Deep learning-based COVID-19 triage tool: An observational study on an X-ray dataset

Background: Easy availability, low cost, and low radiation exposure make chest radiography an ideal modality for coronavirus disease 2019 (COVID-19) detection. Objective(s): In this study, we propose the use of an artificial intelligence (AI) algorithm to automatically detect abnormalities associated with COVID-19 on chest radiographs. We aimed to evaluate the performance of the algorithm against the interpretation of radiologists to assess its utility as a COVID-19 triage tool. Material(s) and Method(s): The study was conducted in collaboration with Kaushalya Medical Trust Foundation Hospital, Thane, Maharashtra, between July and August 2020. We used a collection of public and private datasets to train our AI models. Specificity and sensitivity measures were used to assess the performance of the AI algorithm by comparing AI and radiology predictions using the result of the reverse transcriptase-polymerase chain reaction as reference. We also compared the existing open-source AI algorithms with our method using our private dataset to ascertain the reliability of our algorithm. Result(s): We evaluated 611 scans for semantic and non-semantic features. Our algorithm showed a sensitivity of 77.7% and a specificity of 75.4%. Our AI algorithm performed better than the radiologists who showed a sensitivity of 75.9% and specificity of 75.4%. The open-source model on the same dataset showed a large disparity in performance measures with a specificity of 46.5% and sensitivity of 91.8%, thus confirming the reliability of our approach. Conclusion(s): Our AI algorithm can aid radiologists in confirming the findings of COVID-19 pneumonia on chest radiography and identifying additional abnormalities and can be used as an assistive and complementary first-line COVID-19 triage tool.Copyright © Cancer Research, Statistics, and Treatment.

Assessment of methemoglobin, hemoglobin, ferritin and lactate dehydrogenase in COVID-19 patients

Today world is trying to cope with the biggest pandemic caused by Coronavirus disease 2019 (COVID-19). The disease is graded as mild, moderate, serious and critical illness. Very few studies are done with methemoglobin along with other parameters for the assessment of the severity of COVID-19 disease. The objectives of the study were to estimate methemoglobin (Met-Hb), hemoglobin (Hb), ferritin and lactate dehydrogenase (LDH) levels in patients with COVID-19 disease and to investigate the interaction between these parameters and the severity of the disease. This observational study was conducted in three groups of COVID-19 patients- moderate, severe and critical, each group containing 30 patients, between June 2021 and September 2021 in the biochemistry department of a tertiary care hospital. For all patients, Met-Hb, Hb, ferritin, and LDH levels were estimated on the 2nd-3rd day of hospital admission. Patients in the critical group were older and had significantly high values of Met-Hb, ferritin and LDH and significantly low values of Hb (P<0.05). In multivariate ordinal regression analysis, older age (OR-3.08;95%CI:1.19-7.19;P-0.019), higher values of LDH (OR-8.66;95%CI:2.53-29.5;P-0.001) and ferritin (OR-3.08;95%CI:1.09-8.7;P-0.033) were independently associated with severity of the disease. A cut-off value of 410.50 U/L for LDH predicted the severity of the disease with 90% sensitivity and 88.3% specificity. In conclusion, higher levels of LDH and ferritin were related to the severity of the disease in COVID-19 cases. Although Met-Hb showed a minimal increase without any association with severity, it may be an underlying cause of hypoxia that may go unnoticed. So, monitoring of all these parameters should be done at intervals.

Indian Pharmaceutical Industry's Supply Chain Challenges: An Overview

The pharmaceutical supply chain is very crucial for the overall industry. A crucial role is played by the Indian Pharmaceuticals industry when we consider the global pharmaceuticals industry. Indian pharmaceutical industry fulfils a large portion of the global pharmaceutical demand. After Covid-19 pandemic, many retail outlets have mushroomed everywhere in India though it is good for the business development, it puts a lot of pressure on the existing infrastructure of the supply chain. The level of responsiveness of the supply chain determines how quickly it can satisfy consumer demand. The pharmaceutical industry is ensuring good service levels as it operates at a 95 percent service level. This research paper identifies challenges in pharmaceutical supply chain. Researcher also narrowed down these challenges into two as Supply chain responsiveness and Service level. Here researcher suggested that to enhance Supply chain responsiveness and Service level, pharmaceutical industry should apply new techniques such as AI & ML. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

