Neural reinforcement learning signals predict recovery from impulse control disorder in Parkinson’s disease

Background Impulse control disorders (ICD) in Parkinson’s disease (PD) are associated with a heavy burden on patients and caretakers. While recovery can occur, ICD persists in many patients despite optimal management. The basis for this inter-individual variability in recovery is unclear and poses a major challenge to personalized health care. Methods We adopt a computational psychiatry approach and leverage the longitudinal, prospective Personalized Parkinson Project (N=136 persons with PD, within 5 years of diagnosis) to combine dopaminergic learning theory-informed fMRI with machine learning (at baseline) to predict ICD symptom recovery after two years of follow-up. We focused on a change in QUIP-rs across the entire cohort, regardless of an ICD diagnosis. Results Greater reinforcement learning signals at baseline, including those in the ventral striatum, measured while ON medication were associated with greater recovery from impulse control symptoms two years later. These signals accounted for a unique proportion of the relevant variability over and above that explained by other known factors, such as decreases in dopamine agonist use. Conclusions Our results indicate that dopaminergic learning modeling provides opportunities for recovery from ICD symptoms in PD and a proof of principle for combining generative model-based inference of latent learning processes with machine learning-based predictive modeling of variability in clinical symptom recovery trajectories. These findings may inform the development of future biomarker research for evaluating preventive and therapeutic approaches to ICD. In this collection, you can find the codebase that has been used for the analysis in the paper. Unfortunately, we cannot directly share the raw data, due to privacy concerns. A data acquisition request can be send per e-mail to [e-mail].