Shandong Province, located between latitude 34°25′ and 38°23′ north, and longitude 114°36′ and 112°43′ east, is a coastal province in Eastern China with a population of approximately 98 million people (Figure 1). It includes 140 counties (subdistricts) belonging to 17 regions (municipal districts) with a total land area of 156,700 square kilometers.

Data of HFMD in Shandong Province during 2007 to 2011 were derived from CISDCP, including the basic social-demographic characteristics of HFMD cases, and the pathogen type (CoxA16, EV71 and other EV) of some HFMD cases. The diagnosis was based on the clinical criteria from the HFMD Control and Prevention Guide published by the Chinese Ministry of Health [19]. The report cards of HFMD cases were filled out by professional doctors, and collected by trained reporter and then input into the CISDCP within 24 hours based on the P. R. China infectious disease prevention and cure statute. EV71, CA16 and other enteroviruses were tested by real-time PCR in 17 laboratories located in 17 cities in Shandong guided by Shandong CDC, the pathogen data was also uploaded to the China CISDCP. In this paper, we focused on the children HFMD cases (0 to 5 years) which accounted for about 94% of the total cases (described in the results section). The corresponding demographic data of each county between 2007 and 2011 were obtained from Shandong Statistical Yearbook. All collected data were geographically referenced based on 140 counties of Shandong Province, i.e., 140 spatial units for analysis.

The frequencies of HFMD were summarized monthly and annually by geographic area (i.e., county). The 0 to 5 years incidence rates of HFMD were calculated by HFMD counts aged 0 to 5 years divided by the population aged 0 to 5 years, which were expressed as the number of cases per 100,000. And the incidence rates of all ages were calculated using the total number of HFMD cases and total population.

The autocorrelation statistic (Moran’s I) [20] was used to detect the global spatial autocorrelation of HFMD cases in the study area and disclose the spatial pattern of HFMD with Z score at county level. The significance of Moran’s I was assessed by employing Monte Carlo randomization. A statistically significant (Z score ≥1.96) estimate of I indicates that neighboring counties have a similar prevalence rate of HFMD and the cases are likely to cluster at county level. The software GeoDa™ 0.9.5-i was used to conduct the analysis [21].

Scan statistics [22] were used to determine the presence of high rates clusters of HFMD. (1) Spatial scan statistic, based on discrete Poisson model, was used to identify purely spatial clusters of HFMD cases by year. The purely spatial scan statistic imposes a circular (or elliptic) window which was in turn centered on each geographical area throughout the study region. The radius of the window varies continuously in size according to the population range of the area (from zero to some upper limit specified by user). (2) Space-time scan statistic, based on Space-Time Permutation model, was adopted to determine the presence of space-time clusters of HFMD cases during the study period. Space-Time Permutation scan statistic, which is developed for the early detection of disease outbreaks and is especially useful when we have only the number of cases and no population-at-risk information [23]. This approach was defined by a cylindrical window with a circular (or elliptic) geographic base and with height corresponding to time, which undergo dynamic changes in space and time to detect possible spatial-temporal clusters [24]. The space-time scan statistic automatically adjusted for both purely spatial and purely temporal variation. The base was defined exactly as for the purely spatial scan statistic, while the height changes according to the defined time interval (less than or equal to half the total study period) which reflects the time period of potential clusters. In two scan statistics mentioned above, the null hypothesis is that the rate (Poisson model), or the independence of cases in space and time (Space-Time Permutation model), was the same within and outside the scanning window. For each window, a likelihood ratio and the relative risk were calculated to test the hypothesis. And the P values for detected clusters were calculated by using Monte Carlo hypothesis testing to generate a number of random replications of the data set under the appropriate null hypothesis. The scanning window with the maximum likelihood constituted most likely cluster, other windows for which the likelihood value was statistically significant were defined as secondary clusters ranked according to their likelihood ratio test statistic. The statistical analyses were done by the free SaTScan™ v9.1.1 software.

In this study, we used 140 counties of Shandong Province as spatial units, 60 months from January 2007 to December 2011 as time unit. In order to scan for small to large clusters, the largest radius was set to 50% of the total population at risk, the largest height was set to 50% of the total study period. To ensure excellent statistical power and consider the computation times, 999 Monte Carlo replications were set, and clusters with statistical significance of P<0.05 were all reported, including secondary clusters that did not overlap with a previously reported cluster (i.e., they had no location IDs in common). Furthermore, we used ArcGIS v9.0 (ESRI, Redlands, CA, USA) to visualize the results of scan statistic analysis.

There were 448,251 HFMD cases reported in Shandong Province from 2007 to 2011, including 9,006 severe and 79 fatal cases. The annual average incidence rate of HFMD was 93.70 per 100,000 (ranged from 35.34 per 100,000 in 2008 to 148.82 per 100,000 in 2010).

