Materials and methods: Here, we report two cases of serious AEFI who required ICU admission. Results: Case 1: A 55-y-m hospitalized with complaints of giddiness for 4 days and onset of weakness of all four limbs with altered sensorium for 1 day. He had no history of any comorbidity, non-smoker and non-alcoholic, and no previous episodes of transient ischemic attacks. He was vaccinated with a second dose of adenoviral vector-based ChAdOx1 nCov-19 vaccine (8 days before the onset of first symptoms). After hospitalization, immediate intubation was done for airway protection. His neurological examination revealed blinking of eyes spontaneously, motor power of 0/5 in all four limbs, deep tendon reflex of +2, and mute plantar. MRI Brain was done on the next day (day of illness, DOI-4), which revealed acute infarct in the pons and bilateral cerebellar hemisphere. He was referred to our ICU on DOI-12. Repeat MRI Brain on DOI-16 showed subacute infarcts in the pons, bilateral middle cerebellar peduncles, and left cerebral hemisphere with thrombosed basilar artery. Lipid profile, homocysteine levels, auto-immune work-up were normal. Echocardiography showed normal LV function with no evidence of LA clot. Carotid Doppler showed normal carotid vessels. In view of ischemic stroke and basilar artery thrombosis anti-platelet agent and therapeutic anticoagulation continued. Over the next 3 weeks, he showed gradual improvement in motor power (3/5 in upper limbs and 2/5 in lower limbs) and weaned off from mechanical ventilation. Case 2: A 19-y-m hospitalized with complaints of acute onset paraesthesia and progressive weakness in both lower limbs for 4 days and difficulty in speech and swallowing for 1 day. He had no history of any comorbidity, and no history of preceding viral/bacterial infection except that he had received the first dose of the adenoviral vector-based ChAdOx1 nCov-19 vaccine (16 days before the onset of first symptoms). After hospitalization, he required intubation in view of pooling of oral secretions and respiratory distress. Clinical examination revealed bifacial weakness, severe neck muscle weakness, and flaccid areflexic quadriparesis with prominent proximal upper and lower limb weakness. Pin-prick sensation was distally reduced in both lower limbs with associated autonomic instability in the form of tachycardia and hypertension. MRI Brain was normal in the study. In further work, Guillain-Barré syndrome (GBS) was diagnosed. CSF showed albumin-cytologic dissociation (protein 1.14 g/L and nil cell), and bilateral motor nerve axonal neuropathy on nerve conduction study. Immunoglobulin (IVIG) therapy was started on DOI-6. He did not show significant improvement and was referred to our ICU for further management. During the 5th week of illness, the IVIG dose was repeated without any improvement and continuing requirement of mechanical ventilation. Conclusion: Though vaccination is one of the important public health interventions implemented to tackle the COVID-19 pandemic, there are known and unknown serious AEFI being reported. Both cases presented quadriparesis with different diagnoses, who received vaccination for COVID-19.
ABSTRACT
The Covid-19 pandemic has spread quickly, making identification of the virus critically important in assisting overburdened healthcare systems. Numerous techniques have been used to identify Covid-19, of which the Polymerase chain reaction (PCR) test is the most common. However, obtaining results from the PCR test can take up to two days. An alternative is to use X-ray images of the subject's chest area as inputs to a deep learning neural networks algorithm. The two problems with this approach are the choice of architecture and the method used to deal with the imbalanced data. In this study a comparative analysis of a standard convolutional neural network (CNN) and a number of transfer learning algorithms with a range of imbalanced data techniques was conducted to detect Covid-19 from a data set of chest x-ray images. This data set was an amalgamation of two data sets extracted from the Kaggle Covid-19 open source data repository and non-Covid illnesses taken from the National Institute of Health. The resulting data set was had over 115k records and 15 different type of findings ranging from no-illness to illnesses such as Covid-19, emphysema and lung cancer. This study addresses the problem of class imbalance on the largest data set used for x-ray detection of Covid-19 by combining undersampling and oversampling methods. The results showed that a CNN model in conjunction with these random over and under sampling methods outperformed all other candidates when identifying Covid-19 with a F1-score of 93%, a precision of 90% and a recall of 91%. © 2021 CEUR-WS. All rights reserved.