Construction and evaluation of two computational models for predicting the incidence of influenza in Nagasaki Prefecture, Japan

Convolutional LSTM-LSTM model for predicting the daily number of influenza patients in South Korea using satellite images

OBJECTIVES

Influenza affects a considerable proportion of the global population each year, and meteorological conditions may have a significant impact on its transmission. In this study, we aimed to develop a prediction model for the number of influenza patients at the national level using satellite images and provide a basis for predicting influenza through satellite image data.

STUDY DESIGN

We developed an influenza incidence prediction model using satellite images and influenza patient data.

METHODS

We collected satellite images and daily influenza patient data from July 2014 to June 2019 and developed a convolutional long short-term memory (LSTM)-LSTM neural network model. The model with the lowest average of mean absolute error (MAE) was selected.

RESULTS

The final model showed a high correlation between the predicted and actual number of influenza patients, with an average MAE of 5.9010 per million population. The model performed best with a 2-week time sequence.

CONCLUSIONS

We developed a national-level prediction model using satellite images to predict influenza incidence. The model offers the advantage of nationwide analysis. These results may reduce the burden of influenza by enabling timely public health interventions.

Retrospective analysis and time series forecasting with automated machine learning of ascariasis, enterobiasis and cystic echinococcosis in Romania

The epidemiology of neglected tropical diseases (NTD) is persistently underprioritized, despite NTD being widespread among the poorest populations and in the least developed countries on earth. This situation necessitates thorough and efficient public health intervention. Romania is at the brink of becoming a developed country. However, this South-Eastern European country appears to be a region that is susceptible to an underestimated burden of parasitic diseases despite recent public health reforms. Moreover, there is an evident lack of new epidemiologic data on NTD after Romania's accession to the European Union (EU) in 2007. Using the national ICD-10 dataset for hospitalized patients in Romania, we generated time series datasets for 2008-2018. The objective was to gain deep understanding of the epidemiological distribution of three selected and highly endemic parasitic diseases, namely, ascariasis, enterobiasis and cystic echinococcosis (CE), during this period and forecast their courses for the ensuing two years. Through descriptive and inferential analysis, we observed a decline in case numbers for all three NTD. Several distributional particularities at regional level emerged. Furthermore, we performed predictions using a novel automated time series (AutoTS) machine learning tool and could interestingly show a stable course for these parasitic NTD. Such predictions can help public health officials and medical organizations to implement targeted disease prevention and control. To our knowledge, this is the first study involving a retrospective analysis of ascariasis, enterobiasis and CE on a nationwide scale in Romania. It is also the first to use AutoTS technology for parasitic NTD.

A Bidirectional Long Short-Term Memory Model Algorithm for Predicting COVID-19 in Gulf Countries

Accurate prediction models have become the first goal for aiding pandemic-related decisions. Modeling and predicting the number of new active cases and deaths are important steps for anticipating and controlling COVID-19 outbreaks. The aim of this research was to develop an accurate prediction system for the COVID-19 pandemic that can predict the numbers of active cases and deaths in the Gulf countries of Saudi Arabia, Oman, the United Arab Emirates (UAE), Kuwait, Bahrain, and Qatar. The novelty of the proposed approach is that it uses an advanced prediction model—the bidirectional long short-term memory (Bi-LSTM) network deep learning model. The datasets were collected from an available repository containing updated registered cases of COVID-19 and showing the global numbers of active COVID-19 cases and deaths. Statistical analyses (e.g., mean square error, root mean square error, mean absolute error, and Spearman’s correlation coefficient) were employed to evaluate the results of the adopted Bi-LSTM model. The Bi-LSTM results based on the correlation metric gave predicted confirmed COVID-19 cases of 99.67%, 99.34%, 99.94%, 99.64%, 98.95%, and 99.91% for Saudi Arabia, Oman, the UAE, Kuwait, Bahrain, and Qatar, respectively, while testing the Bi-LSTM model for predicting COVID-19 mortality gave accuracies of 99.87%, 97.09%, 99.53%, 98.71%, 95.62%, and 99%, respectively. The Bi-LSTM model showed significant results using the correlation metric. Overall, the Bi-LSTM model demonstrated significant success in predicting COVID-19. The Bi-LSTM-based deep learning network achieves optimal prediction results and is effective and robust for predicting the numbers of active cases and deaths from COVID-19 in the studied Gulf countries.

