ABSTRACT
COVID-19, is caused by the transmission of SARS-CoV-2 through direct or indirect contact with infected people though respiratory droplets has transitioned from a pandemic to an endemic but is still regarded as active by WHO. Restrictions and lockdowns were lifted as the situation became endemic, but the previous measures had to be kept in place. By developing a module that includes temperature monitoring, face mask detection, a non-contact sanitizer dispenser, and door automation that operates based on the number of individuals inside a closed area in order to maintain social distance, our project aims to incorporate these precautions into our everyday language. As a part of making the new normal easily adaptable, we also introduce a webpagebased reservation system, which wm essentially display the current count and also help in reducing the waiting periods. © 2023 IEEE.
ABSTRACT
There have been attempts made previously to classify and determine the diagnosis of a disease of a patient based on the X-rays and computed tomography images of various parts of the body. In the field of lung disease diagnosis, there have been attempts to identify lungs infected with pneumonia, COVID-19, and tuberculosis, either individually classifying them into two groups of positive and negative of the given disease or in groups with multiple classes. These methods and approaches have used various deep learning models like CNNs, ResNet50, VGG19, Inception V3, MobileNet_V2, hybrid models, and ensemble learning methods. In this paper, we have proposed a model that takes an X-ray image of the lungs of the patients as input and classifies the result as one of the following classes: tuberculosis, pneumonia, COVID-19, or normal, that is, healthy lungs. What we have used here is transfer learning, with our base model being EfficientNet which gives an accuracy of 93%. For this, we have used different datasets of X-ray images of patients with different lung ailments, namely pneumonia, tuberculosis, and COVID. The dataset consists of images in four categories, the above-mentioned three diseases and a fourth category of normal healthy lungs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
ABSTRACT
The coronavirus (COVID-19) outbreak has opened an alarming situation for the whole world and has been marked as one of the most severe and acute medical conditions in the last hundred years. Various medical imaging modalities including computer tomography (CT) and chest x-rays are employed for diagnosis. This paper presents an overview of the recently developed COVID-19 detection systems from chest x-ray images using deep learning approaches. This review explores and analyses the data sets, feature engineering techniques, image pre-processing methods, and experimental results of various works carried out in the literature. It also highlights the transfer learning techniques and different performance metrics used by researchers in this field. This information is helpful to point out the future research direction in the domain of automatic diagnosis of COVID-19 using deep learning techniques.
ABSTRACT
Purpose: During the current pandemic scientists, researchers, and health professionals across the globe are in search of new technological methods for tackling COVID-19. The magnificent performance reported by machine learning and deep learning methods in the previous epidemic has encouraged researchers to develop systems with these methods to diagnose COVID-19. Methods: In this paper, an ensemble-based multi-level voting model is proposed to diagnose COVID-19 from chest x-rays. The multi-level voting model proposed in this paper is built using four machine learning algorithms namely Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) with a linear kernel, and K-Nearest Neighbor (KNN). These algorithms are trained with features extracted using the ResNet50 deep learning model before merging them to form the voting model. In this work, voting is performed at two levels, at level 1 these four algorithms are grouped into 2 sets consisting of two algorithms each (set 1 - SVM with linear kernel and LR and set 2 - RF and KNN) and intra set hard voting is performed. At level 2 these two sets are merged using hard voting to form the proposed model. Results: The proposed multilevel voting model outperformed all the machine learning algorithms, pre-trained models, and other proposed works with an accuracy of 100% and specificity of 100%. Conclusion: The proposed model helps for the faster diagnosis of COVID-19 across the globe.
ABSTRACT
Objective This article determines the occurrence and variables associated with pulse methylprednisolone treatment failure in children with coronavirus disease 2019 (COVID-19)-related multisystem inflammatory syndrome in children (MIS-C). Methods This prospective observational study was undertaken at a tertiary care teaching hospital in Kerala, India. Children admitted with COVID-19-related MIS-C who were treated with pulse methylprednisolone as first-line therapy were included in the study. Depending on the response to the treatment, they were divided into two groups. The clinical, laboratory parameters, and follow-up findings at 3 months were compared between the two groups Results Seventy-six patients were admitted with MIS-C during the study period. Sixty received pulse methylprednisolone as the first-line therapy. Of the 60 patients who received pulse methylprednisolone, 50 responded to treatment, while 10 required repeat immunomodulation. Need for noninvasive or invasive ventilation (relative risk [RR]: 13.14, 95% confidence interval [CI]: 3.147-54.88), six or more organ involvement (RR: 4.667, 95% CI: 1.349-16.149), thrombocytopenia (RR: 6.43, 95% CI: 0.87-47.6, p 0.003), and abnormal chest X-ray findings at admission (RR: 4.5, 95% CI: 1.46-13.8), were found to be associated with increased risk of treatment failure with pulse methylprednisolone therapy. Note that 88% of patients with coronary artery involvement showed resolution at 3-month follow-up. Conclusion More than 80% of children with MIS-C can be treated successfully with corticosteroids. The need for ventilator support, abnormal chest X-ray findings, and thrombocytopenia at admission were found to be factors associated with pulse methylprednisolone treatment failure.
