1
|
Yang E, Zhang H, Guo X, Zang Z, Liu Z, Liu Y. A multivariate multi-step LSTM forecasting model for tuberculosis incidence with model explanation in Liaoning Province, China. BMC Infect Dis 2022; 22:490. [PMID: 35606725 PMCID: PMC9128107 DOI: 10.1186/s12879-022-07462-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2021] [Accepted: 05/10/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Tuberculosis (TB) is the respiratory infectious disease with the highest incidence in China. We aim to design a series of forecasting models and find the factors that affect the incidence of TB, thereby improving the accuracy of the incidence prediction. RESULTS In this paper, we developed a new interpretable prediction system based on the multivariate multi-step Long Short-Term Memory (LSTM) model and SHapley Additive exPlanation (SHAP) method. Four accuracy measures are introduced into the system: Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, and symmetric Mean Absolute Percentage Error. The Autoregressive Integrated Moving Average (ARIMA) model and seasonal ARIMA model are established. The multi-step ARIMA-LSTM model is proposed for the first time to examine the performance of each model in the short, medium, and long term, respectively. Compared with the ARIMA model, each error of the multivariate 2-step LSTM model is reduced by 12.92%, 15.94%, 15.97%, and 14.81% in the short term. The 3-step ARIMA-LSTM model achieved excellent performance, with each error decreased to 15.19%, 33.14%, 36.79%, and 29.76% in the medium and long term. We provide the local and global explanation of the multivariate single-step LSTM model in the field of incidence prediction, pioneering. CONCLUSIONS The multivariate 2-step LSTM model is suitable for short-term prediction and obtained a similar performance as previous studies. The 3-step ARIMA-LSTM model is appropriate for medium-to-long-term prediction and outperforms these models. The SHAP results indicate that the five most crucial features are maximum temperature, average relative humidity, local financial budget, monthly sunshine percentage, and sunshine hours.
Collapse
Affiliation(s)
- Enbin Yang
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China
| | - Hao Zhang
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China
- College of Software, Jilin University, Changchun, 130012 China
| | - Xinsheng Guo
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China
| | - Zinan Zang
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China
| | - Zhen Liu
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Graduate School of Engineering, Nagasaki Institute of Applied Science, 536 Aba-machi, Nagasaki, 851-0193 Japan
| | - Yuanning Liu
- College of Computer Science and Technology, Jilin University, Changchun, 130012 China
- Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012 China
- College of Software, Jilin University, Changchun, 130012 China
| |
Collapse
|
2
|
Guo Z, He K, Xiao D. Early warning of some notifiable infectious diseases in China by the artificial neural network. ROYAL SOCIETY OPEN SCIENCE 2020; 7:191420. [PMID: 32257314 PMCID: PMC7062078 DOI: 10.1098/rsos.191420] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/15/2019] [Accepted: 01/21/2020] [Indexed: 06/11/2023]
Abstract
In order to accurately grasp the timing for the prevention and control of diseases, we established an artificial neural network model to issue early warning signals. The real-time recurrent learning (RTRL) and extended Kalman filter (EKF) methods were performed to analyse four types of respiratory infectious diseases and four types of digestive tract infectious diseases in China to comprehensively determine the epidemic intensities and whether to issue early warning signals. The numbers of new confirmed cases per month between January 2004 and December 2017 were used as the training set; the data from 2018 were used as the test set. The results of RTRL showed that the number of new confirmed cases of respiratory infectious diseases in September 2018 increased abnormally. The results of the EKF showed that the number of new confirmed cases of respiratory infectious diseases increased abnormally in January and February of 2018. The results of these two algorithms showed that the number of new confirmed cases of digestive tract infectious diseases in the test set did not have any abnormal increases. The neural network and machine learning can further enrich and develop the early warning theory.
