Visualizing and Quantifying Longitudinal Changes in Verbal Fluency Using Recurrence Plots

Abstract

The verbal fluency task, where participants name as many instances of a specific semantic or phonemic category as possible in a certain time limit, is widely used to probe language and memory retrieval functions in research and clinical settings. More recently, interests in using longitudinal observations in verbal fluency to examine changes over the lifespan have grown, in part due to the increasing availability of such datasets, yet quantitative methods for comparing repeated measures of verbal fluency responses remain scarce. As a result, existing studies tend to focus only on the number of unique words produced and how this metric changes over time, overlooking changes in other important features in the data, such as the identity of the words and the order in which they are produced. Here, we provide an example of how the literature of recurrence analysis, which aims to visualize and analyze non-linear time series, may present useful visualization and analytical approaches for this problem. Drawing on this literature, we introduce a novel metric (the "distance from diagonal," or DfD) to quantify semantic fluency data that incorporates analysis of the sequence order and changes between two lists. As a demonstration, we apply these methods to a longitudinal dataset of semantic fluency in people with Alzheimer's disease and age-matched controls. We show that DfD differs significantly between healthy controls and Alzheimer's disease patients, and that it complements common existing metrics in diagnostic prediction. Our visualization method also allows incorporation of other less common metrics-including the order that words are recalled, repetitions of words within a list, and out-of-category intrusions. Additionally, we show that these plots can be used to visualize and compare aggregate recall data at the group level. These methods can improve understanding of verbal fluency deficits observed in various neuropsychiatric and neurological disorders.

Keywords: Alzheimer’s disease; data visualization; recall data; recurrence plots; verbal fluency.

FIGURE 1

Basic features of recurrence plots. Basic visualization principles for recurrence plots of recall data: one sequence of words is plotted along one axis and another along the other axis; areas of similarity are shaded using dark blue points. In semantic fluency the two lists compared could be taken from two different time points when the task was performed to track progress, whereas for list learning the lists would be the actual list compared to the participant’s recalled sequence. Identical lists fill the diagonal (A), whereas lists that are increasingly different look more scattered (B,C).

FIGURE 2

Basic features of semantic fluency visualizations. (A) The first sequence (chronologically) is plotted on the x-axis and the second on the y-axis. Areas of similarity are shaded in blue. Items present in one sequence but forgotten in the other are indicated by orange points on the corresponding axis, i.e., orange points on the x-axis indicate items present in the first (x-axis) list but missing from the second (y-axis) list. Repeated items are indicated by green arrows and green item labels. For semantic fluency data specifically, invalid (out-of-category) items, also referred to as intrusions, are indicated by a red “x” and asterisk. Repetitions and out-of-category items can occur as words present in both lists (blue points) or just in one list (orange), so these markers are overlaid on the appropriate color point. (B) Changes in sequence length are easily visualized via the aspect ratios of the plots. Square plots correspond to no change, landscape-oriented rectangles (right) correspond to the second sequence being shorter in length, and portrait-oriented rectangles (left) correspond to the second sequence being longer.

FIGURE 3

Interactive features of visualizations. The plots can be made interactive to facilitate usage. Hovering over a point shows the identity of the items that it corresponds to as well as salient features, such as repeated or invalid items.

FIGURE 4

Visualizing group-level comparisons of fluency data. (A) Cumulative plots of every chronologically adjacent pair of sequences (i.e., a sequence from one clinic visit paired with one from the next) from the same participant from visits where the participant was diagnosed as healthy control. Individual similarity matrices (where 1 indicates a position of overlap between the sequences and 0 indicates no overlap) are added together and then scaled (by dividing by the total number of matrices or plots in each group). Scale bar thus indicates the proportion of matrices where the indicated point overlaps between a participant’s two lists. n = 97 participants, 724 pairs of sequences. (B) Cumulative plots of every chronologically adjacent pair of sequences from the same participant from visits where the participant was diagnosed as Probable AD. Individual similarity matrices are added together and then scaled as described above. n = 61 participants, 221 pairs of sequences. (C) Subtraction of the cumulative scaled plot of healthy control participants (A) minus the cumulative plot of Probable AD participants (B). Scale bar indicates how much more likely a point is to belong to the overall control (pink) or ProbAD (blue) group pattern. Pink areas correspond to relatively stronger healthy control patterns (controls tend to have more lists that overlap in these areas) and blue colors correspond to stronger Probable AD patterns (ProbAD participants tend to have more lists that overlap in these areas).