STRESS AND MEMORY

Stressful and emotional events can promote or impair the acquisition of new memories, depending on the type of stressful experience, the type of learning—even the sex of the animal. Stress is the external condition that places demands on the organism, and the stress response is the organism's adaptive response to the stressor, typically measured as changes in performance or physiological or biochemical states.

Most adaptive responses are crucial to an organism's capacity for survival and are easily reconcilable with theories of natural selection. For instance, the release of glucocorticoids from the adrenal glands directs glucose to the brain and musculature in preparation for "fight or flight," thereby eliminating unnecessary processing of ongoing vegetative functions such as digestion. These physiological responses to stress in turn affect cognitive processes such as learning and memory, thereby allowing the animal to prepare for or avoid subsequent sources of stress. The interaction between stress and memory is a complex one that does not always serve the best interests of the animal.

At first it seems reasonable to assume that there is a direct correlation between degree of stress and degree of detriment. In reality, animals (including humans) perform optimally at moderate levels of demand, and performance is compromised at the extremes. Hence, the relationship between stress and performance is an inverted U-shaped function: Performance is impaired equally at high levels of stress and at low levels (boredom or drowsiness); moderate levels, performance is enhanced. For example, exposure to a moderate stressor such as background noise can facilitate performance of a prolonged vigilance task. Substituting arousal for stress, Donald Hebb (1955) suggested that continuing neural activity could provide a physiological means of describing such self-motivating phenomena as curiosity and exploration and their obvious contribution to learning. Moreover, he emphasized that without such an arousal foundation, no learning would occur. This relationship, in combination with the inverted-U relationship proposed between stress and performance, predicts a linear relationship between stress and arousal. Others, however, have reported an upright U-shaped correlation between stress and arousal, which forecasts a monotonic relationship between stress and performance. Still others report that stress and arousal are independent variables.

Exactly how stressful experience will affect memory formation depends, presumably, on the significance of the information to be remembered and therefore on the type of learning that is being tapped. Under most circumstances, an animal will remember an aversive event for most of its life. But subsequent experience can change these memories. Autonomic tasks entailing a high degree of preparedness are less likely to be adversely affected than tasks requiring high cognitive capacity and concentration. These two extremes can be viewed as the ends of a continuum, with stress impairing performance as task difficulty increases. This relationship is exemplified by the intense training and practice required of highly skilled professionals such as military personnel, who must perform optimally under high levels of stress and uncertainty.

The degree to which stress impinges on performance is highly susceptible to individual differences. Although there is a limit to the attentive capacity that can be allocated to a particular task, this capacity is not fixed and will vary from individual to individual and from day to day. On the evidence of human self-report scales, high-anxiety subjects tend to perform optimally on easy tasks, and low-anxiety subjects perform optimally under more demanding circumstances; within tasks, low-anxiety subjects perform better during early stages of learning, and high anxiety facilitates the later stages. Other variables include social factors, age, and disease. But the most significant is past memories. The animal must not only calculate the imbalance between the perceived demand and the ability to cope with that demand but must also incorporate this information into its previous experience.

In the early 1960s J. B. Overmier and M. E. P. Seligman noticed that dogs exposed to inescapable shock were later impaired in their ability to perform a task where escape was possible. They suggested that the animals became helpless after learning that the aversive event and the ability to cope with that event were not contingent; they termed the phenomenon learned helplessness. Because the secondary characteristics that accompany helplessness—weight loss, sleep disturbances, decreased activity, and so on—resemble characteristics of depressed humans, the phenomenon evolved into one of the first experimental models of depression. It has helped to demonstrate stress-induced effects on immune function, ulcer development, tumor growth, analgesia, aggression, and status within a dominance hierarchy. But impairment in performance remains the most notable result.

However intuitively appealing, this paradigm of helplessness is constrained by more general theories of stress and learning and, in fact, depends on individual sex, species, and strain differences as well as the nature and difficulty of the task. For example, prior exposure to inescapable stresses such as tail shocks or swim stress facilitates classical conditioning of the eyeblink response in male rats, whereas exposure to the same stresses impairs conditioning in female rats. Recent studies in humans have suggested that males and females also differ in the ways in which they deal with stress; males tend to isolate themselves, whereas females tend to befriend others and seek comfort. These differences can affect what types of learning opportunities arise after stressful experience.