Collapse
Affiliation(s)
- Zuiyuan Guo
- Department of Disease Control, Center for Disease Control and Prevention in Northern Theater Command, Shenyang, People's Republic of China
| | - Kevin He
- Biostatistics Department, University of Michigan, Ann Arbor, MI 48109, USA
| | - Dan Xiao
- China National Clinical Research Center for Neurological Diseases, Beijing Tian Tan Hospital, No. 119, South 4th Ring Road West, Fengtai District, Beijing, People's Republic of China
| |
Collapse
|
3
|
Impact of meteorological factors on the incidence of bacillary dysentery in Beijing, China: A time series analysis (1970-2012). PLoS One 2017; 12:e0182937. [PMID: 28796834 PMCID: PMC5552134 DOI: 10.1371/journal.pone.0182937] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2017] [Accepted: 07/20/2017] [Indexed: 11/19/2022] Open
Abstract
Objectives Influence of meteorological variables on the transmission of bacillary dysentery (BD) is under investigated topic and effective forecasting models as public health tool are lacking. This paper aimed to quantify the relationship between meteorological variables and BD cases in Beijing and to establish an effective forecasting model. Methods A time series analysis was conducted in the Beijing area based upon monthly data on weather variables (i.e. temperature, rainfall, relative humidity, vapor pressure, and wind speed) and on the number of BD cases during the period 1970–2012. Autoregressive integrated moving average models with explanatory variables (ARIMAX) were built based on the data from 1970 to 2004. Prediction of monthly BD cases from 2005 to 2012 was made using the established models. The prediction accuracy was evaluated by the mean square error (MSE). Results Firstly, temperature with 2-month and 7-month lags and rainfall with 12-month lag were found positively correlated with the number of BD cases in Beijing. Secondly, ARIMAX model with covariates of temperature with 7-month lag (β = 0.021, 95% confidence interval(CI): 0.004–0.038) and rainfall with 12-month lag (β = 0.023, 95% CI: 0.009–0.037) displayed the highest prediction accuracy. Conclusions The ARIMAX model developed in this study showed an accurate goodness of fit and precise prediction accuracy in the short term, which would be beneficial for government departments to take early public health measures to prevent and control possible BD popularity.
Collapse
|
4
|
Zhao D, Wang L, Cheng J, Xu J, Xu Z, Xie M, Yang H, Li K, Wen L, Wang X, Zhang H, Wang S, Su H. Impact of weather factors on hand, foot and mouth disease, and its role in short-term incidence trend forecast in Huainan City, Anhui Province. INTERNATIONAL JOURNAL OF BIOMETEOROLOGY 2017; 61:453-461. [PMID: 27557791 DOI: 10.1007/s00484-016-1225-9] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/28/2015] [Revised: 07/28/2016] [Accepted: 07/30/2016] [Indexed: 05/04/2023]
Abstract
Hand, foot, and mouth disease (HFMD) is one of the most common communicable diseases in China, and current climate change had been recognized as a significant contributor. Nevertheless, no reliable models have been put forward to predict the dynamics of HFMD cases based on short-term weather variations. The present study aimed to examine the association between weather factors and HFMD, and to explore the accuracy of seasonal auto-regressive integrated moving average (SARIMA) model with local weather conditions in forecasting HFMD. Weather and HFMD data from 2009 to 2014 in Huainan, China, were used. Poisson regression model combined with a distributed lag non-linear model (DLNM) was applied to examine the relationship between weather factors and HFMD. The forecasting model for HFMD was performed by using the SARIMA model. The results showed that temperature rise was significantly associated with an elevated risk of HFMD. Yet, no correlations between relative humidity, barometric pressure and rainfall, and HFMD were observed. SARIMA models with temperature variable fitted HFMD data better than the model without it (sR 2 increased, while the BIC decreased), and the SARIMA (0, 1, 1)(0, 1, 0)52 offered the best fit for HFMD data. In addition, compared with females and nursery children, males and scattered children may be more suitable for using SARIMA model to predict the number of HFMD cases and it has high precision. In conclusion, high temperature could increase the risk of contracting HFMD. SARIMA model with temperature variable can effectively improve its forecast accuracy, which can provide valuable information for the policy makers and public health to construct a best-fitting model and optimize HFMD prevention.
Collapse
Affiliation(s)
- Desheng Zhao
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Lulu Wang
- School of Nursing, Anhui Medical University, Hefei, Anhui, China
| | - Jian Cheng
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Jun Xu
- Department of Clinical Laboratory, the Affiliated Provincial Hospital of Anhui Medical University, Hefei, Anhui, China
| | - Zhiwei Xu
- School of Public Health and Social Work & Institute of Health and Biomedical Innovation, Queensland University of Technology, Kelvin Grove, Brisbane, QLD, 4509, Australia
| | - Mingyu Xie
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Huihui Yang
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Kesheng Li
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Lingying Wen
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Xu Wang
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Heng Zhang
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Shusi Wang
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China
| | - Hong Su
- Department of Epidemiology and Health Statistics, School of Public Health, Anhui Medical University, 81 Meishan Road, Hefei, Anhui Province, 230032, China.
| |
Collapse
|