NCT07505394

Efficacy of a Prediction Model-based Algorithm to PREVENT Drug-induced Impulse Control Disorders in Parkinson's Disease

• Status: Not Yet Recruiting
• Phase: N/A
• Study type: Interventional
• Enrollment: 528 (estimated)
• Sponsor: Assistance Publique - Hôpitaux de Paris · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Not accepted

Summary

Impulse control disorders and related behaviors (ICDRBs) are characterized by pathological gambling, compulsive shopping or eating, and hypersexuality, but other related behaviors have been described, e.g. hobbyism, and punding. ICDRBs are frequent in Parkinson's Disease (PD), affecting up to 50% of the patients after 5 years with major medical, social, and legal impact, with life changing consequences for patients and caregivers. The main risk factor is dopaminergic therapy, particularly the cumulative dose of dopamine agonists (DA). On the other hand, the dopaminergic therapy is necessary to control motor symptoms, and DA have demonstrated efficacy in delaying motor complications occurring in PD. Ideally, dopaminergic therapy would have to be adjusted to the individual risk of developing ICRDBs to maximize the benefit/risk ratio of each drug. However, despite several clinical risk factors associated with the risk of ICDRBs (in addition to the dopaminergic therapy), it is still not possible to predict their risk at the individual level, and not every patient treated with dopaminergic medications will develop ICDRBs. A machine learning algorithm to predict ICDRBs, based on clinical data, validated by cross-validation on independent replication cohorts has been developed. The PREVENT-ICD study proposes to test the efficacy of a new application, ICD-Shield, based on an algorithm to predict and prevent ICDs,in a multicenter randomized controlled trial to prevent ICDRBs in PD patients by proposing to the clinician treatment adjustment according to the risk predicted by the algorithm, as compared to the standard of care (SoC)

Detailed description

This Clinical Investigation is a multicenter comparative randomized, controlled, masked (patient and primary criteria evaluator), superiority trial, with 2 parallel groups (Intervention group: Algorithm-guided arm; Control group: standard of care arm). PD patients, treated by DA at inclusion, will be randomized (1:1 ratio) either to the standard of care (SoC) arm, or to the Algorithm-guided arm. They will be recruited at PD expert centers of the NSPARK/FCRIN network. The primary objective is to assess the efficacy of the ICD SHIELD app, a software with a computer-based algorithm assisting clinicians in the prescription of dopaminergic medications, as compared to the standard of care, on the primary endpoint After the inclusion (V0 at M0), four follow-up visits will be performed : V1 at M6, V2 at M12, V3 at M18 and V4 at M24 during outpatients clinics where participants are usually followed. At each follow up visit (M6 to M24), the neurologist will record medical and treatment history, perform neurological examination MDS-UPDRS sections III to IV and CGI-I scale, and will review the MDS-UPDRS sections I and II for potential reassessment/clarification. The PGI scale, PDQ39 questionnaire, MDS-UPDRS sections I and II, and the HAD scales will be filled by the patient. The MoCA scale, ASBPD and QUIP-RS will be performed by a neuropsychologist, or an investigator trained for each scale, according to scoring instructions and blind to treatment arm allocation. Then, the treatment will be adapted by the neurologist, according to the recommendation by the algorithm output or to the clinician sole recommendation depending on the arm in which the patient is randomized. An additional phone call will be made 3 months after the previous visit for a remote checkup to confirm that the prescription change (decreasing or stopping DA) has been properly followed by the patient, if the adjustment to stop completely or decrease DA to a dose equivalent of 40mg of Levodopa was applied. An optional blood sample will be drawn at baseline or at a follow-up visit and sent for DNA extraction and biobanking at the ICM, Pitié-Salpêtrière Hospital, Paris. The duration of recruitment will be 2 years. The duration of participation for each participant will be 2 years, the total duration of the study will be 4 years. The main analysis will be in Intention to treat and will involve a mixed generalized linear model (GLMM) with a logit link adjusted for minimization stratification factors (center, sex, age, Levodopa Equivalent Daily Dose (LEDD) at inclusion).

Conditions

• Parkinson Disease
• Impulse Control Disorder

Interventions

Type	Name	Description
DEVICE	Algorithm-guided group	After the evaluation of the patient and the clinical inputs entered in the ICD SHIELD app including the planned choice of prescription by the neurologist for the next period, the clinician will receive the therapeutic approach recommended by the ICD SHIELD app depending on the output given by the algorithm. The clinician can repeat the use of the app if he/she plans to try various choice of prescription in the app if deemed necessary, but a single use is recommended at each visit. The neurologist will have to follow the recommendation of the ICD SHIELD app as much as possible unless judged inappropriate. The neurologist makes the final decision.
BEHAVIORAL	Standard of Care (SoC) group	In the SoC arm the patient treatment will be adapted by the neurologistbased only on their clinical appreciation and international guidelines.

Timeline

• Start date: 2026-06-01
• Primary completion: 2030-06-01
• Completion: 2030-06-01
• First posted: 2026-04-01
• Last updated: 2026-04-01