Active and resting motor threshold are efficiently obtained with adaptive threshold hunting

Abstract

Transcranial magnetic studies typically rely on measures of active and resting motor threshold (i.e. AMT, RMT). Previous work has demonstrated that adaptive threshold hunting approaches are efficient for estimating RMT. To date, no study has compared motor threshold estimation approaches for measures of AMT, yet this measure is fundamental in transcranial magnetic stimulation (TMS) studies that probe intracortical circuits. The present study compared two methods for acquiring AMT and RMT: the Rossini-Rothwell (R-R) relative-frequency estimation method and an adaptive threshold-hunting method based on maximum-likelihood parameter estimation by sequential testing (ML-PEST). AMT and RMT were quantified via the R-R and ML-PEST methods in 15 healthy right-handed participants in an experimenter-blinded within-subject study design. AMT and RMT estimations obtained with both the R-R and ML-PEST approaches were not different, with strong intraclass correlation and good limits of agreement. However, ML-PEST required 17 and 15 fewer stimuli than the R-R method for the AMT and RMT estimation, respectively. ML-PEST is effective in reducing the number of TMS pulses required to estimate AMT and RMT without compromising the accuracy of these estimates. Using ML-PEST to estimate AMT and RMT increases the efficiency of the TMS experiment as it reduces the number of pulses to acquire these measures without compromising accuracy. The benefits of using the ML-PEST approach are amplified when multiple target muscles are tested within a session.

Fig 1. Comparison of RR and ML-PEST approach.

(A) Comparison of the mean MSO using different testing conditions: the group-averaged MSO obtained for R-R_AMT and ML-PEST_AMT demonstrating no significant difference. (B) Limits of agreement between R-R_AMT and ML-PEST_AMT using a Bland-Altman plot demonstrating good agreement with optimal analysis for these data. (C) Scatter plot demonstrating relationship between R-R_AMT and ML-PEST_AMT also confirming similarities between estimation tools. (D) Comparison of the mean MSO using different testing conditions: the group-averaged MSO obtained for R-R_RMT and ML-PEST_RMT demonstrating no significant difference. (E) Limits of agreement between R-R_RMT and ML-PEST_RMT using a Bland-Altman plot demonstrating good agreement with optimal analysis for these data. (F) Scatter plot demonstrating relationship between R-R_RMT and ML-PEST_RMT also confirming similarities between estimation tools. Data from participant 12, shown with a triangle, was not included in any statistical analyses.