A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records

Gong, Kuang; Wu, Dufan; Arru, Chiara; Homayounieh, Fatemeh; Neumark, Nir; Guan, Jiahui; Buch, Varun; Kim, Kyungsang; Bizzo, Bernardo C.; Hui, Rutai; Tak, Won Young; Park, Soo Young; Lee, Yu Rim; Kang, Min Kyu; Park, Jung Gil; Carriero, Alessandro; Saba, Luca; Masjedi, Mahsa; Talari, Hamid Reza; Babaei, Rosa; Mobin, Hadi Karimi; Ebrahimian, Shadi; Guo, Ning; Digumarthy, Subba R.; Dayan, Ittai; Kalra, Mannudeep K.; Li, Quanzheng

doi:10.1016/j.ejrad.2021.109583

Cited by 33 publications

(27 citation statements)

References 44 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study also indicated that some studies developed new networks based on existing widely used networks such as AlexNet, U-Net, ResNet, VGG, and GoogLeNet [13,42,43]. Since GAN was proposed, DCGAN [44], WGAN [45], CycleGAN [21], BEGAN [46], and BigBiGAN [47] were optimised for domain adaptation, data augmentation, and imageto-image translation.…”

Section: Discussionmentioning

confidence: 76%

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Wang

Huang

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

To evaluate the general rules and future trajectories of deep learning (DL) networks in medical image analysis through bibliometric and hot spot analysis of original articles published between 2012 and 2020. Methods: Original articles related to DL and medical imaging were retrieved from the PubMed database. For the analysis, data regarding radiological subspecialties; imaging techniques; DL networks; sample size; study purposes, setting, origins and design; statistical analysis; funding sources; authors; and first authors' affiliation was manually extracted from each article. The Bibliographic Item Co-Occurrence Matrix Builder and VOSviewer were used to identify the research topics of the included articles and illustrate the future trajectories of studies.Results: The study included 2685 original articles. The number of publications on DL and medical imaging has increased substantially since 2017, accounting for 97.2% of all included articles. We evaluated the rules of the application of 47 DL networks to eight radiological tasks on 11 human organ sites. Neuroradiology, thorax, and abdomen were frequent research subjects, while thyroid was under-represented. Segmentation and classification tasks were the primary purposes. U-Net, ResNet, and VGG were the most frequently used Convolutional neural network-derived networks. GAN-derived networks were widely developed and applied in 2020, and transfer learning was highlighted in the COVID-19 studies. Brain, prostate, and diabetic retinopathy-related studies were mature research topics in the field. Breast-and lung-related studies were in a stage of rapid development.Conclusions: This study evaluates the general rules and future trajectories of DL network application in medical image analyses and provides guidance for future studies.

show abstract

Section: Discussionmentioning

confidence: 76%

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Wang

Huang

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence (AI) has also contributed to the detection of lung changes characteristic of COVID during the pandemic [19,20,42,43]. CAD programs can define the presence of SARS-CoV-2 infection and evaluate the severeness of the disease by analyzing the characteristic opacity patterns and their volume inside the lungs both in CT and X-ray images and, thus, help doctors to diagnose and properly treat COVID-19 patients.…”

Section: Discussionmentioning

confidence: 99%

Are We Overdoing It? Changes in Diagnostic Imaging Workload during the Years 2010–2020 including the Impact of the SARS-CoV-2 Pandemic

et al. 2021

View full text Add to dashboard Cite

Since the 1990s, there has been a significant increase in the number of imaging examinations as well as a related increase in the healthcare expenditure and the exposure of the population to X-rays. This study aimed to analyze the workload trends in radiology during the last decade, including the impact of COVID-19 in a single university hospital in Poland and to identify possible solutions to the challenges that radiology could face in the future. We compared the annual amount of computed tomography (CT), radiography (X-ray), and ultrasound (US) examinations performed between the years 2010 and 2020 and analyzed the changes in the number of practicing radiologists in Poland. The mean number of patients treated in our hospital was 60,727 per year. During the last decade, the number of CT and US examinations nearly doubled (from 87.4 to 155.7 and from 52.1 to 86.5 per 1000 patients in 2010 and 2020 respectively), while X-ray examinations decreased from 115.1 to 96.9 per 1000 patients. The SARS-CoV-2 pandemic did not change the workload trends as more chest examinations were performed. AI, which contributed to the COVID-19 diagnosis, could aid radiologists in the future with the growing workload by increasing the efficiency of radiology departments as well as by potentially minimizing the related costs.

show abstract

“…Data mining algorithms have only been used to discover symptom patterns in COVID-19 patients [ 52 ] as well as to make predictions about COVID-19 patient severity [ 2 , [7] , [8] , [9] ] and recovery [ 53 ]. The MLP algorithm classified the severe patients with a precision (96.5%), similar to XGBoost [ 9 ] and other multipurpose algorithms [ 7 ], but with the advantage of using laboratory tests.…”

Section: Discussionmentioning

confidence: 99%

“…ML algorithms are just beginning to be investigated as prognostic tools. ML-driven predictions of COVID-19 outcomes are based on clinical data and largely radiological features extracted from X-ray computed tomography (CT) [ 2 , [7] , [8] , [9] ]. However, CT scan images are time consuming, weakly correlated with initial disease severity [ 10 ] and unable to detect small infected lung regions.…”

Section: Introductionmentioning

confidence: 99%

Biomarkers of severe COVID-19 pneumonia on admission using data-mining powered by common laboratory blood tests-datasets

Pulgar-Sánchez

Chamorro

Fors

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

In the epidemiological COVID-19 research, artificial intelligence is a unique approach to make predictions about disease severity to manage COVID-19 patients. A limitation of artificial intelligence is, however, the high risk of bias. We investigated the skill of data mining and machine learning, two advanced forms of artificial intelligence, to predict severe COVID-19 pneumonia based on routine laboratory tests. A sample of 4009 COVID-19 patients was divided into Severe (PaO 2 < 60 mmHg, 489 cases) and Non-Severe (PaO 2 ≥ 60 mmHg, 3520 cases) groups according to blood hypoxemia on admission and their laboratory datasets analyzed by the R software and WEKA workbench. After curation, data were processed for the selection of the most influential features including hemogram, pCO 2 , blood acid-base balance, prothrombin time, inflammation biomarkers, and glucose. The best fit of variables was successfully confirmed by either the Multilayer Perceptron, a feedforward neural network algorithm that performed machine recognition of severe COVID-19 with 96.5% precision, or by the C4.5 software, a supervised learning algorithm based on an objective-predefined variable (severity) that generated a decision tree with 89.4% precision. Finally, a complex bivariate Pearson's correlation matrix combined with advanced hierarchical clustering (dendrograms) were conducted for knowledge discovery. The hidden structure of the datasets revealed shift patterns related to the development of COVID-19-induced pneumonia that involved the lymphocyte-to-C-reactive protein and leukocyte-to-C-protein ratios, neutrophil %, pH and pCO 2 . The data mining approaches to the hematological fluctuations associated with severe COVID-19 pneumonia could not only anticipate adverse clinical outcomes, but also reveal putative therapeutic targets.

show abstract

A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records

Cited by 33 publications

References 44 publications

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Are We Overdoing It? Changes in Diagnostic Imaging Workload during the Years 2010–2020 including the Impact of the SARS-CoV-2 Pandemic

Biomarkers of severe COVID-19 pneumonia on admission using data-mining powered by common laboratory blood tests-datasets

Contact Info

Product

Resources

About