ABSTRACT
The PyRx software and Discovery studio were used in the present molecular docking studies of the 16 ligands of Ocimum tenuiflorum L., selected based on their high therapeutic potentials, viz., (E)-6-hydroxy-4,6-dimethylhept-3-en-2-one, Apigenin, Bieugenol, Cirsilineol, Cirsimaritin, β-Caryophyllene epoxide, Dehydrodieugenol B, Eugenol, Ferulaldehyde, Isothymonin, Isothymusin, Linalool, Luteolin, Ocimarin, Rosmarinic acid, and Thymol. Saquinavir was used as a positive control. The binding affinities of the 16 ligands to the main proteases of COVID-19 6LU7 and 6Y2E (critical for viral replication) and their ability to arrest the virus replication were recorded. The binding affinities of the ligands to 6LU7 and 6Y2E ranged from-4.3 and-4.7 kcal/mol (for (E)-6-hydroxy-4,6-dimethylhept-3-en-2-one) to-7.6 (for Rosmarinic acid to both target proteins). While the corresponding values for the control drug Saquinavir were-7.8 and-7.6 respectively. The Rosmarinic acid, in binding with both the proteases (-7.6 and-7.6 kcal/mol) showed six conventional hydrogen bonds, one carbon hydrogen bond (ASP 153 had one conventional hydrogen bond and one carbon hydrogen bond), one Pi-alkyl bond, one Pi-Pi stacked bond, eight van der waals bonds for 6LU7 protease;it formed three conventional hydrogen bonds, two Pi-alkyl bonds, one unfavourable donor – donor bond and 14 van der waals bonds with 6Y2E protease. The control drug – Saquinavir in binding with 6LU7 protease showed 12 van der waals, one alkyl, one Pi-alkyl, one Pi-cation, one Pi-stacked and four conventional hydrogen bonds, which indicates that it has less affinity when compared with Rosmarinic acid. Similarly, the control drug on binding with 6Y2E protease exhibited ten van der waals, four Pi-alkyl, one cation and three hydrogen bonds. The results are in conformity to similar other studies, and herald a promising scope for Rosmarinic acid as lead molecule in the drug discovery for COVID-19. © The authors.
ABSTRACT
The whole world faces an uncommon situation in its history due to the spread of the novel coronavirus (COVID-19). First impacted its existence during December 2019 in Wuhan City, Hubei Province, China. However, the spread of the disease is marginally visible and resulting in an epidemic distribution across capital cities of India. As of June 15, 2020, in India, 368705 are the confirmed cases, and 12280 people have deceased their lives. Collecting the statistics of daily infections, deaths and recovery data and predicting epidemic trends of COVID-19 in India has the most significant importance for developing and measuring the impacts of public intervention strategies. Based on India and Tamil Nadu's initial 105 days of COVID-19 statistics of (one of its states), we built the logistic growth model and compared their accuracy with the R2 coefficient measure. Based on the lockdown periods and severe protection measures, a scenario-based analysis of four different SIR models predicts the confirmed cases. This proposed scenario-based analysis is helpful to pre-estimate the maximum infection rate and maximum peak day of infection with the total percentage of the population being infected by the COVID-19 outbreak in India. This analysis suggests that the severe control measures are working well in India, despite the exponential growth of the outbreak situation. © 2022 Author(s).