Toward the accurate estimation of elliptical side orifice discharge coefficient applying two rigorous kernel-based data-intelligence paradigms

In the present study, two kernel-based data-intelligence paradigms, namely, Gaussian Process Regression (GPR) and Kernel Extreme Learning Machine (KELM) along with Generalized Regression Neural Network (GRNN) and Response Surface Methodology (RSM), as the validated schemes, employed to precisely estimate the elliptical side orifice discharge coefficient in rectangular channels. A total of 588 laboratory data in various geometric and hydraulic conditions were used to develop the models. The discharge coefficient was considered as a function of five dimensionless hydraulically and geometrical variables. The results showed that the machine learning models used in this study had shown good performance compared to the regression-based relationships. Comparison between machine learning models showed that GPR (RMSE = 0.0081, R = 0.958, MAPE = 1.3242) and KELM (RMSE = 0.0082, R = 0.9564, MAPE = 1.3499) models provide higher accuracy. Base on the RSM model, a new practical equation was developed to predict the discharge coefficient. Also, the sensitivity analysis of the input parameters showed that the main channel width to orifice height ratio (B/b) has the most significant effect on determining the discharge coefficient. The leveraged approach was applied to identify outlier data and applicability domain.

Estimating the Long-Term Epidemiological Trends and Seasonality of Hemorrhagic Fever with Renal Syndrome in China

OBJECTIVE

We aim to examine the adequacy of an innovation state-space modeling framework (called TBATS) in forecasting the long-term epidemic seasonality and trends of hemorrhagic fever with renal syndrome (HFRS).

METHODS

The HFRS morbidity data from January 1995 to December 2020 were taken, and subsequently, the data were split into six different training and testing segments (including 12, 24, 36, 60, 84, and 108 holdout monthly data) to investigate its predictive ability of the TBATS method, and its forecasting performance was compared with the seasonal autoregressive integrated moving average (SARIMA).

RESULTS

The TBATS (0.27, {0,0}, -, {<12,4>}) and SARIMA (0,1,(1,3))(0,1,1)12 were selected as the best TBATS and SARIMA methods, respectively, for the 12-step ahead prediction. The mean absolute deviation, root mean square error, mean absolute percentage error, mean error rate, and root mean square percentage error were 91.799, 14.772, 123.653, 0.129, and 0.193, respectively, for the preferred TBATS method and were 144.734, 25.049, 161.671, 0.203, and 0.296, respectively, for the preferred SARIMA method. Likewise, for the 24-, 36-, 60-, 84-, and 108-step ahead predictions, the preferred TBATS methods produced smaller forecasting errors over the best SARIMA methods. Further validations also suggested that the TBATS model outperformed the Error-Trend-Seasonal framework, with little exception. HFRS had dual seasonal behaviors, peaking in May-June and November-December. Overall a notable decrease in the HFRS morbidity was seen during the study period (average annual percentage change=-6.767, 95% confidence intervals: -10.592 to -2.778), and yet different stages had different variation trends. Besides, the TBATS model predicted a plateau in the HFRS morbidity in the next ten years.

CONCLUSION

The TBATS approach outperforms the SARIMA approach in estimating the long-term epidemic seasonality and trends of HFRS, which is capable of being deemed as a promising alternative to help stakeholders to inform future preventive policy or practical solutions to tackle the evolving scenarios.

