Application of machine learning in CT images and X-rays of COVID-19 pneumonia

Fengjun, Z

doi:10.1097/md.0000000000026855

Cited by 42 publications

(22 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It must be noted, however, that this study was conducted on smaller population (2,500 patients in current study vs. 1,455 cases in Goodman-Meza et al) and led to creation of model characterised by lower AUC value (0.99 vs. 0.91) and area under precision recall curve (1.00 vs. 0.76). The above studies were all based on the biochemical parameters, nonetheless the created models could be enhanced by including an analysis X-ray or computer tomography images, as suggested by the previous reports ( 64 , 65 ). Further research in this matter is necessary.…”

Section: Discussionmentioning

confidence: 99%

Influence of Co-morbidities During SARS-CoV-2 Infection in an Indian Population

et al. 2022

View full text Add to dashboard Cite

BackgroundSince the outbreak of COVID-19 pandemic the interindividual variability in the course of the disease has been reported, indicating a wide range of factors influencing it. Factors which were the most often associated with increased COVID-19 severity include higher age, obesity and diabetes. The influence of cytokine storm is complex, reflecting the complexity of the immunological processes triggered by SARS-CoV-2 infection. A modern challenge such as a worldwide pandemic requires modern solutions, which in this case is harnessing the machine learning for the purpose of analysing the differences in the clinical properties of the populations affected by the disease, followed by grading its significance, consequently leading to creation of tool applicable for assessing the individual risk of SARS-CoV-2 infection.MethodsBiochemical and morphological parameters values of 5,000 patients (Curisin Healthcare (India) were gathered and used for calculation of eGFR, SII index and N/L ratio. Spearman’s rank correlation coefficient formula was used for assessment of correlations between each of the features in the population and the presence of the SARS-CoV-2 infection. Feature importance was evaluated by fitting a Random Forest machine learning model to the data and examining their predictive value. Its accuracy was measured as the F1 Score.ResultsThe parameters which showed the highest correlation coefficient were age, random serum glucose, serum urea, gender and serum cholesterol, whereas the highest inverse correlation coefficient was assessed for alanine transaminase, red blood cells count and serum creatinine. The accuracy of created model for differentiating positive from negative SARS-CoV-2 cases was 97%. Features of highest importance were age, alanine transaminase, random serum glucose and red blood cells count.ConclusionThe current analysis indicates a number of parameters available for a routine screening in clinical setting. It also presents a tool created on the basis of these parameters, useful for assessing the individual risk of developing COVID-19 in patients. The limitation of the study is the demographic specificity of the studied population, which might restrict its general applicability.

show abstract

Section: Discussionmentioning

confidence: 99%

Influence of Co-morbidities During SARS-CoV-2 Infection in an Indian Population

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Machine learning, together with image processing, has been employed in recent years to assist doctors during clinical and diagnostic process [ 80 , 81 ].…”

Section: Imaging Of Biofilms and The Diversity Of Detection Methodsmentioning

confidence: 99%

The Two Weapons against Bacterial Biofilms: Detection and Treatment

et al. 2021

View full text Add to dashboard Cite

Bacterial biofilms are defined as complex aggregates of bacteria that grow attached to surfaces or are associated with interfaces. Bacteria within biofilms are embedded in a self-produced extracellular matrix made of polysaccharides, nucleic acids, and proteins. It is recognized that bacterial biofilms are responsible for the majority of microbial infections that occur in the human body, and that biofilm-related infections are extremely difficult to treat. This is related with the fact that microbial cells in biofilms exhibit increased resistance levels to antibiotics in comparison with planktonic (free-floating) cells. In the last years, the introduction into the market of novel compounds that can overcome the resistance to antimicrobial agents associated with biofilm infection has slowed down. If this situation is not altered, millions of lives are at risk, and this will also strongly affect the world economy. As such, research into the identification and eradication of biofilms is important for the future of human health. In this sense, this article provides an overview of techniques developed to detect and imaging biofilms as well as recent strategies that can be applied to treat biofilms during the several biofilm formation steps.

show abstract

“…ey are computer systems [26][27][28][29] that try to emulate some of the functions of living organisms. is means that they are made up of elements that mimic (in basic functions) the behavior and organization of the organism.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Detection of Pneumonia Infection by Using Deep Learning on a Mobile Platform

Alhazmi

Alassery

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Pneumonia is a disease that spreads quickly and poses a serious risk to the health and well-being of its victims. An accurate biomedical diagnosis of pneumonia necessitates the use of various diagnostic tools and the evaluation of various clinical features, all of which are hindered by the lack of available experts and tools. According to the research presented here, a mobile app that uses deep learning techniques to classify whether or not a patient has pneumonia is being developed. It was hoped that a mobile application prototype for detecting pneumonia using neural networks would be developed as part of this study. The use of a high-level tool such as Create ML makes this process easier and eliminates issues such as how many layers a neural network has, initializing the model parameters, or which algorithms to use. The model can now be accessed by anyone, anywhere, via a mobile application. The dataset of more than 5,000 real images was used to train an image classification model using Create ML, a tool with a graphical interface, and there was no need for specialized knowledge.

show abstract

Application of machine learning in CT images and X-rays of COVID-19 pneumonia

Cited by 42 publications

References 100 publications

Influence of Co-morbidities During SARS-CoV-2 Infection in an Indian Population

Influence of Co-morbidities During SARS-CoV-2 Infection in an Indian Population

The Two Weapons against Bacterial Biofilms: Detection and Treatment

Detection of Pneumonia Infection by Using Deep Learning on a Mobile Platform

Contact Info

Product

Resources

About