Artificial Intelligence in Molecular Imaging: Predicting Parkinson's Risk in REM Sleep Behavior Disorder

Not Applicable

Recruiting

• Conditions: Parkinson Disease; REM Sleep Behavior Disorder; Dementia, Lewy Body
• Interventions: Device: PET/CT with 18-FDG; Device: MRI

• Registration Number: NCT06629207
• Lead Sponsor: Insel Gruppe AG, University Hospital Bern

Brief Summary

The study aims to systematically document the course of REM sleep behavior disorder (RBD) and investigate possible clinical and imaging biomarkers for disease progression and conversion risk to Parkinson's disease (PD), dementia with Lewy bodies (DLB), and multiple system atrophy (MSA). The study will use artificial intelligence to analyze imaging and develop a reliable method to predict and stratify patients approaching conversion to overt a-synucleinopathy. Participants will be clinically evaluated and 2 imaging procedures will be done.

Detailed Description

Not available

Study Timeline

• Study First Submitted: 2024-10-04
• Study First Submitted QC: 2024-10-04
• Study Start: 2024-10-07
• Study First Posted: 2024-10-08
• Status Verified: 2024-11
• Last Update Submitted: 2024-11-07
• Last Update Posted: 2024-11-08
• Primary Completion: 2026-08-01
• Study Completion: 2026-08-01

Recruitment & Eligibility

• Status: RECRUITING
• Sex: All
• Target Recruitment: 20

Inclusion Criteria

1. Confirmed clinical iRBD diagnosis by movement disorder specialists according to the International Classification of Sleep Disorders
2. Written informed consent

Exclusion Criteria

1. Known diagnosis of PD or other neurodegenerative disorder
2. Unequivocal signs of parkinsonism on examination
3. Narcolepsy or other known causes of RBD
4. Moderate to severe obstructive sleep apnea
5. Abnormal neurological or MRI examination

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: SINGLE_GROUP

Arm && Interventions

Group	Intervention	Description
NUK-RB Study	PET/CT with 18-FDG	-
NUK-RB Study	MRI	-

Primary Outcome Measures

Name	Time	Method
Assessment of Deep Learning Model Accuracy in Predicting Neurodegenerative Conversion in isolated REM sleep behavior disorder (iRBD) through Early Biomarker Detection	From enrollment to end of follow-up period, expected to be 48 months	The investigators aim to evaluate the predictive accuracy of a deep learning model in identifying patients with iRBD who will progress to a neurodegenerative disorder. The primary outcome will assess the model's sensitivity in detecting early imaging biomarkers linked to disease progression, with the goal of enabling earlier intervention and improving long-term outcomes.

Secondary Outcome Measures

Name	Time	Method
Comparison of the Estimated versus Observed Annual Conversion Risk of Isolated Rapid Eye Movement Behavior Disorder (iRBD) to Neurodegenerative Disorders	From enrollment to end of follow-up period, expected to be 48 months	The investigators aim to compare the estimated annual conversion risk of 6.3% in patients with iRBD to Parkinson's disease or another overt alpha-synucleinopathy with the conversion rates observed in the study.
Evaluation of Deep Learning Model Accuracy in Predicting Conversion of Isolated REM Sleep Behavior Disorder (iRBD) to Parkinson's Disease	From enrollment to end of follow-up period, expected to be 48 months	The investigators aim to evaluate the accuracy, receiver operating characteristic curves and area under the curve, specificity, and positive and negative predictive values of the applied deep learning method, predicting the conversion risk from iRBD to Parkinson's disease or another overt alpha-synucleinopathy.

Trial Locations

Locations (1)

Inselspital, University Clinic for Nuclear Medicine; 🇨🇭 Bern, Switzerland