An improved algorithm for model-based analysis of evoked skin conductance responses

Abstract

Model-based analysis of psychophysiological signals is more robust to noise - compared to standard approaches - and may furnish better predictors of psychological state, given a physiological signal. We have previously established the improved predictive validity of model-based analysis of evoked skin conductance responses to brief stimuli, relative to standard approaches. Here, we consider some technical aspects of the underlying generative model and demonstrate further improvements. Most importantly, harvesting between-subject variability in response shape can improve predictive validity, but only under constraints on plausible response forms. A further improvement is achieved by conditioning the physiological signal with high pass filtering. A general conclusion is that precise modelling of physiological time series does not markedly increase predictive validity; instead, it appears that a more constrained model and optimised data features provide better results, probably through a suppression of physiological fluctuation that is not caused by the experiment.

Keywords: Electrodermal activity (EDA); Galvanic skin response (GSR); General linear convolution model (GLM); Generative model; Model inversion; Skin conductance responses (SCR).

Fig. 1

Step 1: comparison of a linear model for evoked SCR, using different response functions as explained in Section 2. Lower Log Bayes Factors (LBF) indicate higher model evidence for the target model. Upper panel: predictive validity; i.e., ability of estimated SN amplitudes to predict a known sympathetic state, for three contrasts from two experiments, expressed in LBF as negative log likelihood difference between the model in question and a reference model. Several peak scoring methods (PS) are added for illustrative purposes as null models (left of the dashed line). Lower panel: Model Log evidence of the within-subject model, expressed as difference in AIC between the target model and our benchmark model, summed over participants. Abbreviations: PS: SPR (1–4 s) amp – peak scoring amplitude according to the SPR recommendations, using a 1–4 s post-stimulus onset window; PS: SPR (1–4 s) mag – peak scoring magnitude according to the SPR recommendations, using a 1–4 s post-stimulus onset window; PS: SPR (1–3 s) amp – peak scoring amplitude according to the SPR recommendations, using a 1–3 s post-stimulus onset window; PS: SPR (1–4 s) mag – peak scoring magnitude according to the SPR recommendations, using a 1–4 s post-stimulus onset window; PS: peak/baseline – peak scoring magnitude, substracting a 1 s pre-stimulus baseline from the maximum value within a 1–4 s post-stimulus window; SCRF – skin conductance response function (benchmark method); SCRF/time deriv. – skin conductance response function with time derivative; SCRF/time and disp deriv. – skin conductance response function with time and dispersion derivative; FIR 15 s – uninformed finite impulse response function with 15 timebins of 1 s duration; FIR 30 s – uninformed finite impulse response function with 30 timebins of 1 s duration; Cosine nth order – cosine basis set of nth order; SRF – subject-specific response function.

Fig. 2

Step 2: comparison of different unidirectional and bidirectional high pass filters, applied to the data before model inversion. Lower Log Bayes Factors indicate higher target model evidence. All Log Bayes Factors are with respect to our current standard filter, a bidirectional first order Butterworth filter with cut off frequency of 0.0159 Hz.

Fig. 3

Step 3: comparison of several linear with non-linear models for evoked responses. Lower Log Bayes Factors indicate higher target model evidence.