A Deep Neural Network-Based Method for Prediction of Dementia Using Big Data

The rise in dementia among the aging Korean population will quickly create a financial burden on society, but timely recognition of early warning for dementia and proper responses to the occurrence of dementia can enhance medical treatment. Health behavior and medical service usage data are relatively more accessible than clinical data, and a prescreening tool with easily accessible data could be a good solution for dementia-related problems. In this paper, we apply a deep neural network (DNN) to prediction of dementia using health behavior and medical service usage data, using data from 7031 subjects aged over 65 collected from the Korea National Health and Nutrition Examination Survey (KNHANES) in 2001 and 2005. In the proposed model, principal component analysis (PCA) featuring and min/max scaling are used to preprocess and extract relevant background features. We compared our proposed methodology, a DNN/scaled PCA, with five well-known machine learning algorithms. The proposed methodology shows 85.5% of the area under the curve (AUC), a better result than that using other algorithms. The proposed early prescreening method for possible dementia can be used by both patients and doctors.

Use of meteorological parameters for forecasting scarlet fever morbidity in Tianjin, Northern China

The scarlet fever incidence has increased drastically in recent years in China. However, the long-term relationship between climate variation and scarlet fever remains contradictory, and an early detection system is lacking. In this study, we aim to explore the potential long-term effects of variations in monthly climatic parameters on scarlet fever and to develop an early scarlet-fever detection tool. Data comprising monthly scarlet fever cases and monthly average climatic variables from 2004 to 2017 were retrieved from the Notifiable Infectious Disease Surveillance System and National Meteorological Science Center, respectively. We used a negative binomial multivariable regression to assess the long-term impacts of weather parameters on scarlet fever and then built a novel forecasting technique by integrating an autoregressive distributed lag (ARDL) method with a nonlinear autoregressive neural network (NARNN) based on the significant meteorological drivers. Scarlet fever was a seasonal disease that predominantly peaked in spring and winter. The regression results indicated that a 1 °C increment in the monthly average temperature and a 1-h increment in the monthly aggregate sunshine hours were associated with 17.578% (95% CI 7.674 to 28.393%) and 0.529% (95% CI 0.035 to 1.025%) increases in scarlet fever cases, respectively; a 1-hPa increase in the average atmospheric pressure at a 1-month lag was associated with 12.996% (95% CI 9.972 to 15.919%) decrements in scarlet fever cases. Based on the model evaluation criteria, the best-performing basic and combined approaches were ARDL(1,0,0,1) and ARDL(1,0,0,1)-NARNN(5, 22), respectively, and this hybrid approach comprised smaller performance measures in both the training and testing stages than those of the basic model. Climate variability has a significant long-term influence on scarlet fever. The ARDL-NARNN technique with the incorporation of meteorological drivers can be used to forecast the future epidemic trends of scarlet fever. These findings may be of great help for the prevention and control of scarlet fever.

A framework for the risk prediction of avian influenza occurrence: An Indonesian case study

Avian influenza viruses can cause economically devastating diseases in poultry and have the potential for zoonotic transmission. To mitigate the consequences of avian influenza, disease prediction systems have become increasingly important. In this study, we have proposed a framework for the prediction of the occurrence and spread of avian influenza events in a geographical area. The application of the proposed framework was examined in an Indonesian case study. An extensive list of historical data sources containing disease predictors and target variables was used to build spatiotemporal and transactional datasets. To combine disparate sources, data rows were scaled to a temporal scale of 1-week and a spatial scale of 1-degree × 1-degree cells. Given the constructed datasets, underlying patterns in the form of rules explaining the risk of occurrence and spread of avian influenza were discovered. The created rules were combined and ordered based on their importance and then stored in a knowledge base. The results suggested that the proposed framework could act as a tool to gain a broad understanding of the drivers of avian influenza epidemics and may facilitate the prediction of future disease events.

