Bangladesh is in the floodplains of the Ganges, Brahmaputra, and Meghna River delta, crisscrossed by an intricate web of rivers. Although the country is highly prone to flooding, the use of state-of-the-art deep learning models in predicting river water levels to aid flood forecasting is underexplored. Deep learning and attention-based models have shown high potential for accurately forecasting floods over space and time. The present study aims to develop a long short-term memory (LSTM) network and its attention-based architectures to predict flood water levels in the rivers of Bangladesh. The models developed in this study incorporated gauge-based water level data over 7 days for flood prediction at Dhaka and Sylhet stations. This study developed five models: artificial neural network (ANN), LSTM, spatial attention LSTM (SALSTM), temporal attention LSTM (TALSTM), and spatiotemporal attention LSTM (STALSTM). The multiple imputation by chained equations (MICE) method was applied to address missing data in the time series analysis. The results showed that the use of both spatial and temporal attention together increases the predictive performance of the LSTM model, which outperforms other attention-based LSTM models. The STALSTM-based flood forecasting system, developed in this study, could inform flood management plans to accurately predict floods in Bangladesh and elsewhere.

No abstract

Introduction: COVID-19 has infected people all over the world. By the end of November 2020, it was confirmed that about 67M people were suffering from COVID-19 and almost 1.7 million people had died due to it. The symptoms of COVID-19 had a wide range from mild upper respiratory indications to severe acute respiratory distress syndrome. Certain factors of COVID-19 include old age, males, hypertension, and diabetes. Aim: To detect and predict those patients who would develop lung fibrosis after Covid-19 infection as early introduction of anti-fibrotic drugs can be started. Methodology: Overall, 85 individuals were involved in this study. Patients who were having COVID-19, confirmed by PCR, were examined by follow-up MDCT. CT scan was performed and similar research was involved with some follow-up data that include residual fibrotic changes and different radiological signs. Some risk factors were predicted that were said to be the source of lung fibrosis after COVID-19. These factors include cigarette smoking, old age, CT severity score being high and mechanical ventilation in the long term. Results: The analysis of 85 patients, from which males were 43 and females were 42. Their age varied from 24 to 76 years old. A total of 30 (37.5%) individuals had a history of cigarette smoking of more than 25 cigarettes per day for more than ten years. People in the age group 60 to 76 years old had the highest commonness of getting post-COVID-19 pulmonary fibrosis. About 15 out of thirty-two patients, which is 46.2 percent, had pulmonary fibrosis. Patients of the age group 45 to 60 years had mild prevalence which is 7 out of 27 patients (25.9 percent). Conclusion: If post-COVID-19 pulmonary fibrosis is detected early in individuals, there may be some changes to prevent such long-term complications.

Aim: To assess the role of computed tomography for management of Covid-19. Study design: Prospective study Place and duration of study: Department of Radiology, Ghulam Muhammad Mahar Medical College Teaching Hospital Sukkur from 1st November 2020 to 31st December 2021. Methodology: One hundred cases within various ages 5-55 years for analyzing their risk for CT scanning on them by highlighting the facts related to CT scan, patient perceptions and uncertainties regarding it. A 50 radiologist and 50 emergency doctors were also asked questions regarding their knowledge about CT scan risks and their responses were also documented. However previous CT record of patients suffering from carcinoma was also analyzed for understanding the fact related with CT imaging. Results: The mean age of patients undergoing CT scan was 39.5±5.6 years. There were 55% males who underwent CT scans while 45% females. The usual dosage for various radiological procedure shows that highest dose deliverance was given to the patients of CT pulmonary angiogram and coronary angiography. Only 50% of radiologists knew that CT scan is associated with high risk of malignancies. There were only 10% emergency medical doctors who also knew CT imaging relation with malignancy risk. Only 54% patients considered abdomen pelvic scan to be associated with increasing lifetime risk of cancer while 23% of the patients considered chest scan to be associated with escalating the risk of cancer. Conclusion: Computed tomography scan is related with a high risk of radiation exposure. There is a dire need of perception development and risk understanding with medical professionals and general public for minimizing this risk. Key words: Computed tomography, Risk, Facts, Perception, Uncertainties

Aim: To assess the role of chest computed tomography for management of Covid-19. Study design: Prospective study Place and duration of study: Department of Radiology, Peoples University of Medical & Health Sciences for Women, Nawabshah, Shaheed Benazirabad from 1st August 2020 to 30th September 2021. Methodology: Two hundred patients were enrolled within the age range of 18-70 years. The clinical/medical record of all those patients who were moderately to critically ill assessed in detail. These patients visited the hospital with symptoms of cough, fever, hypoxia, dyspnea, diarrhoea, flu, headache and other related symptoms. All patients underwent chest reverse transcription polymerase chain reaction as well as chest computed tomography scan. The reverse transcription polymerase chain reaction was performed through nasopharyngeal swab. Results: The mean age of the patients was 64.5±5.6 years with 120 (60%) males and 80 (40%) females. The specificity was 75%, sensitivity 100%, positive predictive value 79%, negative predictive value 66.67% and diagnostic accuracy 75%. Conclusion: Computed tomography scan imaging is a most reliable with high sensitivity and non-predictive value Key words: Role, Computed tomography imaging, Management, Covid-19