Semantic Relations in a Categorical Verbal Fluency Test: An Exploratory Investigation in Mild Cognitive Impairment

Abstract

Categorical verbal fluency tests (CFT) are commonly used to assess the integrity of semantic memory in individuals with brain damage. Persons with Dementia of the Alzheimer's Type display a reduced output on CFT, and a similar pattern has been reported in persons with amnesic Mild Cognitive Impairment (aMCI). The aims of the present study were to assess whether the semantic relations between lexical entries produced on a categorical fluency test were different between healthy persons and those with aMCI, and whether this difference was more pronounced in individuals who converted to dementia during a 3-year follow-up period.

Methods: We recruited 34 individuals with aMCI and 29 matched healthy persons. During the follow-up period, 10 individuals converted to Dementia (aMCI-conv). Two measures assessing semantic relations between consecutively produced word pairs (Path length and Extended Gloss Overlap) were obtained from the Wordnet database.

Results: The number of word pairs analyzed among the healthy participants (HP) and persons with aMCI were 498 (birds: 262; pieces of furniture: 236) and 395 (birds: 174; pieces of furniture: 221), respectively. Path length was lower in aMCI-conv than in HP (p = 0.035), but no differences were found between stable aMCI and HP, and between aMCI-stable and aMCI-conv. The ANOVA for lexical entries belonging to the "birds" category showed a significant effect of group (F = 5.630; p = 0.004); the post hoc analysis showed a significant difference between HP and aMCI-conv (p = 0.003). The "pieces of furniture" category was significantly affected by group (F = 4.107; p = 0.017); the post hoc test showed significant differences between aMCI-conv and healthy individuals (p = 0.049), and between aMCI-conv and stable aMCI (p = 0.001).

Discussion: Individuals with aMCI who convert to dementia show a deterioration in the semantic relations between lexical entries, produced on a CFT. This phenomenon may be interpreted as a marker of a very early disruption of semantic memory.

Keywords: category fluency task; dementia of the Alzheimer type; mild cognitive impairment; semantic memory; semantic proximity.

FIGURE 1

In category fluency tasks, the production of a subsequent word may be influenced by the previous one through the activation of shared features that may facilitate the retrieval of the following lexical entry. In the example depicted here, the production of the word “hawk” may cause the activation of features such as the ones marked with a continuous line that are shared with “eagle,” but not with “duck.” Thus, “eagle” has a higher probability of being produced, than “duck.” When this kind of strategy (resembling classical “clustering”) is exhausted, the subject must “switch” to other subcategories.

FIGURE 2

(A,B) Complete hierarchical trees for the word “hawk” and the corresponding Italian term “falco,” as derived from WordNet and MultiWordNet.

GRAPH 1

Mean values of path length in the “birds” and “pieces of furniture” categories among healthy participants (HP), aMCI who remained stable (aMCI-stable) and aMCI who converted to dementia (aMCI-conv). Error bars correspond to 95% Confidence Interval. ^∗HP vs. aMCI-conv p < 0.05.

GRAPH 2

Mean values of extended gloss overlap in the “birds” and “pieces of furniture” categories among HP, aMCI who remained stable (aMCI-stable) and aMCI who converted to dementia (aMCI-conv). Error bars correspond to 95% Confidence Interval. ^∗HP vs. aMCI-conv p < 0.05.

GRAPH 3

Mean number of clusters identified for the “birds” and “pieces of furniture” categories among HP, aMCI who remained stable (aMCI-stable) and aMCI who converted to dementia (aMCI-conv). Error bars correspond to 95% Confidence Interval. ^∗HP vs. aMCI-conv p < 0.05. #HP vs. aMCI-stable p < 0.05.