Predicting mortality rate and associated risks in COVID-19 patients

Satpathy, Suneeta; Mangla, Monika; Sharma, Nonita; Deshmukh, Hardik; Mohanty, Sachinandan

doi:10.1007/s41324-021-00379-5

Cited by 37 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where the W requisites determine weight matrices such as Wix is the weights matrix from the input gate to the input function and, W ic , W fc , W oc are diagonal matrices of weights for a peephole associations, further, the b provisos represents bias vectors where b i is the input gate bias vector, σ is the logistic sigmoid function, and I, f, o and c are respectively the input gate, f or get gate, output gate, and cell activation vectors all of which are of the same size as the cell output activation vector m, is the element-wise ⊙ product of the vectors, g and h are the cell input and cell output activation functions [19,22,23].…”

Section: Theory Of Lstmmentioning

confidence: 99%

A Deep Learning Method to Forecast COVID-19 Outbreak

Dash

Chakravarty

Mohanty³

et al. 2021

New Gener. Comput.

View full text Add to dashboard Cite

A new pandemic attack happened over the world in the last month of the year 2019 which disrupt the lifestyle of everyone around the globe. All the related research communities are trying to identify the behaviour of pandemic so that they can know when it ends but every time it makes them surprise by giving new values of different parameters. In this paper, support vector regression (SVR) and deep neural network method have been used to develop the prediction models. SVR employs the principle of a support vector machine that uses a function to estimate mapping from an input domain to real numbers on the basis of a training model and leads to a more accurate solution. The long short-term memory networks usually called LSTM, are a special kind of RNN, capable of learning long-term dependencies. And also is quite useful when the neural network needs to switch between remembering recent things, and things from a long time ago and it provides an accurate prediction to COVID-19. Therefore, in this study, SVR and LSTM techniques have been used to simulate the behaviour of this pandemic. Simulation results show that LSTM provides more realistic results in the Indian Scenario.

show abstract

Section: Theory Of Lstmmentioning

confidence: 99%

A Deep Learning Method to Forecast COVID-19 Outbreak

Dash

Chakravarty

Mohanty³

et al. 2021

New Gener. Comput.

View full text Add to dashboard Cite

show abstract

“…Numerous performance metrics are used to find the competence of the proposed models. Auto seasonal auto regressive integrated moving average model overcomes the performance of other models [ 12 ]. To detect the hotspots of the Covid-19 in India, four factors are taken into considerations which are foreign tourist’s arrival in India, total population, reported confirmed cases and population density.…”

Section: Literature Reviewmentioning

confidence: 99%

CoBiD-net: a tailored deep learning ensemble model for time series forecasting of covid-19

et al. 2021

View full text Add to dashboard Cite

The pandemic of novel coronavirus disease 2019 (Covid-19) has left the world to a standstill by creating a calamitous situation. To mitigate this devastating effect the inception of artificial intelligence into medical health care is mandatory. This study aims to present the educational perspective of Covid-19 and forecast the number of confirmed and death cases in the USA, India, and Brazil along with the discussion of endothelial dysfunction in epithelial cells and Angiotensin-Converting Enzyme 2 receptor (ACE2) with the Covid-19. Three different deep learning based experimental setups have been framed to forecast Covid-19. Models are (i) Bi-directional Long Short Term Memory (LSTM) (ii) Convolutional LSTM (iii) Proposed ensemble of Convolutional and Bi-directional LSTM network are known as CoBiD-Net ensemble. The educational perspective of Covid-19 has been given along with an architectural discussion of multi-organ failure due to intrusion of Covid-19 with the cell receptors of the human body. Different classification metrics have been calculated using all three models. Proposed CoBiD-Net ensemble model outperforms the other two models with respect to accuracy and mean absolute percentage error (MAPE). Using CoBiD-Net ensemble, accuracy for Covid-19 cases ranges from 98.10 to 99.13% with MAPE ranges from 0.87 to 1.90. This study will help the countries to know the severity of Covid-19 concerning education in the future along with forecasting of Covid-19 cases and human body interaction with the Covid-19 to make it the self-replicating phenomena. Supplementary Information The online version contains supplementary material available at 10.1007/s41324-021-00408-3.

show abstract

“…However, the designed models did not provide the better sensitivity to recognize patients at low risk. Artificial intelligence-mediated models were introduced in Suneeta Satpathy et al ( 2021 ) to predict the mortality rate of COVID-19. The designed methods minimize the root mean square error.…”

Section: Introductionmentioning

confidence: 99%

Biserial targeted feature projection based radial kernel regressive deep belief neural learning for covid-19 prediction

Bose¹,

Kumar

Premkumar

et al. 2022

Soft Comput

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19) is a highly infectious viral disease caused by the novel SARS-CoV-2 virus. Different prediction techniques have been developed to predict the coronavirus disease’s existence in patients. However, the accurate prediction was not improved and time consumption was not minimized. In order to address these existing problems, a novel technique called Biserial Targeted Feature Projection-based Radial Kernel Regressive Deep Belief Neural Learning (BTFP-RKRDBNL) is introduced to perform accurate disease prediction with lesser time consumption. The BTFP-RKRDBNL techniques perform disease prediction with the help of different layers such as two visible layers namely input and layer and two hidden layers. Initially, the features and data are collected from the dataset and transmitted to the input layer. The Point Biserial Correlative Target feature projection is used to select relevant features and other irrelevant features are removed with minimizing the disease prediction time. Then the relevant features are sent to the hidden layer 2. Next, Radial Kernel Regression is applied to analyze the training features and testing disease features to identify the disease with higher accuracy and a lesser false positive rate. Experimental analysis is planned to measure the prediction accuracy, sensitivity, and specificity, and prediction time for different numbers of patients. The result illustrates that the method increases the prediction accuracy, sensitivity, and specificity by 10, 6, and 21% and reduces the prediction time by 10% as compared to state-of-the-art works.

show abstract

Predicting mortality rate and associated risks in COVID-19 patients

Cited by 37 publications

References 30 publications

A Deep Learning Method to Forecast COVID-19 Outbreak

A Deep Learning Method to Forecast COVID-19 Outbreak

CoBiD-net: a tailored deep learning ensemble model for time series forecasting of covid-19

Biserial targeted feature projection based radial kernel regressive deep belief neural learning for covid-19 prediction

Contact Info

Product

Resources

About