Study on the influence of meteorological factors on influenza in different regions and predictions based on an LSTM algorithm

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.

The prediction of influenza-like illness using national influenza surveillance data and Baidu query data

BACKGROUND

Seasonal influenza and other respiratory tract infections are serious public health problems that need to be further addressed and investigated. Internet search data are recognized as a valuable source for forecasting influenza or other respiratory tract infection epidemics. However, the selection of internet search data and the application of forecasting methods are important for improving forecasting accuracy. The aim of the present study was to forecast influenza epidemics based on the long short-term memory neural network (LSTM) method, Baidu search index data, and the influenza-like-illness (ILI) rate.

METHODS

The official weekly ILI% data for northern and southern mainland China were obtained from the Chinese Influenza Center from 2018 to 2021. Based on the Baidu Index, search indices related to influenza infection over the corresponding time period were obtained. Pearson correlation analysis was performed to explore the association between influenza-related search queries and the ILI% of southern and northern mainland China. The LSTM model was used to forecast the influenza epidemic within the same week and at lags of 1-4 weeks. The model performance was assessed by evaluation metrics, including the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE).

RESULTS

In total, 24 search queries in northern mainland China and 7 search queries in southern mainland China were found to be correlated and were used to construct the LSTM model, which included the same week and a lag of 1-4 weeks. The LSTM model showed that ILI% + mask with one lag week and ILI% + influenza name were good prediction modules, with reduced RMSE predictions of 16.75% and 4.20%, respectively, compared with the estimated ILI% for northern and southern mainland China.

CONCLUSIONS

The results illuminate the feasibility of using an internet search index as a complementary data source for influenza forecasting and the efficiency of using the LSTM model to forecast influenza epidemics.

The role of meteorological factors on influenza incidence among children in Guangzhou China, 2019-2022

Objective

Analyzing the epidemiological characteristics of influenza cases among children aged 0-17 years in Guangzhou from 2019 to 2022. Assessing the relationships between multiple meteorological factors and influenza, improving the early warning systems for influenza, and providing a scientific basis for influenza prevention and control measures.

Methods

The influenza data were obtained from the Chinese Center for Disease Control and Prevention. Meteorological data were provided by Guangdong Meteorological Service. Spearman correlation analysis was conducted to examine the relevance between meteorological factors and the number of influenza cases. Distributed lag non-linear models (DLNM) were used to explore the effects of meteorological factors on influenza incidence.

Results

The relationship between mean temperature, rainfall, sunshine hours, and influenza cases presented a wavy pattern. The correlation between relative humidity and influenza cases was illustrated by a U-shaped curve. When the temperature dropped below 13°C, Relative risk (RR) increased sharply with decreasing temperature, peaking at 5.7°C with an RR of 83.78 (95% CI: 25.52, 275.09). The RR was increased when the relative humidity was below 66% or above 79%, and the highest RR was 7.50 (95% CI: 22.92, 19.25) at 99%. The RR was increased exponentially when the rainfall exceeded 1,625 mm, reaching a maximum value of 2566.29 (95% CI: 21.85, 3558574.07) at the highest rainfall levels. Both low and high sunshine hours were associated with reduced incidence of influenza, and the lowest RR was 0.20 (95% CI: 20.08, 0.49) at 9.4 h. No significant difference of the meteorological factors on influenza was observed between males and females. The impacts of cumulative extreme low temperature and low relative humidity on influenza among children aged 0-3 presented protective effects and the 0-3 years group had the lowest RRs of cumulative extreme high relative humidity and rainfall. The highest RRs of cumulative extreme effect of all meteorological factors (expect sunshine hours) were observed in the 7-12 years group.

Conclusion

Temperature, relative humidity, rainfall, and sunshine hours can be used as important predictors of influenza in children to improve the early warning system of influenza. Extreme weather reduces the risk of influenza in the age group of 0-3 years, but significantly increases the risk for those aged 7-12 years.

