Meteorological factors and tick density affect the dynamics of SFTS in jiangsu province, China

Abstract

Background: This study aimed to explore whether the transmission routes of severe fever with thrombocytopenia syndrome (SFTS) will be affected by tick density and meteorological factors, and to explore the factors that affect the transmission of SFTS. We used the transmission dynamics model to calculate the transmission rate coefficients of different transmission routes of SFTS, and used the generalized additive model to uncover how meteorological factors and tick density affect the spread of SFTS.

Methods: In this study, the time-varying infection rate coefficients of different transmission routes of SFTS in Jiangsu Province from 2017 to 2020 were calculated based on the previous multi-population multi-route dynamic model (MMDM) of SFTS. The changes in transmission routes were summarized by collecting questionnaires from 537 SFTS cases in 2018-2020 in Jiangsu Province. The incidence rate of SFTS and the infection rate coefficients of different transmission routes were dependent variables, and month, meteorological factors and tick density were independent variables to establish a generalized additive model (GAM). The optimal GAM was selected using the generalized cross-validation score (GCV), and the model was validated by the 2016 data of Zhejiang Province and 2020 data of Jiangsu Province. The validated GAMs were used to predict the incidence and infection rate coefficients of SFTS in Jiangsu province in 2021, and also to predict the effect of extreme weather on SFTS.

Results: The number and proportion of infections by different transmission routes for each year and found that tick-to-human and human-to-human infections decreased yearly, but infections through animal and environmental transmission were gradually increasing. MMDM fitted well with the three-year SFTS incidence data (P<0.05). The best intervention to reduce the incidence of SFTS is to reduce the effective exposure of the population to the surroundings. Based on correlation tests, tick density was positively correlated with air temperature, wind speed, and sunshine duration. The best GAM was a model with tick transmissibility to humans as the dependent variable, without considering lagged effects (GCV = 5.9247E-22, R2 = 96%). Reported incidence increased when sunshine duration was higher than 11 h per day and decreased when temperatures were too high (>28°C). Sunshine duration and temperature had the greatest effect on transmission from host animals to humans. The effect of extreme weather conditions on SFTS was short-term, but there was no effect on SFTS after high temperature and sunshine hours.

Conclusions: Different factors affect the infection rate coefficients of different transmission routes. Sunshine duration, relative humidity, temperature and tick density are important factors affecting the occurrence of SFTS. Hurricanes reduce the incidence of SFTS in the short term, but have little effect in the long term. The most effective intervention to reduce the incidence of SFTS is to reduce population exposure to high-risk environments.

Fig 1. Study design of meteorological factors and tick density affect the SFTS transmission.

SD = Sunshine duration, RH = Relative humidity, AT = Average temperature, PRCP = 24-hour precipitation, WS = Wind speed, TD = Tick density, and GCV = generalized cross-validation score; GAM: Generalized additive model; MMDM: Multi-population and multi-route dynamic model of SFTS.

Fig 2. Land use map of each SFTS case location in Jiangsu Province from 2017 to 2019.

http://www.globallandcover.com/defaults.html?type=data&src=/Scripts/map/defaults/browse.html&head=browse&type=data (Map source).

Fig 3. MMDM fitting result of SFTS incidence of 2017–2019.

MMDM: Multi-population and multi-route dynamic model of SFTS.

Fig 4. Correlation analysis between no time lagging meteorological factors and tick density.

AP = Air pressure; SD = Sunshine duration; RH = Relative humidity; AT = Average temperature; PRCP = 24-hour precipitation; WS = Wind speed; TD = Tick density. Correlation coefficient (r) greater than 0.7 indicates a strong correlation between the two.

Fig 5. Correlation analysis between time lagging meteorological factors and tick density.

AP = Air pressure; SD = Sunshine duration; RH = Relative humidity; AT = Average temperature; PRCP = 24-hour precipitation; WS = Wind speed; TD = Tick density. Correlation coefficient (r) greater than 0.7 indicates a strong correlation between the two.

Fig 6. Non-linear relationship between SFTS incidence and different transmissibility with meteorological factors and tick density in Jiangsu Province.

Part A: SFTS incidence and different infection coefficients with meteorological factors and tick density in no time lag GAM; A1: Plots of non-linear relationship with factors associated with reported incidence; A2: Plot of non-linear relationship with factors associated with the infection coefficient of human-to-human; A3: Plot of non-linear relationship with factors associated with the infection coefficient of environment-to-human; A4: Plot of non-linear relationship with factors associated with the infection coefficient of tick-to-human; A5: Plot of non-linear relationship with factors associated with the infection coefficient of animal-to-human. Part B: SFTS incidence and different infection coefficients with meteorological factors and tick density in time lag GAM; B1: Plots of non-linear relationship with factors associated with reported incidence; B2: Plot of non-linear relationship with factors associated with the infection coefficient of human-to-human; B3: Plot of non-linear relationship with factors associated with the infection coefficient of environment-to-human; B4: Plot of non-linear relationship with factors associated with the infection coefficient of tick-to-human; B5: Plot of non-linear relationship with factors associated with the infection coefficient of animal-to-human).

Fig 7. Comparison of reported data of SFTS incidence and different infection coefficients with predicted GAM data without time lag in Zhejiang Province, 2016.

A: Reported incidence and GAM simulated incidence; B: Calculated human-to-human infection coefficient and the GAM simulated infection coefficient, β₁:Infection coefficient of human-to-human; β_w1:Infection coefficient of environment-to-human; β₂₁:Infection coefficient of tick-to-human; β₃₁:Infection coefficient of animal-to-human).

Fig 8. GAM predicts the incidence of SFTS, infection coefficient and the impact of extreme weather in Jiangsu Province in 2020–2021.

Part 1: the prediction of GAM about SFTS incidence and different infection coefficients in normal weather; Part 2: the prediction of GAM about SFTS incidence and different infection coefficients in hurricane; Yellow part is the duration of the hurricane; Part 3: the prediction of GAM about SFTS incidence and different infection coefficients in drought; green part is the duration of the drought).