Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease

Abstract In this uncontrolled, open-label exploratory clinical study, the authors explore the potential of blink data as a digital biomarker for estimating clinical indices of Parkinson’s disease (PD) using a machine learning approach. Blink data were collected from 20 patients with PD before and af...

Full description

Saved in:
Bibliographic Details
Main Authors: Noriko Nishikawa, Shin Tejima, Daiki Kamiyama, Mitsumasa Kurita, Koshi Yamamoto, Satoki Imai, Wataru Sako, Genko Oyama, Taku Hatano, Nobutaka Hattori
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Parkinson's Disease
Online Access:https://doi.org/10.1038/s41531-025-01094-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226474838556672
author Noriko Nishikawa
Shin Tejima
Daiki Kamiyama
Mitsumasa Kurita
Koshi Yamamoto
Satoki Imai
Wataru Sako
Genko Oyama
Taku Hatano
Nobutaka Hattori
author_facet Noriko Nishikawa
Shin Tejima
Daiki Kamiyama
Mitsumasa Kurita
Koshi Yamamoto
Satoki Imai
Wataru Sako
Genko Oyama
Taku Hatano
Nobutaka Hattori
author_sort Noriko Nishikawa
collection DOAJ
description Abstract In this uncontrolled, open-label exploratory clinical study, the authors explore the potential of blink data as a digital biomarker for estimating clinical indices of Parkinson’s disease (PD) using a machine learning approach. Blink data were collected from 20 patients with PD before and after (up to 4 h) L-dopa/decarboxylase inhibitor administration. Concurrent assessments of patient diary-based ON/OFF and dyskinesia, L-dopa plasma concentration, and MDS-UPDRS Part III scores were conducted at 30 min intervals. The models were developed to predict clinical symptoms based on blink data collected at 3 min intervals. The most effective post-processing models accurately predicted the ON/OFF states (mean area under the receiver operating characteristic curve (AUCROC) = 0.87) and the presence of dyskinesia (mean AUCROC = 0.84). They also moderately predicted MDS-UPDRS Part III scores (mean Spearman’s correlation ρ = 0.54) and plasma L-dopa concentrations (ρ = 0.57). Our findings highlight the potential of the spontaneous eye blink as a noninvasive, real-time digital biomarker for PD.
format Article
id doaj-art-0ef1e20f64ae4330be9887f979e0a834
institution Kabale University
issn 2373-8057
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Parkinson's Disease
spelling doaj-art-0ef1e20f64ae4330be9887f979e0a8342025-08-24T11:14:35ZengNature Portfolionpj Parkinson's Disease2373-80572025-08-0111111210.1038/s41531-025-01094-wSpontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s diseaseNoriko Nishikawa0Shin Tejima1Daiki Kamiyama2Mitsumasa Kurita3Koshi Yamamoto4Satoki Imai5Wataru Sako6Genko Oyama7Taku Hatano8Nobutaka Hattori9Department of Neurology, Juntendo University School of MedicineSumitomo Pharma Co., Ltd.Department of Neurology, Juntendo University School of MedicineSumitomo Pharma Co., Ltd.Sumitomo Pharma Co., Ltd.Sumitomo Pharma Co., Ltd.Department of Neurology, Juntendo University School of MedicineDepartment of Neurology, Juntendo University School of MedicineDepartment of Neurology, Juntendo University School of MedicineDepartment of Neurology, Juntendo University School of MedicineAbstract In this uncontrolled, open-label exploratory clinical study, the authors explore the potential of blink data as a digital biomarker for estimating clinical indices of Parkinson’s disease (PD) using a machine learning approach. Blink data were collected from 20 patients with PD before and after (up to 4 h) L-dopa/decarboxylase inhibitor administration. Concurrent assessments of patient diary-based ON/OFF and dyskinesia, L-dopa plasma concentration, and MDS-UPDRS Part III scores were conducted at 30 min intervals. The models were developed to predict clinical symptoms based on blink data collected at 3 min intervals. The most effective post-processing models accurately predicted the ON/OFF states (mean area under the receiver operating characteristic curve (AUCROC) = 0.87) and the presence of dyskinesia (mean AUCROC = 0.84). They also moderately predicted MDS-UPDRS Part III scores (mean Spearman’s correlation ρ = 0.54) and plasma L-dopa concentrations (ρ = 0.57). Our findings highlight the potential of the spontaneous eye blink as a noninvasive, real-time digital biomarker for PD.https://doi.org/10.1038/s41531-025-01094-w
spellingShingle Noriko Nishikawa
Shin Tejima
Daiki Kamiyama
Mitsumasa Kurita
Koshi Yamamoto
Satoki Imai
Wataru Sako
Genko Oyama
Taku Hatano
Nobutaka Hattori
Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
npj Parkinson's Disease
title Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
title_full Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
title_fullStr Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
title_full_unstemmed Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
title_short Spontaneous eye blink-based machine learning for tracking clinical fluctuations in Parkinson’s disease
title_sort spontaneous eye blink based machine learning for tracking clinical fluctuations in parkinson s disease
url https://doi.org/10.1038/s41531-025-01094-w
work_keys_str_mv AT norikonishikawa spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT shintejima spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT daikikamiyama spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT mitsumasakurita spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT koshiyamamoto spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT satokiimai spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT watarusako spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT genkooyama spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT takuhatano spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease
AT nobutakahattori spontaneouseyeblinkbasedmachinelearningfortrackingclinicalfluctuationsinparkinsonsdisease