Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China

Wang, Gang; Wei, Wudi; Jiang, Junjun; Ning, Chuanyi; Chen, Hongkang; Huang, Jiegang; Liang, Bingyu; Zang, Ning; Liao, Yulin; Chen, Runhuan; Lai, Jingzhen; Zhou, Oulu; Han, Jing; Liang, Hai‐Wei; Ye, L.

doi:10.1017/s095026881900075x

Cited by 29 publications

(33 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ARIMA model is one of the most popular methods used in infectious disease prediction, such as HFMD [ 2 , 8 ], COVID-19 [ 10 ], hepatitis [ 11 ], influenza [ 12 ], tuberculosis [ 13 ], as well as blood glucose concentrations and hypoglycemia [ 14 ], hospital daily outpatient visits [ 15 ], etc. LSTM is a special case of Recurrent Neural Networks (RNN) and is increasing in use in recent years in domains such as stocks [ 16 ], speech recognition [ 17 ], and disease prediction, such as HFMD [ 18 ], COVID-19 [ 19 ] and HIV [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China

Zhang

Guo

Meng

et al. 2021

IJERPH

View full text Add to dashboard Cite

Background: This study intends to identify the best model for predicting the incidence of hand, foot and mouth disease (HFMD) in Ningbo by comparing Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory Neural Network (LSTM) models combined and uncombined with exogenous meteorological variables. Methods: The data of daily HFMD incidence in Ningbo from January 2014 to November 2017 were set as the training set, and the data of December 2017 were set as the test set. ARIMA and LSTM models combined and uncombined with exogenous meteorological variables were adopted to fit the daily incidence of HFMD by using the data of the training set. The forecasting performances of the four fitted models were verified by using the data of the test set. Root mean square error (RMSE) was selected as the main measure to evaluate the performance of the models. Results: The RMSE for multivariate LSTM, univariate LSTM, ARIMA and ARIMAX (Autoregressive Integrated Moving Average Model with Exogenous Input Variables) was 10.78, 11.20, 12.43 and 14.73, respectively. The LSTM model with exogenous meteorological variables has the best performance among the four models and meteorological variables can increase the prediction accuracy of LSTM model. For the ARIMA model, exogenous meteorological variables did not increase the prediction accuracy but became the interference factor of the model. Conclusions: Multivariate LSTM is the best among the four models to fit the daily incidence of HFMD in Ningbo. It can provide a scientific method to build the HFMD early warning system and the methodology can also be applied to other communicable diseases.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China

Zhang

Guo

Meng

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…We explored the ES model using JMP 14 Pro software as previously described [21]. The ES model proposed by Robert G. Brown was a technique for manipulating data from a series of chronological observations to downplay the effects of random variation [22][23][24].…”

Section: Construction Of Es Modelmentioning

confidence: 99%

Comparison of ARIMA, ES, GRNN and ARIMA–GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States

Wang

Wei

et al. 2021

Epidemiol. Infect.

Self Cite

View full text Add to dashboard Cite

As acute infectious pneumonia, the coronavirus disease-2019 (COVID-19) has created unique challenges for each nation and region. Both India and the United States (US) have experienced a second outbreak, resulting in a severe disease burden. The study aimed to develop optimal models to predict the daily new cases, in order to help to develop public health strategies. The autoregressive integrated moving average (ARIMA) models, generalised regression neural network (GRNN) models, ARIMA–GRNN hybrid model and exponential smoothing (ES) model were used to fit the daily new cases. The performances were evaluated by minimum mean absolute per cent error (MAPE). The predictive value with ARIMA (3, 1, 3) (1, 1, 1)14 model was closest to the actual value in India, while the ARIMA–GRNN presented a better performance in the US. According to the models, the number of daily new COVID-19 cases in India continued to decrease after 27 May 2021. In conclusion, the ARIMA model presented to be the best-fit model in forecasting daily COVID-19 new cases in India, and the ARIMA–GRNN hybrid model had the best prediction performance in the US. The appropriate model should be selected for different regions in predicting daily new cases. The results can shed light on understanding the trends of the outbreak and giving ideas of the epidemiological stage of these regions.

show abstract

“…Moreover, Maurizio et al and Margaret et al [21] used machine learning in studying HIV drug resistance, and developed a framework that has many important applications in viral genomics more broadly. Wang et al [22]: Four models were applied: LSTM, NN, ARIMA, and GRNN -LSTM was the best. Pranav et al [23]: tuberculosis (TB) is the leading cause of preventable death in HIV/AIDS-positive patients.…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning and deep learning for the prediction of HIV/AIDS

Alehegn¹

2022

HIV & AIDS Review

View full text Add to dashboard Cite

Introduction: Nowadays human immunodeficiency virus (HIV)/acquired immunodeficiency syndrome (AIDS) is very dangerous. HIV targets the resistant system and weakens people's denial against many contaminations and some kinds of cancer. As the virus breaks up and impairs the function of immunity, infected people gradually become immunodeficient. Both deep learning and machine learning models play a great role in the prediction of diseases. The function of immunity is CD4 cell count. In this study both the machine learning and deep learning algorithms were applied. Material and methods:In this paper the data were collected from data world. Support vector machine, random forest, naïve Bayes, gated recurrent unit, and long short-term memory were used to fit the incidence data. The performance of the model was evaluated by accuracy, precision, sensitivity, and F-score with respective errors.Results: Based on the evaluation, deep learning models achieve better results in the metrics of accuracy, precision, and F-score than machine learning models. But in sensitivity metrics machine learning models achieve better result than deep learning. Machine learning algorithms SVM, RF, and NB provide accuracy of 89.00%, 87.00%, and 86.94%; precision of 75.89%, 74.97%, and 75.78%; sensitivity of 87.96%, 84.00%, and 84.12%; F-score of 82.87%, 80.03%, and 79.05%, respectively. LSTM, GRU provides accuracy of 97.65%, 96.00%, precision of 77.35%, 84.00%, sensitivity of 87.93%, 82.98%, and F-score of 82.03%, 83.20%, respectively. Conclusions:The possibility survival of the illness is less than no illness. The existence of TB negative is higher than TB positive. In the machine learning model SVM provides better sensitivity with 87.96%, long short-term memory provides accuracy of 97.65%, precision of 77.35%, sensitivity of 87.93%, and F-score of 82.03%.

show abstract

Application of a long short-term memory neural network: a burgeoning method of deep learning in forecasting HIV incidence in Guangxi, China

Cited by 29 publications

References 33 publications

Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China

Comparison of ARIMA and LSTM in Forecasting the Incidence of HFMD Combined and Uncombined with Exogenous Meteorological Variables in Ningbo, China

Comparison of ARIMA, ES, GRNN and ARIMA–GRNN hybrid models to forecast the second wave of COVID-19 in India and the United States

Application of machine learning and deep learning for the prediction of HIV/AIDS

Contact Info

Product

Resources

About