A prospective prediction tool for understanding Crimean-Congo haemorrhagic fever dynamics in Turkey

Abstract

Objectives: We aimed to develop a prospective prediction tool on Crimean-Congo haemorrhagic fever (CCHF) to identify geographic regions at risk. The tool could support public health decision-makers in implementation of an effective control strategy in a timely manner.

Methods: We used monthly surveillance data between 2004 and 2015 to predict case counts between 2016 and 2017 prospectively. The Turkish nationwide surveillance data set collected by the Ministry of Health contained 10 411 confirmed CCHF cases. We collected potential explanatory covariates about climate, land use, and animal and human populations at risk to capture spatiotemporal transmission dynamics. We developed a structured Gaussian process algorithm and prospectively tested this tool predicting the future year's cases given past years' cases.

Results: We predicted the annual cases in 2016 and 2017 as 438 and 341, whereas the observed cases were 432 and 343, respectively. Pearson's correlation coefficient and normalized root mean squared error values for 2016 and 2017 predictions were (0.83; 0.58) and (0.87; 0.52), respectively. The most important covariates were found to be the number of settlements with fewer than 25 000 inhabitants, latitude, longitude and potential evapotranspiration (evaporation and transpiration).

Conclusions: Main driving factors of CCHF dynamics were human population at risk in rural areas, geographical dependency and climate effect on ticks. Our model was able to prospectively predict the numbers of CCHF cases. Our proof-of-concept study also provided insight for understanding possible mechanisms of infectious diseases and found important directions for practice and policy to combat against emerging infectious diseases.

Keywords: Crimean–Congo haemorrhagic fever; Gaussian processes; Machine learning; Spatiotemporal epidemiology; Vector-borne disease.

Fig. 1

Summary of Turkish nationwide Crimean–Congo haemorrhagic fever (CCHF) surveillance data set. (a) Monthly confirmed CCHF case counts between January 2004 and December 2017. (b) Total confirmed CCHF case counts for each province between years 2004 and 2017. Numbers in the key of (b) correspond to the minimum and maximum numbers of observed cases in provinces between 2004 and 2017. Yearly case count maps can be seen at http://midas.ku.edu.tr/ProspectiveCCHF/.

Fig. 2

Prediction results obtained by our structured Gaussian process algorithm for 2016. Observed cases are shown in blue and predicted cases are shown in red. (a) Monthly observed and predicted Crimean–Congo haemorrhagic fever (CCHF) case counts for 2016. (b) Annual observed CCHF case counts for each province in 2016. (c) Annual predicted CCHF case counts for each province in 2016. Numbers in the keys of (b) and (c) correspond to the minimum and maximum numbers of observed and predicted cases in provinces for 2016. Monthly prediction maps can be seen at http://midas.ku.edu.tr/ProspectiveCCHF/.

Fig. 3

Prediction results obtained by our structured Gaussian process algorithm for 2017. Observed cases are shown in blue and predicted cases are shown in red. (a) Monthly observed and predicted Crimean–Congo haemorrhagic fever (CCHF) case counts for 2017. (b) Annual observed CCHF case counts for each province in 2017. (c) Annual predicted CCHF case counts for each province in 2017. Numbers in the keys of (b) and (c) correspond to the minimum and maximum numbers of observed and predicted cases in provinces for 2017. Monthly prediction maps can be seen at http://midas.ku.edu.tr/ProspectiveCCHF/.