Using an Agent-Based Model to Examine the Role of Dynamic Bacterial Virulence Potential in the Pathogenesis of Surgical Site Infection

Abstract

Objective: Despite clinical advances, surgical site infections (SSIs) remain a problem. The development of SSIs involves a complex interplay between the cellular and molecular mechanisms of wound healing and contaminating bacteria, and here, we utilize an agent-based model (ABM) to investigate the role of bacterial virulence potential in the pathogenesis of SSI.

Approach: The Muscle Wound ABM (MWABM) incorporates muscle cells, neutrophils, macrophages, myoblasts, abstracted blood vessels, and avirulent/virulent bacteria to simulate the pathogenesis of SSIs. Simulated bacteria with virulence potential can mutate to possess resistance to reactive oxygen species and increased invasiveness. Simulated experiments (t=7 days) involved parameter sweeps of initial wound size to identify transition zones between healed and nonhealed wounds/SSIs, and to evaluate the effect of avirulent/virulent bacteria.

Results: The MWABM reproduced the dynamics of normal successful healing, including a transition zone in initial wound size beyond which healing was significantly impaired. Parameter sweeps with avirulent bacteria demonstrated that smaller wound sizes were associated with healing failure. This effect was even more pronounced with the addition of virulence potential to the contaminating bacteria.

Innovation: The MWABM integrates the myriad factors involved in the healing of a normal wound and the pathogenesis of SSIs. This type of model can serve as a useful framework into which more detailed mechanistic knowledge can be embedded.

Conclusion: Future work will involve more comprehensive representation of host factors, and especially the ability of those host factors to activate virulence potential in the microbes involved.

Gary An, MD

Figure 1.

Overall schematic of cells, cellular functions mediators present in the MWABM: This figure is a semi-cross section of the MWABM, where the IMC matrix is depicted as a row of healthy IMCs, damaged/dead IMCs, and pus agents at the bottom of the figure. The wound diameter is denoted as a section of this row. Mobile inflammatory cells, migratory myoblasts, and bacteria are seen above the matrix row, along with the mediators produced by and affecting their activity. Solid arrows denote positive/stimulatory effects, whereas dashed arrows denote negative/inhibitory effects. The specific rules associated with each of these interactions can be seen in the Agent types and rules section of Materials and Methods, as well as in Tables 1 and 2. MWABM, Muscle Wound agent-based model.

Figure 2.

Series of MWABM screenshots of a single representative run demonstrating successful healing. (A–J) show the progression of the MWABM from healthy (A) with initial injury (B) followed by neutrophil influx and pus generation (C–E), macrophage influx and pus clearance (D–G), and, finally, myoblast influx and muscle regeneration (F–I) until the healthy state is returned (I, J, A). To see this illustration in color, the reader is referred to the web version of this article at www.liebertpub.com/wound

Figure 3.

Time courses of mediators present in a representative healing run of the MWABM. These graphs (A–I) depict the system-wide values of the respective mediators present in the MWABM in the same run that produced the screenshots in Figure 2. The values themselves are unitless and not calibrated to actual metrics, but are qualitatively valid in relation to each other.

Figure 4.

Time course of cellular populations of neutrophils, macrophages, and pus in a representative healing run of the MWABM. These cell populations were generated from the same run that produced the screenshots in Figure 2 and the graphs in Figure 3.

Figure 5.

Time course of myoblast populations in a representative healed run of the MWABM. The regular oscillation in the population level is an artifact of the code scheduler in the NetLogo implementation; myoblast levels can be considered the mean of the oscillation amplitude. This cell population corresponds to the graphs seen in Figure 3.

Figure 6.

Depiction of transition zone between healed and nonhealed/SSI outcomes in the base MWABM (no bacteria). This figure demonstrates the results of a parameter sweep of initial injury size (# of cells damaged in increments of 10), with an n=10 for each initial injury size. The transition zone is defined as extending from the initial injury size at which nonhealing is first seen to the injury size at which no healing is seen at all. This parameter sweep in the base MWABM (without any bacteria) is done to establish the “normal” case from which pathogenic conditions can be assessed. The transition zone in this case extends from 260 to 360 initial damage size.

Figure 7.

Screenshots of both successfully healed MWABM run (A) and an SSI (B). These images depict the healing and SSI phenotypes as seen in the MWABM. In particular, note the highly irregular shape of the SSI phenotype; this reflects a loss of effective containment of the initial injury, and reinforces the spatial nature of the wound healing process. SSI, surgical site infection. To see this illustration in color, the reader is referred to the web version of this article at www.liebertpub.com/wound

Figure 8.

Depiction of transition zone between healed and nonhealed/SSI outcomes in the MWABM with avirulent bacteria. This parameter sweep was performed in the same manner as the simulations used to generate Figure 6, but with the addition of 100 avirulent bacteria with the initial damage. The notable finding here is that the transition zone underwent a left shift to damage size 210 to 320, suggesting the detrimental effect of bacterial contamination on the effectiveness of wound healing manifesting as an SSI. Also of note, the size of the transition zone (90 damaged cells) is relatively similar to the size of the baseline transition zone (100 damaged cells).

Figure 9.

Depiction of transition zone between healed and nonhealed/SSI outcomes in the MWABM with virulent bacteria. This parameter sweep was performed in the same fashion as the simulations used to generate Figure 8, but with the addition of dynamic virulence potential (arising 1:1,000 bacteria productions). The notable finding here is that while the upper threshold of the transition zone (Damage #=320), reflecting the upper extent of contamination, is the same as with avirulent bacteria, the lower threshold (Damage #=170), reflecting the lower bound of contamination, is considerably less. Given the attention paid to antisepsis, it is plausible to assume that a large percentage of unanticipated SSIs would occur at the lower bound, suggesting that the role of bacterial virulence potential has a disproportionate effect in the clinical pathogenesis of SSI.