Levodopa medication improves incidental sequence learning in Parkinson's disease

Abstract

Empirical evidence suggests that levodopa medication used to treat the motor symptoms of Parkinson's disease (PD) may either improve, impair or not affect specific cognitive processes. This evidence led to the 'dopamine overdose' hypothesis that levodopa medication impairs performance on cognitive tasks if they recruit fronto-striatal circuits which are not yet dopamine-depleted in early PD and as a result the medication leads to an excess of dopamine. This hypothesis has been supported for various learning tasks including conditional associative learning, reversal learning, classification learning and intentional deterministic sequence learning, on all of which PD patients demonstrated significantly worse performance when tested on relative to off dopamine medication. Incidental sequence learning is impaired in PD, but how such learning is affected by dopaminergic therapy remains undetermined. The aim of the current study was to investigate the effect of dopaminergic medication on incidental sequence learning in PD. We used a probabilistic serial reaction time task (SRTT), a sequence learning paradigm considered to make the sequence less apparent and more likely to be learned incidentally rather than intentionally. We compared learning by the same group of PD patients (n=15) on two separate occasions following oral administration of levodopa medication (on state) and after overnight withdrawal of medication (off state). Our results demonstrate for the first time that levodopa medication enhances incidental learning of a probabilistic sequence on the serial reaction time task in PD. However, neither group significantly differed from performance of a control group without a neurological disease, which indicates the importance of within group comparisons for identifying deficits. Levodopa medication enhanced incidental learning by patients with PD on a probabilistic sequence learning paradigm even though the patients were not aware of the existence of the sequence or their acquired knowledge. The results suggest a role in acquiring incidental motor sequence learning for dorsal striatal areas strongly affected by dopamine depletion in early PD.

Keywords: Basal ganglia; Incidental sequence learning; Levodopa medication; Parkinson's disease; Serial reaction time; Striatum.

Fig. 1

Illustration of the button box used with an example of the stimuli presented on the monitor.

Fig. 2

a and b: Mean of the median reaction times in milliseconds (ms) for probable and improbable trials, plotted separately for patients with Parkinson's disease on (2a) and off (2b) levodopa medication across 15 blocks of the Serial RT task. Error bars represent one standard error of the mean.

Fig. 3

a and b. Mean RT difference scores (improbable minus probable reaction times) plotted (a) as an overall mean across blocks for each of the two medication conditions and (b) for blocks 1–15 collapsed across medication conditions.

Fig. 4

Mean number of test chunks completed with either the final item of a triplet from the trained sequence (old) or an untrained sequence (new) on and off levodopa medication. Completions were calculated out of a possible 12 that could have been achieved in the inclusion and exclusion tests. Error bars represent one standard error of the mean.

Fig. 5

Mean recognition ratings for old and new test sequences on and off levodopa medication. Participants responded to 12 old and 12 new sequences and made a recognition judgement for each sequence (1=certain new, 6=certain old).