Sepsis: multiple abnormalities, heterogeneous responses, and evolving understanding

Abstract

Sepsis represents the host's systemic inflammatory response to a severe infection. It causes substantial human morbidity resulting in hundreds of thousands of deaths each year. Despite decades of intense research, the basic mechanisms still remain elusive. In either experimental animal models of sepsis or human patients, there are substantial physiological changes, many of which may result in subsequent organ injury. Variations in age, gender, and medical comorbidities including diabetes and renal failure create additional complexity that influence the outcomes in septic patients. Specific system-based alterations, such as the coagulopathy observed in sepsis, offer both potential insight and possible therapeutic targets. Intracellular stress induces changes in the endoplasmic reticulum yielding misfolded proteins that contribute to the underlying pathophysiological changes. With these multiple changes it is difficult to precisely classify an individual's response in sepsis as proinflammatory or immunosuppressed. This heterogeneity also may explain why most therapeutic interventions have not improved survival. Given the complexity of sepsis, biomarkers and mathematical models offer potential guidance once they have been carefully validated. This review discusses each of these important factors to provide a framework for understanding the complex and current challenges of managing the septic patient. Clinical trial failures and the therapeutic interventions that have proven successful are also discussed.

Figure 1.

End organ damage in sepsis. Multiple organs may be damaged during the septic response. There may be dysfunction and failure of an individual organ, or multi-system organ failure may occur.

Figure 2.

Clot formation. Coagulation is an amplified cascade that begins with exposure of a few initiating molecules and ends with many thousands of thrombin molecules. The initiators are tissue factor (extrinsic pathway; primary in vivo initiator of coagulation) or contact activation of factors XII and XI (intrinsic pathway). Subsequent reactions repeat a simple amplification unit: a cofactor (green) binds an enzyme (red) on a phospholipid surface (lime green). This assembled trimeric complex binds a circulating zymogen precursor (yellow) so that the complexed enzyme can cleave and activate it. A new enzyme is created, and this is incorporated into the next amplification unit for activation of the next zymogen precursor. Each step requires calcium (factor IV), and activated platelets provide the majority of the phospholipid surfaces needed. By this mechanism, the prothrombinase complex (factors Xa, Va, phospholipid) cleaves prothrombin (factor II), releasing fragment 1.2 and creating thrombin. Thrombin removes fibrinopeptides A and B from fibrinogen, which creates fibrin. The fibrin monomers aggregate and are cross-linked into an insoluble fibrin mesh. This provides surfaces necessary for the fibrinolytic pathway, another set of activators and enzymes that cleave the clot and release clot fragments (fibrin degradation products, FDP; d-dimer) into the circulation. Thrombin is pluripotent, acting as a coagulation enzyme, a mitogenic growth factor, and a proinflammatory mediator. Thrombin activates protease-activated receptors (PARs) on platelets and endothelial cells to propagate inflammation signaling. Many feedback loops in the coagulation cascade fine-tune clot formation to serve the needs of the immediate environment. In a patient with severe sepsis and DIC, uncontrolled coagulation results in consumption of coagulation factors and platelets, which paradoxically create a bleeding risk and considerable therapeutic challenges.

Figure 3.

Common coagulation tests. The most common clinical tests of coagulation measure the time for citrated plasma to clot. The prothrombin time (PT, orange box) is the number of seconds required for a clot to form, starting from the extrinsic pathway's amplification unit of tissue factor + VIIa + phospholipid. To obtain a PT, exogenous thromboplastin is added to citrated plasma as a source of tissue factor and phospholipid, calcium is added, and the time to clot is measured. PT results are usually reported as an international normalized ratio (INR) value, which permits comparison of values from different laboratories and different thromboplastin preparations. The activated partial thromboplastin time (APTT) is the number of seconds to make a clot starting from the intrinsic contact activation pathway. It is a “partial” clotting time because tissue factor is not present. A variety of immunoassays are available that measure products of coagulation or fibrinolysis. These are less commonly used clinically but still have great value. These assays include quantification of prothrombin fragment 1.2 (F1.2) generated during limited proteolysis of prothrombin to thrombin, the inactive thrombin-antithrombin complex (TAT), fibrinopeptide A (FPA) released during formation of fibrin, and pieces of cross-linked fibrin released during fibrinolysis of the clots (fibrin degradation products, FDP; d-dimer).

Figure 4.

Controlling clot formation. Many natural inhibitors of coagulation target the amplification units that include tissue factor (initiator), factors VIIIa and Va (amplifying cofactors), and factor Xa (shared by intrinsic and extrinisic pathways). Tissue factor pathway inhibitor (TFPI) blocks the tissue factor pathway. The protein C pathway minimizes factors VIIIa and Va activities. This pathway on endothelial cells is responsible for making the activated protein C (APC) enzyme by the combined efforts of the endothelial protein C receptor (EPCR), thrombin, and thrombomodulin (TM). In concert with protein S (PS), activated protein C cleaves cofactors VIIIa and Va which slows clotting by orders of magnitude. APC also activates PAR-1, initiating signaling pathways that contribute to endothelial barrier protection. Antithrombin is the primary natural inhibitor of thrombin, but it also has broad specificity for several coagulation enzymes including factors IXa and Xa. Antithrombin activity is accelerated orders of magnitude by heparin and becomes a specific of factor Xa in the presence of low-molecular-weight heparin. Hirudin, originally derived from leech salivary glands and now available as a recombinant peptide, is a specific inhibitor of thrombin. The new chemical anticoagulants target factor Xa, at the junction of both arms of the coagulation cascade.

