A DEEP LEARNING APPROACH LUNG SEGMENTATION AND PNEUMONIA DETECTION FROM X-RAYS

Lung segmentation is a process of detection and identification of lung cancer and pneumonia with the help of image processing techniques. Deep learning algorithms can be incorporated to build the computer-aided diagnosis (CAD) system for detecting or recognizing broad objects like acute respiratory distress syndrome (ARDS), Tuberculosis, Pneumonia, Lung cancer, Covid, and several other respiratory diseases. This paper presents pneumonia detection from lung segmentation using deep learning methods on chest radiography. Chest X-ray is the most useful technique among other existing techniques, due to its lesser cost. The main drawback of a chest x-ray is that it cannot detect all problems in the chest. Thus, implementing convolutional neural networks (CNN) to perform lung segmentation and to obtain correct results. The 'lost' regions of the lungs are reconstructed by an automatic segmentation method from raw images of chest X-ray. © 2022 IEEE.

Coverage of Coronavirus Disease-2019 (COVID-19) Booster Dose (Precautionary) in the Adult Population: An Online Survey.

Background The coronavirus disease-2019 (COVID-19) pandemic devastated public health worldwide, including India. COVID-19 vaccines and their boosters are life-saving developments that have helped prevent and control the spread of COVID-19. We conducted this study to assess the coverage of the booster dose in an Indian population (the third dose of the COVID-19 vaccine in India is referred to as the booster or precautionary dose), record the reasons for not taking the booster dose, and determine the effectiveness of the booster. The levels of adherence to COVID-19 precautionary behavior was also assessed.  Methods We conducted a descriptive, cross-sectional study using convenient sampling via an online survey of 550 respondents older than 18 in the second quarter of 2022. The respondents were distributed among 18 states and union territories in India. The data were analyzed as simple proportions and percentages. Results Of the 550 respondents, 152 (27.6%) received the booster dose, indicating low coverage. A small percentage of respondents (7.2%) reported suffering from COVID-19 following the booster, of whom 91% were medical professionals. The most common reported reason for not taking the vaccine was that the respondents were not yet due for their dose (48.1%). The time between the second dose of the COVID-19 vaccine and the booster had no impact on infection rates. Men were less likely to adhere to COVID-19 precautionary behavior than women, despite similar vaccination rates. Conclusion The COVID-19 vaccine booster had a low acceptance in our study population, with roughly one-quarter of the population receiving the booster. The booster dose has been influential in the prevention of COVID-19. Most respondents followed behavioral safety measures despite the decline of active cases of COVID-19 in India following the Omicron wave. Our results indicate a need to strengthen public strategies to affect behavioral changes, such as improving India's Behavior Change Communication program to ensure adequate booster dose coverage.

Covid-19 Detection and Classification using Transfer learning with XGboost

The 2019 new corona virus (COVID-19), with a genesis phase in China, has dispersed apace amid individuals subsisting in distinct nations and is rising toward about twelve lakh cases in the balance as per the intuition of the European center for Health Security and Communicable diseases and ECDC. There is a foreordained figure of COVID-19 trial caskets attainable in medical centers because of the escalating cases in day-to-day life. In this way, it is important to execute a programmed location framework as a snappy elective conclusion alternative to forestall COVID-19 transmitting between peoples. In this examination, three disparate Convolutional neural system- based models (XGBOOST/LIGHTGBM, Inception-ResNetV2 and InceptionV3) have been put forward for the whereabouts of coronavirus and pneumonia contaminated convalescent by harnessing thoracic radiographic screening. Receiver Operating Characteristics (ROC) investigations and disordered networks by those tripartite models are bestowed and deteriorated by exploiting 5-superimpose traverse accredit. Contemplating the demonstration outcome obtained, it is perceived that the pre- prepared XGBOOST/LIGHTGBM model accouters the most upraised characterization execution with 98.6% exactness amongst the other two propounded models (96% correctness for InceptionV3 and 85% exactness for Inception-ResNetV2). © 2023 IEEE.

Clinical Spectrum and Outcome of Neonatal Multi-System Inflammatory Syndrome (MIS-N) - A Prospective Cohort Study. (preprint)

AIMS: To analyze the clinical spectrum in Neonates with MIS-N based on the time of presentation and also to assess the use of immunomodulator therapy in MIS-N. SUBJECTS AND METHODS: We studied 100 neonates, delivered at BLDE (DU) Shri B M Patil Medical College Hospital admitted to Level III-A NICU from JULY 2020 to MAY 2021. 98 neonates had high titers of Ig G antibodies and negative for COVID Antigen. We categorized the cohorts into EARLY MIS-N (<72 hrs) and LATE MIS-N (>72 hrs). RESULTS: 58 presented as EARLY MIS-N with Respiratory Distress in 40 (70%), cardiac dysfunction 34 (60%), PPHN 12(20%), Fever 12(20%), seizures 12(20%), encephalopathy in 6(10%), sepsis-like features 6(10%), had elevated inflammatory markers like CRP (30%), D-Dimer (70%), Ferritin (30%), cardiac biomarkers like BNP (60%), LDH (30%) and ECHO showing LV dysfunction in 50%. LATE MIS-N presented mostly with fever 28(70%), sepsis-like features 24(60%), Respiratory Distress in 16(40%), cardiac dysfunction 12 (30%), hypoglycemia 4(10%) parotitis 4(10%), had significantly elevated inflammatory markers like CRP (70%), D-Dimer (50%), Ferritin (70%), cardiac biomarkers like BNP (40%), LDH (20%) and ECHO showing LV dysfunction in 20%, dilated coronaries in 20 %, PPHN in 10%. Oxygen and respiratory support requirement was more in EARLY presenters and IVIG and steroid requirement was more in LATE presenters. CONCLUSION: We observed that maternal SARS COV2 antibodies transferred transplacentally and neonatal antibodies acquired after COVID 19 infection can cause MIS-N in neonates. The immunomodulator therapy is required in severe cases of MIS-N only.