Spatiotemporal effects of meteorological conditions on global influenza peaks

BACKGROUND

Numerous studies have suggested that meteorological conditions such as temperature and absolute humidity are highly indicative of influenza outbreaks. However, the explanatory power of meteorological factors on the seasonal influenza peaks varied widely between countries at different latitudes.

OBJECTIVES

We aimed to explore the modification effects of meteorological factors on the seasonal influenza peaks in multi-countries.

METHODS

Data on influenza positive rate (IPR) were collected across 57 countries and data on meteorological factors were collected from ECMWF Reanalysis v5 (ERA5). We used linear regression and generalized additive models to investigate the spatiotemporal associations between meteorological conditions and influenza peaks in cold and warm seasons.

RESULTS

Influenza peaks were significantly correlated with months with both lower and higher temperatures. In temperate countries, the average intensity of cold season peaks was stronger than that of warm season peaks. However, the average intensity of warm season peaks was stronfger than of cold season peaks in tropical countries. Temperature and specific humidity had synergistic effects on influenza peaks at different latitudes, stronger in temperate countries (cold season: R2=0.90; warm season: R2=0.84) and weaker in tropical countries (cold season: R2=0.64; warm season: R2=0.03). Furthermore, the effects could be divided into cold-dry and warm-humid modes. The temperature transition threshold between the two modes was 16.5-19.5 °C. During the transition from cold-dry mode to warm-humid mode, the average 2 m specific humidity increased by 2.15 times, illustrating that transporting a large amount of water vapor may compensate for the negative effect of rising temperatures on the spread of the influenza virus.

CONCLUSION

Differences in the global influenza peaks were related to the synergistic influence of temperature and specific humidity. The global influenza peaks could be divided into cold-dry and warm-humid modes, and specific thresholds of meteorological conditions were needed for the transition of the two modes.

Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China

BACKGROUND

Influenza is an acute respiratory infectious disease that is highly infectious and seriously damages human health. Reasonable prediction is of great significance to control the epidemic of influenza.

METHODS

Our Influenza data were extracted from Shanxi Provincial Center for Disease Control and Prevention. Seasonal-trend decomposition using Loess (STL) was adopted to analyze the season characteristics of the influenza in Shanxi Province, China, from the 1st week in 2010 to the 52nd week in 2019. To handle the insufficient prediction performance of the seasonal autoregressive integrated moving average (SARIMA) model in predicting the nonlinear parts and the poor accuracy of directly predicting the original sequence, this study established the SARIMA model, the combination model of SARIMA and Long-Short Term Memory neural network (SARIMA-LSTM) and the combination model of SARIMA-LSTM based on Singular spectrum analysis (SSA-SARIMA-LSTM) to make predictions and identify the best model. Additionally, the Mean Squared Error (MSE), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) were used to evaluate the performance of the models.

RESULTS

The influenza time series in Shanxi Province from the 1st week in 2010 to the 52nd week in 2019 showed a year-by-year decrease with obvious seasonal characteristics. The peak period of the disease mainly concentrated from the end of the year to the beginning of the next year. The best fitting and prediction performance was the SSA-SARIMA-LSTM model. Compared with the SARIMA model, the MSE, MAE and RMSE of the SSA-SARIMA-LSTM model decreased by 38.12, 17.39 and 21.34%, respectively, in fitting performance; the MSE, MAE and RMSE decreased by 42.41, 18.69 and 24.11%, respectively, in prediction performances. Furthermore, compared with the SARIMA-LSTM model, the MSE, MAE and RMSE of the SSA-SARIMA-LSTM model decreased by 28.26, 14.61 and 15.30%, respectively, in fitting performance; the MSE, MAE and RMSE decreased by 36.99, 7.22 and 20.62%, respectively, in prediction performances.

CONCLUSIONS

The fitting and prediction performances of the SSA-SARIMA-LSTM model were better than those of the SARIMA and the SARIMA-LSTM models. Generally speaking, we can apply the SSA-SARIMA-LSTM model to the prediction of influenza, and offer a leg-up for public policy.