ABSTRACT
COVID-19 is a deadly disease that may cause lasting harm to the lungs and other organs. It can be life-threatening if timely action is not taken and therefore detection at an early is vital. The objective of this paper is to use chest X-rays to identify COVID-19 images using deep learning models. Since COVID-19 harms the respiratory epithelial cells, we could make use of X-rays to determine the patient's lungs condition. When the number of patients is exceptionally high and thus the required radiological expertise is low, deep learning-based recommender systems can be extremely useful. The goal is to use pre-trained models to develop an image classification model that can predict Covid-19 in Chest X-Ray scans with reasonably high accuracy. CNN's are primarily used for medical image classification tasks as they can easily detect the important features and classify them accordingly. Four distinct pre-trained models were used for this purpose. In this work, the analysis of the results showed that compared with other models, the DenseNet201 model provides the highest accuracy (96.54%) in detecting chest X-rays. This model can be used by any medical professional on any system to quickly identify Covid +ve patients using chest X-ray scans. © 2021 IEEE.
ABSTRACT
Background: Covid 19 pandemic has caused a significant death toll across the world, its effects on placental morphology are of great concern to the obstetricians and pregnant women because it effects the health of the fetus.
ABSTRACT
Lung related issues are rapidly increasing day by day as it is very important to identify the disease and get treated earliest possible as lungs are part of very complex system, expanding and relaxing thousands of times each day allow us to breathe by bringing oxygen into our bodies and sending carbon dioxide out. Lung related issues are directly preoperational to breathing problems. X-rays are one of the important ways of identifying the status of lungs. As there are many communicable diseases like Covid-19, the person should be identified early and should be treated to control the spread of virus. Lung Opacity is one of the major problem faced by many people and also a very serious problem if not treated early it will spread entire lungs and which leads to cancer similarly Pneumonia is another disease which is an infection to one's lungs caused by spread of virus. All these diseases directly affect Respiratory system of human. The paper aims to lung diseases classification among Pneumonia, Lung opacity, Normal and Covid-19 using the proposed hybrid model. The Deep Transfer Learning model helps to extract good features which helps for better learning and greater results. The Ensembled model of Deep Transfer Learning is used in this paper, which is a combination of VGG, EfficientNet and DenseNet. Considering the output of image augmentation as input for Ensembled model and classification of lung disease. The accuracy of the proposed hybrid model is very much accurate when compared to individual base models. © 2021 IEEE.
ABSTRACT
INTRODUCTION: Despite several ongoing efforts in biomedicine and traditional medicine, there are no drugs or vaccines for coronavirus disease 2019 (COVID-19) as of May 2020; Kabasura Kudineer (KSK), a polyherbal formulation from India's Siddha system of medicine, has been traditionally used for clinical presentations similar to that of COVID-19. We explored the efficacy of KSK in reducing viral load and preventing the disease progression in asymptomatic, COVID-19 cases. METHODS: A prospective, single-center, open-labeled, randomized, controlled trial was conducted in a COVID Care Centre in Chennai, India. We recruited reverse-transcription polymerase chain reaction (RT-PCR)-confirmed COVID-19 of 18 to 55 years of age, without clinical symptoms and co-morbidities. They were randomized (1:1 ratio) to KSK (60 mL twice daily for 7 days) or standard of care (7 days supplementation of vitamin C 60,000 IU morning daily and zinc 100 mg evening daily) groups. The primary outcomes were reduction in the SARS-CoV-2 load [as measured by cyclic threshold (CT) value of RT-PCR], prevention of progression of asymptomatic to symptomatic state, and changes in the immunity markers including interleukins (IL-6, IL-10, IL-2), interferon gamma (IFNγ), and tumor necrosis factor (TNF α). Siddha clinical assessment and the occurrence of adverse effects were documented as secondary outcomes. Paired t-test was used in statistical analysis. RESULTS: Viral load in terms of the CT value (RdRp: 95% CI = 1.89 to 5.74) declined significantly on the seventh day in the KSK group and that of the control group, more pronounced in the study group. None progressed to the symptomatic state. There was no significant difference in the biochemical parameters. We did not observe any changes in the Siddha-based clinical examination and adverse events in both groups. CONCLUSION: KSK significantly reduced SARS-CoV-2 viral load among asymptomatic COVID-19 cases and did not record any adverse effect, indicating the use of KSK in the strategy against COVID-19. Larger, multi-centric trials can strengthen the current findings. TRIAL REGISTRATION: Clinical Trial Registry of India CTRI2020/05/025215 . Registered on 16 May 2020.