Interactive Analysis of Epidemic Situations Based on a Spatiotemporal Information Knowledge Graph of COVID-19

In view of the lack of data association in spatiotemporal information analysis and the lack of spatiotemporal situation analysis in knowledge graphs, this article combines the semantic web of the geographic knowledge graph with the visual analysis model of spatial information and puts forward the comprehensive utilization of the related technologies of the geographic knowledge graph and big data visual analysis. Then, it realizes the situational analysis of COVID-19 (Coronavirus Disease 2019) and the exploration of patient relationships through interactive collaborative analysis. The main contributions of the paper are as follows. (1) Based on the characteristics of the geographic knowledge graph, a patient entity model and an entity relationship type and knowledge representation method are proposed, and a knowledge graph of the spatiotemporal information of COVID-19 is constructed. (2) To analyse the COVID-19 patients' situations and explore their relationships, an analytical framework is designed. The framework, combining the semantic web of the geographic knowledge graph and the visual analysis model of geographic information, allows one to analyse the semantic web by using the node attribute similarity calculation, key stage mining, community prediction and other methods. (3)An efficient epidemic prevention and anti-epidemic method is proposed which is of referential significance. It is based on experiments and the collaborative analysis of the semantic web and spatial information, allowing for real-time situational understanding, the discovery of patients' relationships, the analysis of the spatiotemporal distribution of patients, super spreader mining, key node analysis, and the prevention and control of high-risk groups.

Estimating the Prevalence and Mortality of Coronavirus Disease 2019 (COVID-19) in the USA, the UK, Russia, and India

Objective

The aim of this study is to apply the advanced error-trend-seasonal (ETS) framework to forecast the prevalence and mortality series of COVID-19 in the USA, the UK, Russia, and India, and the predictive performance of the ETS framework was compared with the most frequently used autoregressive integrated moving average (ARIMA) model.

Materials and Methods

The prevalence and mortality data of COVID-19 in the USA, the UK, Russia, and India between 20 February 2020 and 15 May 2020 were extracted from the WHO website. Then, the data subsamples between 20 February 2020 and 3 May 2020 were treated as the training horizon, and the others were used as the testing horizon to construct the ARIMA models and the ETS models.

Results

Based on the model evaluation criteria, the ARIMA (0,2,1) and ETS (M,MD,N), sparse coefficient ARIMA (0,2,(1,6)) and ETS (A,AD,M), ARIMA (1,1,1) and ETS (A,MD,A), together with ARIMA (2,2,1) and ETS (A,M,A) specifications were identified as the preferred ARIMA and ETS models for the prevalence data in the USA, the UK, Russia, and India, respectively; the ARIMA (0,2,1) and ETS (M,A,M), ARIMA (0,2,1) and ETS (M,A,N), ARIMA (0,2,1) and ETS (A,A,N), coupled with ARIMA (0,2,2) and ETS (M,M,N) specifications were selected as the optimal ARIMA and ETS models for the mortality data in these four countries, respectively. Among these best-fitting models, the ETS models produced smaller forecasting error rates than the ARIMA models in all the datasets.

Conclusion

The ETS framework can be used to nowcast and forecast the long-term temporal trends of the COVID-19 prevalence and mortality in the USA, the UK, Russia, and India, and which provides a notable performance improvement over the most frequently used ARIMA model. Our findings can aid governments as a reference to prepare for and respond to the COVID-19 pandemic both in restricting the transmission of the disease and in lowering the disease-related deaths in the upcoming days.

The Probability of Ischaemic Stroke Prediction with a Multi-Neural-Network Model

As is known, cerebral stroke has become one of the main diseases endangering people’s health; ischaemic strokes accounts for approximately 85% of cerebral strokes. According to research, early prediction and prevention can effectively reduce the incidence rate of the disease. However, it is difficult to predict the ischaemic stroke because the data related to the disease are multi-modal. To achieve high accuracy of prediction and combine the stroke risk predictors obtained by previous researchers, a method for predicting the probability of stroke occurrence based on a multi-model fusion convolutional neural network structure is proposed. In such a way, the accuracy of ischaemic stroke prediction is improved by processing multi-modal data through multiple end-to-end neural networks. In this method, the feature extraction of structured data (age, gender, history of hypertension, etc.) and streaming data (heart rate, blood pressure, etc.) based on a convolutional neural network is first realized. A neural network model for feature fusion is then constructed to realize the feature fusion of structured data and streaming data. Finally, a predictive model for predicting the probability of stroke is obtained by training. As shown in the experimental results, the accuracy of ischaemic stroke prediction reached 98.53%. Such a high prediction accuracy will be helpful for preventing the occurrence of stroke.

Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database

The application of machine learning (ML) for use in generating insights and making predictions on new records continues to expand within the medical community. Despite this progress to date, the application of time series analysis has remained underexplored due to complexity of the underlying techniques. In this study, we have deployed a novel ML, called automated time series (AutoTS) machine learning, to automate data processing and the application of a multitude of models to assess which best forecasts future values. This rapid experimentation allows for and enables the selection of the most accurate model in order to perform time series predictions. By using the nation-wide ICD-10 (International Classification of Diseases, Tenth Revision) dataset of hospitalized patients of Romania, we have generated time series datasets over the period of 2008–2018 and performed highly accurate AutoTS predictions for the ten deadliest diseases. Forecast results for the years 2019 and 2020 were generated on a NUTS 2 (Nomenclature of Territorial Units for Statistics) regional level. This is the first study to our knowledge to perform time series forecasting of multiple diseases at a regional level using automated time series machine learning on a national ICD-10 dataset. The deployment of AutoTS technology can help decision makers in implementing targeted national health policies more efficiently.

Multiscaled Neural Autoregressive Distributed Lag: A New Empirical Mode Decomposition Model for Nonlinear Time Series Forecasting

Forecasting has always been the cornerstone of machine learning and statistics. Despite the great evolution of the time series theory, forecasters are still in the hunt for better models to make more accurate decisions. The huge advances in neural networks over the last years has led to the emergence of a new generation of effective models replacing classic econometric models. It is in this direction that we propose, in this paper, a new multiscaled Feedforward Neural Network (FNN), with the aim of forecasting multivariate time series. This new model, called Empirical Mode Decomposition (EMD)-based Neural ARDL, is inspired from the well-known Autoregressive Distributed Lag (ARDL) model being our proposal founded upon the concepts of nonlinearity, EMD-multiresolution and neural networks. These features give the model the ability to effectively capture many nonlinear patterns like the ones often present in econophysical time series, such as nonlinear trends, seasonal effects, long-range dependency, etc. The proposed algorithm can be summarized into the following four basic tasks: (i) EMD breaking-down multivariate time series into different resolution levels, (ii) feeding EMD components from the same levels into a number of feedforward neural ARDL models, (iii) from one level to the next, extrapolating the component corresponding to the response variable (scalar output) a number of steps ahead, and finally, (iv) recombining level-by-level forecasts into a single output. An optimal learning scheme is rigorously designed for efficiently training the new proposed architecture. The approach is finally tested and compared to a number of powerful benchmark models, where experiments are conducted on real-world data.

Association Between Seasonal Influenza and Absolute Humidity: Time-Series Analysis with Daily Surveillance Data in Japan

Seasonal influenza epidemics are associated with various meteorological factors. Recently absolute humidity (AH) has garnered attention, and some epidemiological studies show an association between AH and human influenza infection. However, they mainly analyzed weekly surveillance data, and daily data remains largely unexplored despite its potential benefits. In this study, we analyze daily influenza surveillance data using a distributed lag non-linear model to examine the association of AH with the number of influenza cases and the magnitude of the association. Additionally, we investigate how adjustment for seasonality and autocorrelation in the model affect results. All models used in the study showed a significant increase in the number of influenza cases as AH decreased, although the magnitude of the association differed substantially by model. Furthermore, we found that relative risk reached a peak at lag 10–14 with extremely low AH. To verify these findings, further analysis should be conducted using data from other locations.

