Visual misperceptions (hallucinations, illusions) are common in Parkinson's disease.

Combined bottom-up and top-down altered processes cause visual misperceptions.

Visual misperceptions are biased towards living beings in Parkinson's disease.

The living being bias stems from impaired top-down control over perception.

Parkinson's disease (PD) patients often report seeing persons or animals rather than objects but this phenomenon remains poorly understood. Here, we use three experimental tasks to confirm such observation and to explore its cognitive mechanisms.

Fourteen PD patients with visual hallucinations (PD-VH), 14 PD patients without visual hallucinations (PD-NVH) and 14 controls with similar cognitive performance were tested using ambiguous stimuli. Ambiguous stimuli were morphs in which visual features from faces and flowers were melted together (Experiments 1 and 2) and a black and white picture where a Dalmatian dog was hidden (Experiment 3). In Experiment 1, participants categorised ambiguous stimuli either as face or flower. In Experiment 2, they were shown an ambiguous stimulus, then a mask, and finally two ambiguous stimuli, one of which was identical to the first stimulus. In this discrimination task, participants chose which of the two last stimuli had been presented before. In Experiment 3, participants guessed the items hidden in the picture. We assessed group differences for categorisation with logistic modelling and computed sensitivity index and criterion psychophysical measures in Experiments 1 and 2. The ratio of living beings identified in the Dalmatian dog task was compared across groups.

In the categorisation task, the PD-VH group tended to use a smaller proportion of visual features (point of subjective equality [PSE] = 41.5%) to label a stimulus as Face compared to PD-NVH (51%) and controls (56.2%). In the discrimination task, criterion c was lower in the PD-VH group compared to controls (c: –0.16 vs. 0.27; P = 0.005). In the Dalmatian dog task, the PD-VH group reported seeing livings beings more frequently than controls (P = 0.040). A bias towards living beings was confirmed in the PD-VH group in the three tasks, and a bias toward non-living beings was measured in controls in the discrimination task.

Observing that controls exhibited bias toward non-living beings in the discrimination task, we suggest that impaired top-down control over perception processes explains the bias toward living beings in PD-VH visual misperceptions.

Parkinson's disease

Illusions

Hallucinations

Psychosis

Perception

© 2026 The Authors. Published by Elsevier Masson SAS.