Subject(s)
COVID-19 , SARS-CoV-2 , Ascorbic Acid , Dietary Supplements , Humans , India , Medicine, Ayurvedic , Prospective Studies , Treatment Outcome , Viral Load , ZincABSTRACT
Objective: To study the clinical profile and outcome of children with MIS-C treated with methylprednisolone pulse therapy and/or intravenous immunoglobulin (IVIG). Method: This prospective observational study included children satisfying CDC MIS-C criteria admitted from September to November, 2020. Primary outcome was persistence of fever beyond 36 hours after start of immunomodulation therapy. Secondary outcomes included duration of ICU stay, mortality, need for repeat immunomodulation, time to normalization of CRP and persistence of coronary abnormalities at 2 weeks. Results: Study population included 32 patients with MIS-C with median (IQR) age of 7.5 (5–9.5) years. The proportion of children with gastrointestinal symptoms was 27 (84%), cardiac was 29 (91%) and coronary artery dilatation was 11 (34%). Pulse methylprednisolone and intravenous immunoglobulin were used as first line therapy in 26 (81%), and 6 (19%) patients, respec-tively. Treatment failure was observed in 2/26 patients in methylprednisolone group and 2/6 patients in IVIG group. C-reactive protein levels less than 60mg/L by day 3 was seen in 17(74%) in methylprednisolone group and 2 (25%) in IVIG group (P=0.014). There was no mortality. At 2 weeks follow-up coronary artery dilatation persisted in 4 in methylprednisolone group and 1 in IVIG group. Conclusion: In patients with SARS-CoV-2 related MIS-C, methylprednisolone pulse therapy was associated with favorable short-term outcomes. © 2021, Indian Academy of Pediatrics.
ABSTRACT
BACKGROUND: Multi system inflammatory syndrome in children (MIS-C) is a rare, but life-threatening complication of SARS-CoV-2 infection. OBJECTIVES: To study the clinical profile and outcome of children with MIS-C treated with methylprednisolone pulse therapy and /or IVIG. STUDY DESIGN: Observational study. PARTICIPANTS: Children satisfying CDC MIS-C criteria admitted during the study period. OUTCOME MEASURES: Primary outcome was persistence of fever beyond 36 hours after start of immunomodulation therapy. Secondary outcomes included duration of ICU stay, mortality, need for repeat immunomodulation, time to normalization of CRP and persistence of coronary abnormalities at 2 weeks. RESULTS: Study population included 32 patients with MIS-C with median (IQR) age of 7.5 (5-9.5) years. The proportion of children with gastrointestinal symptoms was 27 (84%), cardiac was 29 (91%) and coronary artery dilatation was 11 (34%). Pulse methylprednisolone and intravenous immunoglobulin were used as first line therapy in 26 (81%), and 6 (19%) patients, respectively. Treatment failure was observed in 2/26 patients in methylprednisolone group and 2/6 patients in IVIG group. C-reactive protein levels less than 60mg/L by day 3 was seen in 17(74%) in methylprednisolone group and 2 (25%) in IVIG group (P=0.014). There was no mortality. At 2 weeks follow-up coronary artery dilatation persisted in 4 in methylprednisolone group and 1 in IVIG group. CONCLUSIONS: In patients with SARS-CoV-2 related MIS-C, methylprednisolone pulse therapy was associated with favorable short-term outcomes.