Spatial-temporal distribution of human brucellosis in mainland China from 2004 to 2017 and an analysis of social and environmental factors

Background

This study aimed to describe the changing distribution of human brucellosis between 2004 and 2017 in mainland China and seek scientific evidence of the relationship between socio-economic, environmental, and ecological factors and human brucellosis incidence.

Methods

The annual numbers of brucellosis cases and incidence rates from 31 provinces in mainland China between 2004 and 2017 were obtained from the Data-Center for China Public Health Science. The number of monthly brucellosis cases in 2018 was obtained from the Chinese Center for Disease Control and Prevention. The electronic map of the People’s Republic of China was downloaded from the National Earth System Science Data Sharing Platform. Human population density, gross domestic product (GDP), and an inventory of cattle and sheep at the end of each year from 2004 to 2017 were obtained from the National Bureau of Statistics of China. Annual rainfall data from 31 provinces in the People’s Republic of China from 2004 to 2017 were collected from the China Meteorological Data Service Center. The risk distribution and changing trends of human brucellosis were mapped with ArcGIS. A cluster analysis was employed to identify geographical areas and periods with statistically significant incidence rates. Multivariate linear regression was used to determine possible factors that were significantly correlated with the presence of human brucellosis cases.

Results

Human brucellosis cases have spread throughout the whole country. Human brucellosis cases occurred mostly from March to August and were concentrated from April to July. The inventory of sheep, GDP, and climate were significantly correlated with the presence of brucellosis cases in mainland China.

Conclusions

The geographical expansion of human brucellosis in mainland China was observed, so did the high-incidence clusters between 2004 and 2017. Most of the cases were reported during the early spring to early summer (February–August). Results from the multivariate linear regression suggested that the inventory of sheep, GDP, and climate were significantly associated with the incidence of human brucellosis in mainland China.

Temporal trends analysis of tuberculosis morbidity in mainland China from 1997 to 2025 using a new SARIMA-NARNNX hybrid model

OBJECTIVE

Tuberculosis (TB) remains a major deadly threat in mainland China. Early warning and advanced response systems play a central role in addressing such a wide-ranging threat. The purpose of this study is to establish a new hybrid model combining a seasonal autoregressive integrated moving average (SARIMA) model and a non-linear autoregressive neural network with exogenous input (NARNNX) model to understand the future epidemiological patterns of TB morbidity.

METHODS

We develop a SARIMA-NARNNX hybrid model for forecasting future levels of TB incidence based on data containing 255 observations from January 1997 to March 2018 in mainland China, and the ultimate simulating and forecasting performances were compared with the basic SARIMA, non-linear autoregressive neural network (NARNN) and error-trend-seasonal (ETS) approaches, as well as the SARIMA-generalised regression neural network (GRNN) and SARIMA-NARNN hybrid techniques.

RESULTS

In terms of the root mean square error, mean absolute error, mean error rate and mean absolute percentage error, the identified best-fitting SARIMA-NARNNX combined model with 17 hidden neurons and 4 feedback delays had smaller values in both in-sample simulating scheme and the out-of-sample forecasting scheme than the preferred single SARIMA(2,1,3)(0,1,1)₁₂ model, a NARNN with 19 hidden neurons and 6 feedback delays and ETS(M,A,A), and the best-performing SARIMA-GRNN and SARIMA-NARNN models with 32 hidden neurons and 6 feedback delays. Every year, there was an obvious high-risk season for the notified TB cases in March and April. Importantly, the epidemic levels of TB from 2006 to 2017 trended slightly downward. According to the projection results from 2018 to 2025, TB incidence will continue to drop by 3.002% annually but will remain high.

CONCLUSIONS

The new SARIMA-NARNNX combined model visibly outperforms the other methods. This hybrid model should be used for forecasting the long-term epidemic patterns of TB, and it may serve as a beneficial and effective tool for controlling this disease.

