The Calculation of Language Lateralization Indices in Post-stroke Aphasia: A Comparison of a Standard and a Lesion-Adjusted Formula

Background: The language lateralization index (LI) is a valuable tool in functional magnetic resonance imaging (fMRI) research, especially in people with post-stroke aphasia. However, there is inconsistent consideration for the overlap of lesions with regions of interest (ROls). The purpose of this study was to determine whether standard LI (SLI) and lesion-adjusted LI (LALI) formulae generate different LI values and language lateralization classification for people with post-stroke chronic aphasia. Methods: SLI and LALI were calculated for an event-related (overt) verb generation task in an anterior and a posterior language ROI. Twelve people with aphasia due to a single left-hemispheric infarct (11 right-handed; 1 left-handed; 77.2 +/- 41.7 months post-stroke) were included (eight females; 57 +/- 8.88 years). Spearman correlation coefficients and intraclass correlation coefficients were calculated to determine the relationship of the LI values generated by the SLI and the LALI formulas. Fischer's exact test and a weighted Cohen's Kappa determined the difference in language lateralization classification and agreement in the classification. Spearman correlation was used to examine the relationship between the difference in lateralization values produced by the LALI and SLI calculations with (1) lesion size, (2) the percentage of lesion overlap in each ROI, and (3) aphasia severity. Results: The two calculation methods were highly correlated and produced similar LI Values, yet yielded significantly different classification for language lateralization. Further, a more leftward LI resulted from application of the LALI formula in 10 participants, in either the anterior ROI (n = 3) or the posterior ROI (n = 7). Finally, for the posterior ROI only, significant correlations were revealed between the two calculation methods and the (1) lesion size and (2) percent of overlap with the ROI. Discussion: While both approaches produce highly correlated LI values, differences in activation lateralization between formulas were observed, including changes in lateralization classification. Examination of the issues raised in the current investigation need to be replicated with a larger sample to determine the utility of a LALI formula in predicting behavioral performance; the findings may have implications for understanding and interpreting fMRI data of people with post-stroke aphasia.