Figure 5.

Endoplasmic reticulum stress responses. Under conditions of homeostasis and equilibrium, abundant BiP/GRP78 chaperone complex (shown in blue) is in contact with the three major membrane-associated sensors of the unfolded protein response: PERK, IRE1α, and ATF6. During sepsis, when a cell is injured and stressed, unfolded proteins accumulate in the endoplasmic reticulum (ER) lumen and bind to BiP, preventing BiP interactions with the membrane sensors. Once released from negative regulation, the three modulators initiate individual pathways that result in generation of transcription factors. Phosphorylated PERK activates and phosphorylates eIF2α which inhibits assembly of the 80S ribosome and generates ATF4 for gene transcription. IRE1α homodimerizes and autophosphorylates, releasing its RNAse activity to generate spliced XBP1 for nuclear translocation and transcription. ATF6 undergoes limited proteolysis and activation in the Golgi, eventually moving to the nucleus to stimulate target genes. The combined and interacting sensor pathways provide the necessary molecules to repair the cell or, in the face of overwhelming stress, to initiate apoptosis by upregulating CHOP. Inhibitors of ER stress (red boxes) including activated protein C (APC), an anticoagulant, and cytoprotective enzyme target the sensors or block CHOP expression.

Figure 6.

Concept of the bimodal evolution of the systemic immunoinflammatory response in sepsis. After septic stimulus, there is an immediate and strong shift towards hyperinflammation (SIRS, overall proinflammatory status) defined by an excessive release of the classical proinflammatory cytokines (top box) into the blood. Over time, predominating SIRS gradually subsides and the septic host enters the hypoinflammatory phase (CARS, overall anti-inflammatory status) characterized by a robust release of anti-inflammatory cytokines (bottom box). The temporary transition period between SIRS and CARS zones is defined as MARS and features an approximate balance between the circulating pro- and anti-inflammatory mediators. A septic subject can undergo alternating shifts toward either SIRS or CARS. [Modified from Oberholzer et al. (276), with permission from Lippincott Williams & Wilkens.]

Figure 7.

Release of pro- and anti-inflammatory cytokines in animal dying and surviving the acute phase of polymicrobial sepsis is simultaneous and of similar magnitude. Average inflammatory scores for each block were computed by retrospectively combining selected proinflammatory (A; IL-1β, IL-6, TNF-α, KC, MIP-2, MCP-1) and anti-inflammatory (B; IL-1ra, IL-10, TNF srI, and II) mediators and dividing them according to outcome. Data are presented as means + SE. *P < 0.0001, #P < 0.005. Data were generated in the mouse model of CLP sepsis. [From Osuchowski et al. (287). Copyright 2006. The American Association of Immunologists, Inc.]

Figure 8.

The immunoinflammatory trajectory in a subject dying from the acute-type septic response. The scheme delineates immunoinflammatory fluctuations using the time of death as the reference point given that the time of the sepsis onset in patients is typically unknown. As the severity of sepsis progresses, the magnitude of the systemic pro- and anti-inflammatory cytokine response and cellular anergy increases. A prelethal immunoinflammatory status of a subject dying from acute sepsis is characterized by both a MARS-like cytokine profile (concurrent presence of both pro- and anti-inflammatory mediators in the blood) and distinct signs of anergy in the cellular compartment. An acute inflammatory response (hyperinflammation), although typically associated with early septic deaths, may occur at any chronological phase of the disease if a septic organism is sufficiently immunologically responsive. The scheme is largely based on data generated in the mouse model of CLP sepsis.

Figure 9.

The immunoinflammatory trajectory in a subject dying from the chronic septic response. The scheme delineates immunoinflammatory fluctuations using the time of death as the reference point given that the time of the sepsis onset in patients is typically unknown. As the severity of sepsis progresses, the magnitude of the systemic pro- and anti-inflammatory cytokine response wanes and becomes erratic while the degree of cellular anergy increases. A prelethal immunoinflammatory status of a subject dying from the chronic-type septic response is characterized by a deteriorating but MARS-like cytokine profile (concurrent presence of both pro- and anti-inflammatory mediators in the blood) and robust signs of anergy in the cellular compartment. A chronic inflammatory response (hypoinflammation), although typically associated with late septic deaths, may also occur at an early chronological phase of the disease if a septic host is immunologically unresponsive. The scheme is largely based on data generated in the mouse model of CLP sepsis.

Figure 10.

Modeling responses to septic challenge. Mathematical modeling of responses to sepsis can include equations and analyses that consider the host hemodynamic, physiological and inflammation parameters, as well as pathogen distribution or growth. Principal component analysis (PCA) is a technique that analyzes the variance between observations. It is used to identify patterns in data and to express the data in such a way as to highlight their similarities and differences. In the example shown here, PCA analysis of normalized and grouped cytokine data from animals (n = 24) challenged with a proinflammatory toxin reveals gradual separation of survivors and nonsurvivors over time when viewed in the PC1-PC2 space. Genomic and microarray data provide a static view of a physiological condition, but patients with sepsis, septic shock, and comorbidities change rapidly so consideration of time in modeling methods is necessary for relevance to patients.