Incidence and tracking of Escherichia coli O157:H7 in a major produce production region in California

Abstract

Fresh vegetables have become associated with outbreaks caused by Escherichia coli O157:H7 (EcO157). Between 1995-2006, 22 produce outbreaks were documented in the United States, with nearly half traced to lettuce or spinach grown in California. Outbreaks between 2002 and 2006 induced investigations of possible sources of pre-harvest contamination on implicated farms in the Salinas and San Juan valleys of California, and a survey of the Salinas watershed. EcO157 was isolated at least once from 15 of 22 different watershed sites over a 19 month period. The incidence of EcO157 increased significantly when heavy rain caused an increased flow rate in the rivers. Approximately 1000 EcO157 isolates obtained from cultures of>100 individual samples were typed using Multi-Locus Variable-number-tandem-repeat Analysis (MLVA) to assist in identifying potential fate and transport of EcO157 in this region. A subset of these environmental isolates were typed by Pulse Field Gel Electrophoresis (PFGE) in order to make comparisons with human clinical isolates associated with outbreak and sporadic illness. Recurrence of identical and closely related EcO157 strains from specific locations in the Salinas and San Juan valleys suggests that transport of the pathogen is usually restricted. In a preliminary study, EcO157 was detected in water at multiple locations in a low-flow creek only within 135 meters of a point source. However, possible transport up to 32 km was detected during periods of higher water flow associated with flooding. During the 2006 baby spinach outbreak investigation, transport was also detected where water was unlikely to be involved. These results indicate that contamination of the environment is a dynamic process involving multiple sources and methods of transport. Intensive studies of the sources, incidence, fate and transport of EcO157 near produce production are required to determine the mechanisms of pre-harvest contamination and potential risks for human illness.

Figure 1. Map of Salinas, CA region showing sample locations.

Farm A is marked as a black dot. The circle marked with “X” is coded by positions numbered clockwise 1 to 23 and representing the sampling dates show in the list below the circle. The approximate rainfall in cm for the 5 days prior to sampling is shown in the list. Dates indicated in red text indicate at least one EcO157 strain was isolated on that date. Circles on the map designated “A” through “V” correspond to the locations where samples were obtained; these are also listed in Table S1. Open circles within the “Location circle” designate that no sample was obtained on that date; blue circles designate that a sample was obtained, but no EcO157 strain was isolated; and red circles designate that a sample was obtained, and at least one strain of EcO157 was isolated.

Figure 2. Correlation of water flow, the concentration of generic E. coli, and the incidence of EcO157 in the Gabilan Creek (Salinas, CA).

Linear regression R² values are indicated. EcO157 incidence is calculated as the fraction of the number of positive samples compared to the total samples obtained. The flow rate was obtained from data from the USGS sampling station #11152600 located at position D (see Figure 1). EcO157 incidence and generic E. coli concentration were determined with duplicate samples.

Figure 3. Concentration of generic E. coli in the Salinas watershed.

Sample locations refer to Figure 1. Red and black dots indicate isolation or non-isolation of EcO157 for the corresponding duplicate water samples, respectively.

Figure 4. Map of Salinas and San Juan valleys showing the positions (A–D) of F/Rs implicated in the traceback investigations associated with the baby spinach outbreak 2006.

Blue lines on the map are waterways.

Figure 5. MLVA types compared to (A) Salinas watershed location or (B) sample date.

Location designations refer to Figure 1 and are separated by horizontal lines in (A) to indicate separate waterways. Black and red dots indicate isolation of the MLVA type at the indicated location or date. Red dots indicate that differences were detected between that isolate and the other isolates of that MLVA type by PFGE.

Figure 6. The persistence and transport of EcO157 in a stream in an elevated area near a point source.

The change in stream elevation is indicated as a function of the distance from a corral with cattle. Sampling positions are indicated by: ⧫; different MLVA types isolated from each location are indicated. The inset shows a phylogenetic tree designating the relationship among the MLVA types isolated in this study (see Figure 7 and Table S1 for more detail).

Figure 7. A comparison of the phylogenetic relationships among 92 MLVA types.

The size of the circles indicate relative number of isolates of each MLVA type (numbers in the circles) recovered from the environment. Those MLVA types shown with the smallest circles were isolated only once. Letters A–H indicate clusters (colored regions) in which types differ at only 1 of the 10 MLVA loci from a neighbor.

Figure 8. Dendrogram of selected isolates from PFGE data.

Taxa are designated as RMXXXX (##), where RMXXXX is the isolate name and ## is an arbitrary number assigned to that MLVA type [refer to Table S1]. Taxa in red type are identical MLVA types differentiated by PFGE. Colored clusters (labeled B–H) are similar to labeled MLVA clusters in Figure 7.