The impact of pandemic of COVID-19 on routine immunization: A cross-sectional study in tertiary care centre at Pune

Background: Due to COVID-19 pandemic there was implementation of preventive measures like lockdown, mobility restriction and fear had an impact on routine immunization of children. There are significantly increases the susceptibility window for vaccine preventable diseases due to delayed vaccination in under five children. The objective of study is to know the trend of routine immunization of previous five year and to assess the impact of COVID-19 pandemic on routine immunization of children of age group up to 7 years at tertiary care hospital at Pune. Method(s): A hospital-based cross-sectional study was conducted in a tertiary care hospital of Pune city from the month of January 2017 to December 2021. All the data of immunization from age group 0 to 7 years present at tertiary care center Pune, was compared and analysed. Data is expressed as numbers and percentages and means. Chi-square test was used to compare observed results with expected results. Result(s): In year 2020, there was a declining trend of all vaccines among children compared to previous 3 years. In year 2019, 2020, 2021, number of children vaccinated are 6547, 4052, and 5062 respectively. Out of this 1078(16%), 1089(26.9%), 1165(23%) children had delayed vaccination in year 2019, 2020, 2021 respectively. There was highly significant increase in delayed vaccination of children in COVID-19 period. Conclusion(s): The routine immunization of children was decreased and delayed due to COVID-19 pandemic. This is an alarming finding to prevent reappearance of new epidemics of vaccine preventable diseases.Actions should be taken to avoid delayed routine immunization in future. Copyright © 2022 Ubiquity Press. All rights reserved.

Title-Perspective of methemoglobin, hemoglobin, lactate dehydrogenase and C reactive protein levels in covid-19 patients with diabetes mellitus

Objectives: Dynamics of COVID-19 disease are changing with the emergence of the new variant of the COVID virus. Still, the severity of this disease is associated with comorbid conditions like diabetes mellitus (DM), hypertension, etc. and several biomarkers are studied. The objectives of the study were to estimate methemoglobin (Met-Hb), hemoglobin(Hb), lactate dehydrogenase (LDH) and C reactive protein(CRP) levels in COVID-19 patients with DM and without DM and then to compare between two groups. Materials and methods: This observational study was conducted in 40 COVID-19 patients with DM and 40 COVID-19 patients without DM from June 2021 to October 2021 in the biochemistry department of a tertiary care hospital. For all patients, estimation of Met-Hb, Hb, LDH and CRP levels were estimated on the 2nd-3rd day of hospital admission. Results: Met-Hb, LDH and CRP levels were significantly high and Hb levels were significantly low in elderly COVID-19 patients with DM than in those without DM (P<0.05). There was a significant positive correlation between Met-Hb with LDH and Met-Hb with CRP in both groups and a significant negative correlation was found between Met-Hb with Hb in the diabetic group. Conclusion: In elderly patients, diabetes is one of the important and independent risk factors for the severity of COVID-19 disease. Derangement of Met-Hb along with LDH and CRP shows the need for routine monitoring of Met-Hb. This may open new options in the treatment of COVID-19 disease with DM and improve outcomes in the future.

Association between Chronic Obstructive Pulmonary Disease and Severity of COVID-19 in a Tertiary Care Centre of Pune City, Maharashtra

Background: COVID-19 is a global pandemic caused by SARS-CoV2, spreading across every continent in world. The risk of developing severe COVID-19 with underlying disorder like COPD might be higher as compared to patients with no comorbidity. This study was undertaken to assess the association between COPD and severity of COVID-19. Material & Methods: This was a hospital-based cohort study conducted between July to December, 2020. Study subjects were confirmed COVID-19 patients admitted to this tertiary care centre and all patients were followed up to final outcome as discharge or death. Depending upon the history of COPD total 113 COVID-19 patients with COPD (exposed) and 339 COVID-19 patients without history of COPD (unexposed) were included in analysis. Statistical analysis was done using logistic regression analysis, and adjusted odd’s ratio with 95% CI were calculated. Results: Age >60 years (OR = 1.38, 95% CI 1.12–3.30) and breathlessness (OR = 2.42, 95% CI 1.21–4.85) were independent risk factors for mortality in COVID-19 patients. In addition to this, other co-morbidities were associated with mechanical ventilation. On multivariable analyses, COPD was not significantly associated with mortality in COVID-19 (OR 0.93;95% CI 0.15–1.58). Conclusion: Underlying COPD was not an independent risk factor for poor outcome in COVID-19 patients. Copyright (c) 2022: Author(s).