ABSTRACT
OBJECTIVES: The primary objectives of this study are to determine efficacy of Siddha medicine, Kabasura kudineer in reduction of SARS-CoV-2 viral load and reducing the onset of symptoms in asymptomatic COVID-19 when compared to Vitamin C and Zinc (CZ) supplementation. In addition, the trial will examine the changes in the immunological markers of the Siddha medicine against control. The secondary objectives of the trial are to evaluate the safety of the Siddha medicine and to document clinical profile of asymptomatic COVID-19 as per principles of Siddha system of Medicine. TRIAL DESIGN: A single centre, open-label, parallel group (1:1 allocation ratio), exploratory randomized controlled trial. PARTICIPANTS: Cases admitted at non-hospital settings designated as COVID Care Centre and managed by the State Government Stanley Medical College, Chennai, Tamil Nadu, India will be recruited. Eligible participants will be those tested positive for COVID-19 by Reverse Transcriptase Polymerase Chain reaction (RT-PCR) aged 18 to 55 years without any symptoms and co-morbidities like diabetes mellitus, hypertension and bronchial asthma. Those pregnant or lactating, with severe respiratory disease, already participating in COVID trials and with severe illness like malignancy will be excluded. INTERVENTION AND COMPARATOR: Adopting traditional methods, decoction of Kabasura kudineer will be prepared by boiling 5g of KSK powder in 240 ml water and reduced to one-fourth (60ml) and filtered. The KSK group will receive a dose of 60ml decoction, orally in the morning and evening after food for 14 days. The control group will receive Vitamin C (60000 IU) and Zinc tablets (100mg) orally in the morning and evening respectively for 14 days. MAIN OUTCOMES: The primary outcomes are the reduction in the SARS-CoV-2 load [as measured by cyclic threshold (CT) value of RT-PCR] from the baseline to that of seventh day of the treatment, prevention of progression of asymptomatic to symptomatic state (clinical symptoms like fever, cough and breathlessness) and changes in the immunity markers [Interleukins (IL) 6, IL10, IL2, Interferon gamma (IFNγ) and Tumor Necrosis Factor (TNF) alpha]. Clinical assessment of COVID-19 as per standard Siddha system of medicine principles and the occurrence of adverse effects will be documented as secondary outcomes. RANDOMISATION: The assignment to the study or control group will be allocated in equal numbers through randomization using random number generation in Microsoft Excel by a statistician who is not involved in the trial. The allocation scheme will be made by an independent statistician using a sealed envelope. The participants will be allocated immediately after the eligibility assessment and informed consent procedures. BLINDING (MASKING): This study is unblinded. The investigators will be blinded to data analysis, which will be carried out by a statistician who is not involved in the trial. NUMBERS TO BE RANDOMISED (SAMPLE SIZE): Sample size could not be calculated, as there is no prior trial on KSK. This trial will be a pilot trial. Hence, we intend to recruit 60 participants in total using a 1:1 allocation ratio, with 30 participants randomised into each arm. TRIAL STATUS: Protocol version 2.0 dated 16th May 2020. Recruitment is completed. The trial started recruitment on the 25th May 2020. We anticipate study including data analysis will finish on November 2020. We also stated that protocol was submitted before the end of data collection TRIAL REGISTRATION: The study protocol was registered with clinical trial registry of India (CTRI) with CTRI/2020/05/025215 on 16 May 2020. FULL PROTOCOL: The full protocol is attached as an additional file, accessible from the Trials website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this Letter serves as a summary of the key elements of the full protocol. The study protocol has been reported in accordance with the Standard Protocol Items: Recommendations for Clinical Interventional Trials (SPIRIT) guidelines (Additional file 2).
Subject(s)
Ascorbic Acid , Betacoronavirus , Coronavirus Infections , Medicine, Ayurvedic/methods , Pandemics , Pneumonia, Viral , Zinc , Adult , Ascorbic Acid/administration & dosage , Ascorbic Acid/adverse effects , Asymptomatic Infections/therapy , Betacoronavirus/drug effects , Betacoronavirus/isolation & purification , COVID-19 , Coronavirus Infections/diagnosis , Coronavirus Infections/drug therapy , Dietary Supplements , Drug Monitoring/methods , Female , Humans , India , Male , Pneumonia, Viral/diagnosis , Pneumonia, Viral/drug therapy , Randomized Controlled Trials as Topic , SARS-CoV-2 , Treatment Outcome , Viral Load/methods , Zinc/administration & dosage , Zinc/adverse effectsABSTRACT
India imposed a nationwide lockdown from 25th March 2020 onwards to combat the spread of COVID-19 pandemic. To model the spread of a disease and to predict its future course, epidemiologists make use of compartmental models such as the SIR model. In order to address some of the assumptions of the standard SIR model, a new modified version of SIR model is proposed in this paper that takes into account the percentage of infected individuals who are tested and quarantined. This approach helps overcome the assumption of homogenous mixing of population which is inherent to the conventional SIR model. Using the available data of the number of COVID-19 positive cases reported in the state of Kerala, and in India till 26th April, 2020 and 12th May 2020, respectively, the parameter estimation problem is converted into an optimization problem with the help of a least squared cost function. The optimization problem is then solved using differential evolution optimizer. The impact of lockdown is quantified by comparing the rising trend in infections before and during the lockdown. Using the estimated set of parameters, the model predicts that in the state of Kerala, by using certain interventions the pandemic can be successfully controlled latest by the first week of July, whereas the R 0 value for India is still greater than 1, and hence lifting of lockdown from all regions of the country is not advisable.