Table 1 summarized the social-demographic characteristics of HFMD cases and the pathogen types of some cases from 2007 to 2011. It showed that 0–5 year old age group was majority of the victims in the outbreaks, which accounted for 93.94% (421,072 cases) of all reported cases over the study period, with the annual average incidence rate 1442.50 (ranged from 550.11 in 2008 to 2249.54 in 2009) per 100,000. Thus, we mainly focused on 0–5 year old age group in the following spatial analysis.

Of 421,488 HFMD cases, 266,185 were boys and 155,303 were girls, with an average male-to-female sex ratio 1.71 (1.73 in 2007, 1.82 in 2008, 1.68 in 2009, 1.73 in 2010, and 1.69 in 2011). In China, all 0–5 year old age children spent their daytime at home, kindergarten or school. Table 1 displayed that most of HFMD cases were preschoolers (74.52% scattered children and 25.35% nursery children), the rest (0.13%) were students. From 2008, pathogen detection for HFMD had been conducting using nucleic acid testing in Shandong Province. Among 13,532 genotyped cases between 2008 and 2011, CoxA16, EV71 and other EV accounted for 30.82%, 45.48% and 23.71% respectively. Clearly, the annual distribution of HFMD pathogens varied heavily (Table 1).

Figure 2 illustrated the monthly distribution of HFMD cases, which indicated that the occurrence of HFMD presented significant seasonality. It was obvious that the incidence peak appeared between April and July in the study years.

Figure 3 showed the annual incidence rate of 0–5 year old age per county accounting for the spatial variability of population size. It clearly indicated that the distribution of HFMD was heterogeneous at county level. Table 2 listed the results of the spatial autocorrelation test, which demonstrated that high global spatial autocorrelation of HFMD was detected at county level in Shandong Province within each epidemic year during 2007 to 2011 (Moran’s I >0.3, P<0.001).

Figure 4 showed the statistically significant spatial clusters (including the most likely cluster and several secondary clusters) for a high occurrence of HFMD identified by purely Spatial scan statistic based on discrete Poisson model. It was obvious that the locations and sizes of these clusters varied by year. The most likely clusters were in Qingdao area (2007, 2010), Jinan area (2010), Linyi area (2008, 2010), Liaocheng area (2009), Zibo, Dongying and Binzhou areas (2010, 2011), Yantai, Weifang, Taian, Weihai, Rizhao, Laiwu, Dezhou areas (2011). Table 3 summarized the size, relative risk, and P value, etc. of most likely clusters, indicating hotspots of HFMD wandered around in the whole Shandong from 2007 to 2011.

Using Space-Time Permutation model, we detected the statistically significant monthly spatial-temporal clusters for a high occurrence of HFMD during 2007 to 2011, shown in Table 4 and Figure 5. Seven spatial-temporal clusters were detected from 2007 to 2011, including 1 most likely cluster and 6 secondary clusters. The first (most likely) cluster was located in southwest Shandong from February 2009 to April 2010 (cluster 1, Radius = 97.01 km) with 36235 cases (RR = 1.83, P<0.0001). The dominant pathogen was EV71 (57.81%). Followed by cluster in north Shandong from May 2011 to October 2011 (cluster 2, Radius = 53.84 km) with 14257 cases (RR = 2.46, P<0.0001) and EV71 as the dominant pathogen (64.37%); cluster in south Shandong from May 2007 to May 2009 (cluster 3, Radius = 59.85 km) with 23147 cases (RR = 1.74, P<0.0001) and EV71 as dominant (68.42%); cluster in northeast Shandong from June to October 2007 (cluster 4, Radius = 145.51 km) with 10488 cases (RR = 2.23, P<0.0001) and no pathogen data; cluster in northwest Shandong from June 2010 to July 2010 (cluster 5, Radius = 82.40 km) with 12097 cases (RR = 1.68, P<0.0001) and CoxA16 as dominant (50.09%); cluster in middle west Shandong from September 2008 to January 2009 (cluster 6, Radius = 28.44 km) with 1234 cases (RR = 6.88, P<0.0001) and EV71 as dominant (83.33%); cluster in middle east Shandong from June 2010 to July 2010 (cluster 7, Radius = 49.09 km) with 10180 cases (RR = 1.70, P<0.0001) and combined EV71 (29.45%) with CoxA16 (26.71%) as dominant. The above spatial pattern of clusters indicated that the occurrence of HFMD was with spatial-temporal heterogeneity. In chronological order, the earliest high occurrence area was cluster 4, followed by cluster 3, cluster 6, cluster 1, cluster 5, cluster 7 and cluster 2. Although different HFMD pathogen existed in different cluster areas, EV71 was the dominant pathogen for most clusters.