Journal Article

FZJ-2026-04872

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Fully-automated sleep staging for Parkinson’s disease and isolated REM sleep behavior disorder

Strøm, J. (First author) ; Skjærbæk, C. (Corresponding author) ; Bertelsen, N. B. ; Simonsen, S. T. ; Okkels, N. ; Bertram, D. ; Röttgen, S. ; Kufer, K. ; Mikkelsen, K. B. ; Otto, M. ; Jennum, P. J. ; Borghammer, P. ; Sommerauer, M.FZJ* ; Kidmose, P.

2026
Macmillan Publishers Limited [Basingstoke]

This record in other databases:  

Please use a persistent id in citations: doi:10.1038/s41746-026-02946-2  doi:10.34734/FZJ-2026-04872

Abstract: Isolated REM sleep behavior disorder (iRBD) is a key prodromal marker of Parkinson’s disease (PD). Video-polysomnography (vPSG) remains the diagnostic gold standard, but manual sleep staging is particularly time-consuming and challenging in neurodegenerative disease. We adapted U-Sleep, a deep neural network, for automated sleep staging in PD and iRBD. A pretrained model (PUB, 19,236 PSGs), was finetuned on multicenter datasets (PACE, CBC: 112 PD, 138 iRBD, 89 controls) and evaluated on a clinical hold-out (DCSM: 81 PD, 36 iRBD, 87 controls). Predictors of staging agreement were analyzed, and low-agreement recordings were blindly rescored. Confidence-based thresholds were applied to enhance REM detection. The pretrained model achieved κ = 0.66 in PACE/CBC, improving to κ = 0.74 after finetuning (p < 0.001). In the hold-out, mean κ increased from 0.60 to 0.64 (p < 0.001). Site-specific finetuning provided minimal benefit. Confidence was a significant predictor of Cohen’s κ (p < 0.001). Recordings with low model agreement also showed low human interrater agreement. Applying a confidence threshold increased REM precision from 85 to 95.6%, preserving sufficient REM sleep in 96% of subjects. This publicly available model achieves human-level agreement enabling scalable, standardized PSG analysis with model-derived confidence as a tool for further refinements.Subject terms: Diseases, Medical research, Neurology, Neuroscience

Note: This study was partly funded by Innovation Fund Denmark through the“Progression Assessment in Neurodegenerative Disorders of Ageing(PANDA)” project (Case no.: 2077-00030B). M.S. received funding from theprogram “Netzwerke 2021”, an initiative of the Ministry of Culture andScience of the State of Northrhine Westphalia, the Federal Ministry ofResearch, Technology and Space (BMFTR) under the funding code (FKZ):01EO2107 and funding under the umbrella of the Partnership Fostering aEuropean Research Area for Health (ERA4Health) (GA N° 101095426 of theEU Horizon Europe Research and Innovation Programme), and theEuropean Research Council (ID 10116958). The authors thank AntoniaBuchal for her assistance with datamanagement of theCBCdataset. P.B. isfunded by research grants from Lundbeck Foundation (R359-2020-2533,R491-2024-1966) and Michael J Fox Foundation (MJFF-022856)

---

Contributing Institute(s):

1. Kognitive Neurowissenschaften (INM-3)

Research Program(s):

1. 5252 - Brain Dysfunction and Plasticity (POF4-525) (POF4-525)

Appears in the scientific report 2026

---

Database coverage:
; ; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF >= 15 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---