Development and evaluation of a deep learning approach for modeling seasonality and trends in hand-foot-mouth disease incidence in mainland China

The high incidence, seasonal pattern and frequent outbreaks of hand, foot, and mouth disease (HFMD) represent a threat for millions of children in mainland China. And advanced response is being used to address this. Here, we aimed to model time series with a long short-term memory (LSTM) based on the HFMD notified data from June 2008 to June 2018 and the ultimate performance was compared with the autoregressive integrated moving average (ARIMA) and nonlinear auto-regressive neural network (NAR). The results indicated that the identified best-fitting LSTM with the better superiority, be it in modeling dataset or two robustness tests dataset, than the best-conducting NAR and seasonal ARIMA (SARIMA) methods in forecasting performances, including the minimum indices of root mean square error, mean absolute error and mean absolute percentage error. The epidemic trends of HFMD remained stable during the study period, but the reported cases were even at significantly high levels with a notable high-risk seasonality in summer, and the incident cases projected by the LSTM would still be fairly high with a slightly upward trend in the future. In this regard, the LSTM approach should be highlighted in forecasting the epidemics of HFMD, and therefore assisting decision makers in making efficient decisions derived from the early detection of the disease incidents.

The Use of Deep Learning to Predict Stroke Patient Mortality

The increase in stroke incidence with the aging of the Korean population will rapidly impose an economic burden on society. Timely treatment can improve stroke prognosis. Awareness of stroke warning signs and appropriate actions in the event of a stroke improve outcomes. Medical service use and health behavior data are easier to collect than medical imaging data. Here, we used a deep neural network to detect stroke using medical service use and health behavior data; we identified 15,099 patients with stroke. Principal component analysis (PCA) featuring quantile scaling was used to extract relevant background features from medical records; we used these to predict stroke. We compared our method (a scaled PCA/deep neural network [DNN] approach) to five other machine-learning methods. The area under the curve (AUC) value of our method was 83.48%; hence; it can be used by both patients and doctors to prescreen for possible stroke.

Application of a hybrid model in predicting the incidence of tuberculosis in a Chinese population

Objective: To investigate suitable forecasting models for tuberculosis (TB) in a Chinese population by comparing the predictive value of the autoregressive integrated moving average (ARIMA) model and the ARIMA-generalized regression neural network (GRNN) hybrid model. Methods: We used the monthly incidence rate of TB in Lianyungang city from January 2007 through June 2016 to construct a fitting model, and we used the incidence rate from July 2016 to December 2016 to evaluate the forecasting accuracy. The root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and mean error rate (MER) were used to assess the performance of these models in fitting and forecasting the incidence of TB. Results: The ARIMA (10, 1, 0) (0, 1, 1)₁₂ model was selected from plausible ARIMA models, and the optimal spread value of the ARIMA-GRNN hybrid model was 0.23. For the fitting dataset, the RMSE, MAPE, MAE and MER were 0.5594, 11.5000, 0.4202 and 0.1132, respectively, for the ARIMA (10, 1, 0) (0, 1, 1)₁₂ model, and 0.5259, 11.2181, 0.3992 and 0.1075, respectively, for the ARIMA-GRNN hybrid model. For the forecasting dataset, the RMSE, MAPE, MAE and MER were 0.2805, 8.8797, 0.2261 and 0.0851, respectively, for the ARIMA (10, 1, 0) (0, 1, 1)₁₂ model, and 0.2553, 5.7222, 0.1519 and 0.0571, respectively, for the ARIMA-GRNN hybrid model. Conclusions: The ARIMA-GRNN hybrid model was shown to be superior to the single ARIMA model in predicting the short-term TB incidence in the Chinese population, especially in fitting and forecasting the peak and trough incidence.

Seasonality and trend prediction of scarlet fever incidence in mainland China from 2004 to 2018 using a hybrid SARIMA-NARX model

Background

Scarlet fever is recognized as being a major public health issue owing to its increase in notifications in mainland China, and an advanced response based on forecasting techniques is being adopted to tackle this. Here, we construct a new hybrid method incorporating seasonal autoregressive integrated moving average (SARIMA) with a nonlinear autoregressive with external input(NARX) to analyze its seasonality and trend in order to efficiently prevent and control this re-emerging disease.

