Less spatial exploration is associated with poorer spatial memory in midlife adults

Abstract

Introduction: Despite its importance for navigation, very little is known about how the normal aging process affects spatial exploration behavior. We aimed to investigate: (1) how spatial exploration behavior may be altered early in the aging process, (2) the relationship between exploration behavior and subsequent spatial memory, and (3) whether exploration behavior can classify participants according to age.

Methods: Fifty healthy young (aged 18-28) and 87 healthy midlife adults (aged 43-61) freely explored a desktop virtual maze, learning the locations of nine target objects. Various exploration behaviors (object visits, distance traveled, turns made, etc.) were measured. In the test phase, participants navigated from one target object to another without feedback, and their wayfinding success (% correct trials) was measured.

Results: In the exploration phase, midlife adults exhibited less exploration overall compared to young adults, and prioritized learning target object locations over maze layout. In the test phase, midlife adults exhibited less wayfinding success when compared to the young adults. Furthermore, following principal components analysis (PCA), regression analyses indicated that both exploration quantity and quality components were associated with wayfinding success in the midlife group, but not the young adults. Finally, we could classify participants according to age with similar accuracy using either their exploration behavior or wayfinding success scores.

Discussion: Our results aid in the understanding of how aging impacts spatial exploration, and encourages future investigations into how pathological aging may affect spatial exploration behavior.

Keywords: age; midlife; spatial exploration; spatial memory; spatial navigation; virtual reality.

Figure 1

Overview of the Maze Learning Task. (A) Overhead map of virtual maze, with positions of target objects (red circles) and paintings (purple rectangles). All target object and hallway locations inside the maze have been respectively labeled with letters of the alphabet. (B) Participant view during maze navigation, with three possible directions to move (view of a painting ahead). (C) View of example target object (spaceship). (D) Participant view of target object during test phase—all target objects have been transformed into red spheres to minimize feedback. Figure modified from Yu et al. (2021).

Figure 2

Violin plots showing group comparisons of all variables in the exploration phase, after controlling for sex. The y axes of all plots denote the raw values for all variables (including those that were transformed). The waves indicate the probability distribution of the variables, the red dots represent the group means, the red lines intersecting the red dots represent the group standard deviations, the blue dots represent the group medians, and the horizontal black lines indicate significant group differences. (A) Distance Traveled, (B) Pause Duration, (C) Number of Button Presses, (D) Number of Target Object Visits, (E) Number of Hallway Visits, (F) Longest Hallway Sequence, (G) Turns Made, (H) Clustering of Exploration of Objects, (I) Clustering of Exploration of Hallways, and (J) Path Roaming Entropy. **p < 0.01, ***p < 0.001.

Figure 3

Violin plot showing the group comparison of wayfinding success in the test phase, after controlling for sex. The y axis denotes the raw, pre-transformed values for this variable. The waves indicate the probability distribution of the variables, the red dots represent the group means, the red lines intersecting the red dots represent the group standard deviations, the blue dots represent the group medians, and the horizontal black line indicates a significant group difference. Note that the standard deviation lines for the midlife group visually extend beyond the plot bounds; this is because due to the highly skewed distribution and presence of extreme values in this group, the standard deviation value is higher than the mean value. *p < 0.05.

Figure 4

Linear regression plots showing the relationship between PCs and wayfinding success in the midlife group (n = 87). (A) The relationship between PC1 (exploration quantity) and wayfinding success. Higher PC1 scores were associated with higher wayfinding success. (B) Relationship between PC2 (exploration quality) and wayfinding success. Higher PC2 scores were associated with higher wayfinding success.

Figure 5

Linear regression plot showing the relationship between PC2 (exploration quality) and wayfinding success in the young group (n = 50). A statistical trend toward significance was seen for higher PC2 scores being associated with more wayfinding success.

Figure 6

Comparison of ROC curves for the logistic regression models with wayfinding success (purple, AUC = 0.793) and a combination of the PCs (orange, AUC = 0.877) as the independent variables. Although the combined exploration model has a higher AUC, the two curves were not significantly different (p = 0.107).