One of the first scientists to define stress and its adaptive utility and underlying mechanisms was the eminent physiologist Hans Seyle. Dr. Seyle defined the stress response as the nonspecific response of the body to any demand placed upon it. In general, Seyle was referring to activation of the hypothalamic-pituitary-adrenal (HPA) axis. In this axis, hypothalamic peptides activate adrenocorticotropin (ACTH) secretion from the anterior pituitary. ACTH induces the release of glucocorticoids from the adrenal cortex, and glucocorticoids, in turn, inhibit the release of pituitary ACTH. Glucocorticoids are released peripherally into the blood upon most stressful encounters and are potentially damaging, especially in high concentrations and/or chronic conditions. There are numerous reports that they can impair later learning; however, there are also reports that they can enhance it. As with exposure to a stressful event, the degree and direction of the effect depends on the amount of glucocorticoids that are released and the time of exposure.

In addition to glucocorticoids, many other stress-related neuromodulators can affect mnemonic processes. The catecholamines have been implicated in learning, as are the dopaminergic systems. Along with ACTH, β-endorphin is released from the pituitary in response to stress. Peptides such as the opioids (the enkephalins), vasopressin, and neuropeptide Y can be affected by exposure to a stressful experience and can thereby influence memory processes. One of more ubiquitous substrates affected by stress is the glutamatergic system, including the corresponding receptors, n-methyl-d-aspartate (NMDA) and α-amino-3-methylsoxazole-4-propionic acid (AMPA). Glutamate is the primary excitatory neurotransmitter in the brain, and activation of its receptors is critical to many types of learning. The dramatic extent to which stress affects this system affords ample opportunity for stressful experiences to affect processes of learning and memory.

Exposure to acute or chronic stressor experiences induces a variety of effects on neuronal plasticity, affecting synaptic morphology, receptor affinity and number, gene expression, and electrophysiological responsiveness. For example, exposure to an acute stressor of inescapable tail shocks induces immediate early gene (IEG) expression, impairs long-term potentiation (LTP), and can enhance the density of dendritic spines; research has identified all of these factors as possible biological substrates for learning in the mammalian brain. Many of these effects unfold in the hippocampal formation, a part of the brain that plays a critical role in some types of memory formation. In addition, the amygdala is a critically factor in many defensive and affective responses to stress or danger. This limbic structure integrates information from numerous sources and sensory systems and participates in the formation of memories about those experiences that are necessary for ensuring an appropriate response to future danger.

Many of the foregoing neuromodulatory systems are colocalized, and the brain regions are highly interconnected, making it difficult to interfere experimentally with one without affecting another. Furthermore, given the wide diversity of stressors and the inherent variance in individual responsiveness to the same stressor, it is probable that specific but overlapping circuits contribute to stress effects on learning. Finally, these stress-induced responses are not necessarily detrimental to the physical and psychological well-being of the organism; in the aftermath of the stressful encounter, they contribute to the reestablishment of homeostasis and an appropriate consolidation of the experience.

See also:HORMONES AND MEMORY; LEARNED HELPLESSNESS; NEURAL COMPUTATION: HIPPOCAMPUS; NEURAL SUBSTRATES OF CLASSICAL CONDITIONING: DISCRETE BEHAVIORAL RESPONSES; NEURAL SUBSTRATES OF EMOTIONAL MEMORY

Bibliography

Blanchard, D. C., and Blanchard, R. J. (1988). Ethoexperimental approaches to the biology of emotion. Annual Review of Psychology 39, 43-68.

Cox, T. (1980). Stress. Baltimore: University Park Press.

Lupien, S. J., and Lepage, M. (2001). Stress, memory, and the hippocampus: Can't live with it, can't live without it. Behavioral Brain Research 14, 137-158.

Shors, T. J. (1998). Sex and stress effects on learning and memory: For better or for worse. The Neuroscientist 4, 353-364.

Taylor, S. E., Klein, L. C., Lewis, B. P., Gruenewald, T. L., Gurang, R. A., and Updegraff, J. A. (2000). Biobehavioral responses to stress in females: Tend-and-befriend, not fight-or-flight. Psychological Review 107, 411-429.

Tracey J.Shors