Methods

Four statistical models, including a basic SARIMA, basic nonlinear autoregressive (NAR) method, traditional SARIMA-NAR and new SARIMA-NARX hybrid approaches, were developed based on scarlet fever incidence data between January 2004 and July 2018 to evaluate its temporal patterns, and their mimic and predictive capacities were compared to discover the optimal using the mean absolute percentage error, root mean square error, mean error rate, and root mean square percentage error.

Results

The four preferred models identified were comprised of the SARIMA(0,1,0)(0,1,1)₁₂, NAR with 14 hidden neurons and five delays, SARIMA-NAR with 33 hidden neurons and five delays, and SARIMA-NARX with 16 hidden neurons and 4 delays. Among which presenting the lowest values of the aforementioned indices in both simulation and prediction horizons is the SARIMA-NARX method. Analyses from the data suggested that scarlet fever was a seasonal disease with predominant peaks of summer and winter and a substantial rising trend in the scarlet fever notifications was observed with an acceleration of 9.641% annually, particularly since 2011 with 12.869%, and moreover such a trend will be projected to continue in the coming year.

Conclusions

The SARIMA-NARX technique has the promising ability to better consider both linearity and non-linearity behind scarlet fever data than the others, which significantly facilitates its prevention and intervention of scarlet fever. Besides, under current trend of ongoing resurgence, specific strategies and countermeasures should be formulated to target scarlet fever.

Temporal trends analysis of human brucellosis incidence in mainland China from 2004 to 2018

With the re-emergence of brucellosis in mainland China since the mid-1990s, an increasing threat to public health tends to become even more violent, advanced warning plays a pivotal role in the control of brucellosis. However, a model integrating the autoregressive integrated moving average (ARIMA) with Error-Trend-Seasonal (ETS) methods remains unexplored in the epidemiological prediction. The hybrid ARIMA-ETS model based on discrete wavelet transform was hence constructed to assess the epidemics of human brucellosis from January 2004 to February 2018 in mainland China. The preferred hybrid model including the best-performing ARIMA method for approximation-forecasting and the best-fitting ETS approach for detail-forecasting is evidently superior to the standard ARIMA and ETS techniques in both three in-sample simulating and out-of-sample forecasting horizons in terms of the minimum performance indices of the root mean square error, mean absolute error, mean error rate and mean absolute percentage error. Whereafter, an ahead prediction from March to December in 2018 displays a dropping trend compared to the preceding years. But being still present, in various trends, in the present or future. This hybrid model can be highlighted in predicting the temporal trends of human brucellosis, which may act as the potential for far-reaching implications for prevention and control of this disease.

Predicting Infectious Disease Using Deep Learning and Big Data

Infectious disease occurs when a person is infected by a pathogen from another person or an animal. It is a problem that causes harm at both individual and macro scales. The Korea Center for Disease Control (KCDC) operates a surveillance system to minimize infectious disease contagions. However, in this system, it is difficult to immediately act against infectious disease because of missing and delayed reports. Moreover, infectious disease trends are not known, which means prediction is not easy. This study predicts infectious diseases by optimizing the parameters of deep learning algorithms while considering big data including social media data. The performance of the deep neural network (DNN) and long-short term memory (LSTM) learning models were compared with the autoregressive integrated moving average (ARIMA) when predicting three infectious diseases one week into the future. The results show that the DNN and LSTM models perform better than ARIMA. When predicting chickenpox, the top-10 DNN and LSTM models improved average performance by 24% and 19%, respectively. The DNN model performed stably and the LSTM model was more accurate when infectious disease was spreading. We believe that this study's models can help eliminate reporting delays in existing surveillance systems and, therefore, minimize costs to society.