Coverage of Coronavirus Disease-2019 (COVID-19) Booster Dose (Precautionary) in the Adult Population: An Online Survey

Background The coronavirus disease-2019 (COVID-19) pandemic devastated public health worldwide, including India. COVID-19 vaccines and their boosters are life-saving developments that have helped prevent and control the spread of COVID-19. We conducted this study to assess the coverage of the booster dose in an Indian population (the third dose of the COVID-19 vaccine in India is referred to as the booster or precautionary dose), record the reasons for not taking the booster dose, and determine the effectiveness of the booster. The levels of adherence to COVID-19 precautionary behavior was also assessed.  Methods We conducted a descriptive, cross-sectional study using convenient sampling via an online survey of 550 respondents older than 18 in the second quarter of 2022. The respondents were distributed among 18 states and union territories in India. The data were analyzed as simple proportions and percentages. Results Of the 550 respondents, 152 (27.6%) received the booster dose, indicating low coverage. A small percentage of respondents (7.2%) reported suffering from COVID-19 following the booster, of whom 91% were medical professionals. The most common reported reason for not taking the vaccine was that the respondents were not yet due for their dose (48.1%). The time between the second dose of the COVID-19 vaccine and the booster had no impact on infection rates. Men were less likely to adhere to COVID-19 precautionary behavior than women, despite similar vaccination rates. Conclusion The COVID-19 vaccine booster had a low acceptance in our study population, with roughly one-quarter of the population receiving the booster. The booster dose has been influential in the prevention of COVID-19. Most respondents followed behavioral safety measures despite the decline of active cases of COVID-19 in India following the Omicron wave. Our results indicate a need to strengthen public strategies to affect behavioral changes, such as improving India's Behavior Change Communication program to ensure adequate booster dose coverage.

Impact of the COVID-19 Pandemic on the Short-Term Course of Obsessive-Compulsive Disorder.

ABSTRACT: There is an understandable concern that obsessive-compulsive disorder (OCD) may worsen during the COVID-19 pandemic, but there are little empirical data. We report the impact of COVID-19 pandemic on the short-term course of OCD. A cohort of patients with a primary diagnosis of OCD (n = 240) who were on regular follow-up at a tertiary care specialty OCD clinic in India were assessed telephonically, about 2 months after the declaration of the pandemic ("pandemic" cohort). Data from the medical records of an independent set of patients with OCD (n = 207) who were followed up during the same period, 1 year prior, was used for comparison (historical controls). The pandemic group and historical controls did not differ in the trajectories of the Yale-Brown Obsessive-Compulsive Scale scores (chi-square likelihood ratio test of the group × time interaction = 2.73, p = 0.255) and relapse rate (21% vs. 20%; adjusted odds ratio, 0.81; 95% confidence interval, 0.41-1.59; p = 0.535). Preexisting contamination symptoms and COVID-19-related health anxiety measured by the COVID-Threat Scale did not predict relapse. Only a small proportion of patients (6%) reported COVID-19-themed obsessive-compulsive symptoms. The COVID-19 pandemic, at least in the short run, did not influence the course of illness.

Impact of the COVID-19 Pandemic on the Short-term Course of Obsessive-Compulsive Disorder (preprint)

Background: There is an understandable concern that obsessive-compulsive disorder (OCD) may worsen during the COVID-19 pandemic, but there is little empirical data. We report the impact of COVID-19 pandemic on the short-term course of OCD. We also assessed for predictors of relapse and emergence of COVID-19-themed obsessive-compulsive symptoms. Methods: A cohort of patients with a primary diagnosis of OCD (n=240) who were on regular follow-up at a tertiary care specialty OCD Clinic in India were assessed telephonically, about 2 months after the declaration of the pandemic ('pandemic' cohort). Data from the medical records of an independent set of patients with OCD (n=207) who were followed-up during the same period, one year prior, was used for comparison (historical controls). Results: The 'pandemic' group and historical controls did not differ in the trajectories of the Yale-Brown Obsessive-Compulsive Scale (YBOCS) scores (Chi-square for likelihood-ratio test of the Group x Time interaction = 2.73, p= 0.255) and relapse rate [21% vs 20%, adjusted odds ratio = 0.81 (95% CI 0.41 -1.59, p=0.535]. Pre-existing contamination symptoms and COVID-19-related health anxiety measured by the COVID-Threat Scale did not predict relapse. Only a small proportion of patients (6%) reported COVID-19-themed obsessive-compulsive symptoms. Limitations: Follow-up 2 months after pandemic declaration may be too early understand the true impact. Conclusions: The COVID-19 pandemic, at least in the short-run, did not influence the course of illness in those who were on medications. It would be pertinent to evaluate the long-term impact of the pandemic on the course of OCD.