Novel artificial intelligence algorithm for automatic detection of COVID-19 abnormalities in computed tomography images

Background: Chest computed tomography (CT) is a readily available diagnostic test that can aid in the detection and assessment of the severity of the coronavirus disease 2019 (COVID-19). Given the wide community spread of the disease, it can be difficult for radiologists to differentiate between COVID-19 and non-COVID-19 pneumonia, especially in the oncological setting. Objective: This study was aimed at developing an artificial intelligence (AI) algorithm that could automatically detect COVID-19-related abnormalities from chest CT images and could serve as a diagnostic tool for COVID-19. In addition, we assessed the performance and accuracy of the algorithm in differentiating COVID-19 from non-COVID-19 lung parenchyma pathologies. Materials and Methods: A total of 1581 chest CT images of individuals affected with COVID-19, individuals affected with non-COVID-19 pathologies, and healthy individuals were included in this study. All the digital images of COVID-19-positive cases were obtained from web databases available in the public domain. About 60% of the data were used for training and validation of the algorithm, and the remaining 40% were used as a test set. A single-stage deep learning architecture based on the RetinaNet framework was used as the AI model for image classification. The performance of the algorithm was evaluated using various publicly available datasets comprising patients with COVID-19, patients with pneumonia, other lung diseases (underlying malignancies), and healthy individuals without any abnormalities. The specificity, sensitivity, and area under the receiver operating characteristic curve (AUC) were measured to estimate the effectiveness of our method. Results: The semantic and non-semantic features of the algorithm were analyzed. For the COVID-19 classification network, the sensitivity, specificity, accuracy, and AUC were 0.92 (95% confidence interval [CI]: 0.85-0.97), 0.995 (95% CI: 0.984-1.0), 0.972 (95% CI: 0.952-0.988), and 0.97 (95% CI: 0.945-0.986), respectively. For the non-COVID classification network, the sensitivity, specificity, and accuracy were 0.931 (95% CI: 0.88-0.975), 0.94 (95% CI: 0.90-0.974), and 0.935 (95% CI: 0.90, 0.965), respectively. Conclusion: The AI algorithm developed in our study can detect COVID-19 abnormalities from CT images with high sensitivity and specificity. Our AI algorithm can be used for the early detection and timely management of patients with COVID-19. © 2021 Cancer Research, Statistics, and Treatment ;Published by Wolters Kluwer - Medknow.

Interactive Teaching in Higher Education for Effective Knowledge Dissemination and Improved Student Participation

The present generation of students has information at their hands with the advances in technology. The conventional teaching in monologue manner, just delivering bookish information and dictation are ineffective to inculcate knowledge and confidence in them. Attendance is another major challenge for the current educational system. Assessment patterns have improved from 'marking' to 'continuous grading' systems. However, the questions in examinations merely evaluate the memorizing and writing skills of the students. There is limited scope for students to think in a scientific and logical manner. In addition, there is a need for teaching-learning beyond the classrooms in emergencies like the prevailing pandemic of Coronavirus Disease / COVID-19. The adoption of Information and Communication Technology (ICT) tools will not suffice all these requirements. Interactive teaching-learning would help to convert bookish information into life-long knowledge. Case-based problem-solving questions would create the need for thinking. The blending of skills and knowledge will inculcate value and confidence in students along with their university degrees. A pre-study perception survey was performed to understand the educational needs of students and expectations of parents and the pharma industry, followed by activities to promote interactive teaching-learning in a selected institute. The post-study feedback survey revealed interesting results, which will, boosts effective knowledge dissemination along with improved student attendance.