Post-stroke cognitive deficits rarely come alone: Handling co-morbidity in lesion-behaviour mapping

Abstract

Post-stroke behavioural symptoms often correlate and systematically co-occur with each other, either because they share cognitive processes, or because their neural correlates are often damaged together. Thus, neuropsychological symptoms often share variance. Many previous lesion-behaviour mapping studies aimed to methodologically consider this shared variance between neuropsychological variables. A first group of studies controlled the behavioural target variable for the variance explained by one or multiple other variables to obtain a more precise mapping of the target variable. A second group of studies focused on the shared variance of multiple variables itself with the aim to map neural correlates of cognitive processes that are shared between the original variables. In the present study, we tested the validity of these methods by using real lesion data and both real and simulated data sets. We show that the variance that is shared between post-stroke behavioural variables is ambiguous, and that mapping procedures that consider this variance are prone to biases and artefacts. We discuss under which conditions such procedures could still be used and what alternative approaches exist.

Keywords: VLSM; lesion-deficit inference; nuisance regression; principal component analysis; statistical parametric mapping.

Figure 1

Illustration of a possible bias in voxel‐based lesion‐behaviour mapping (VLBM) controlled for a secondary variable. Damage to area T induces the behavioural target behaviour that we want to map in the analysis. A secondary behavioural variable correlates with the target variable; damage to the secondary behaviour's neural correlate S induces this deficit. Both areas T and S are often damaged together. Therefore, an uncontrolled VLBM analysis might not only find area T, but also area S. An imaginable bias when we now control the target variable for the secondary variable is that the VLBM might find areas that are usually damaged together with area T, but not with S. This is the ‘?’ area. The example is chosen arbitrarily and is not intended to correspond to any real study

Figure 2

Experimental pipeline in Experiment 1

Figure 3

Results of Experiment 1, showing results for the four conditions: no control (no C), lesion size control (LSC), second variable control (SVC), and lesion size and second variable control (LS+SVC). Error bars indicate standard deviation. DCoM, distance centres of mass

Figure 4

Example results of Experiment 1 for non‐overlapping ground truth regions in the condition with 70% signal. Statistical maps show statistically significant voxels after maximum statistic permutation control. Colour grading indicates t‐values, with warm red colours indicating higher values. Light blue circles have been added to highlight smaller clusters of significant voxels. a) Ground truth regions for the target symptom (red) and the secondary symptom (blue); b)‐e) permutation‐thresholded VLBM results for b) uncontrolled analysis; c) analysis controlled for the secondary variable; d) analysis controlled for lesion size; e) analysis controlled both for the secondary variable and lesion size

Figure 5

Example results of Experiment 1 for overlapping ground truth regions as in Figure 4. †The analysis in (c), middle column, did not yield positive, but only negative significant findings. These are shown here, but have been removed from the analysis in Experiment 1. ‡The analysis in (c), right column, did not yield significant voxels in the slices shown in the other panels, therefore the shown slices were changed to more anterior slices with positive findings. a) Ground truth regions for the target symptom (red) and the secondary symptom (blue), as well as overlap of both (pink); b)‐e) permutation‐thresholded VLBM results for b) uncontrolled analysis; c) analysis controlled for the secondary variable; d) analysis controlled for lesion size; e) analysis controlled both for the secondary variable and lesion size

Figure 6

Results of Experiment 2, showing (a) the mapping of a common factor of hemiparesis and spatial neglect, and (b) example results of the mapping of common factors in simulated behavioural data that were based on non‐overlapping, non‐adjacent ground truth regions. Analyses in (b) were either controlled for lesion size (LS) or not controlled for lesion size

Figure 7

A graphical causal model of lesion‐deficit relations in a situation where damage to a sub‐region of the vasculature can induce damage to two distinct areas. Damage in each of the two areas can lead to a post‐stroke symptom. One of those is the target symptom that is supposed to be investigated by voxel‐based lesion‐behaviour mapping (VLBM), central to the study is the causal relation between damage to area X and the target symptom, that is, we are interested in mapping the neural correlates of the target symptom. The other symptom highly correlates with the target symptom, and one might consider including it as a covariate into the analysis. However, without any direct causal effect of the covariate symptom on the target symptom (dotted grey line), no actual confounding would be present at all, and covariate control would bias the analysis