Association of deep learning-derived optic nerve morphology with Parkinson's disease and drug-induced Parkinsonism: Findings from the LIFE Study
Journal of the Neurological Sciences · 2025
DOI: 10.1016/j.jns.2025.123751 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Neurological Sciences, 2025. Verfasst von Emi Ueda und 10 weiteren Autor:innen. Beteiligte Einrichtung: Center for Cohort Studies, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan; Department of Ophthalmology, Graduate School of Me…. Hauptthemen laut MEDLINE: Deep Learning, Parkinson Disease, Optic Nerve, Parkinson Disease, Secondary. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Japan Science and Technology Agency, Japan Agency for Medical Research and Development, Ministry of Education, Culture, Sports, Science and Technology.
Abstract (Originalsprache)
BACKGROUND: There is a growing need for alternative imaging measures to better understand the neurodegenerative pathology of Parkinson's disease and related conditions, such as drug-induced Parkinsonism. This study investigated the link between optic nerve morphology, specifically, the cup-to-disc ratio, a known neurodegenerative marker, and the presence of Parkinson's disease and drug-induced Parkinsonism in a large-scale, population-based study. METHODS: A total of 14,280 participants aged 40-64 years with available fundus photographs and health data were included from a community-based database of the Longevity Improvement & Fair Evidence (LIFE) Study in Japan. The cup-to-disc ratios were analyzed through deep learning techniques using fundus photographs. Participants were categorized into quartiles based on these measurements. Parkinson's disease and drug-induced Parkinsonism were identified using International Classification of Diseases, 10th Revision codes and prescription records. Odd ratios (ORs) and 95 % confidence intervals (CIs) were estimated using logistic regression models. RESULTS: Among the participants, 131 (0.9 %) had Parkinson's disease, and 152 (1.1 %) had drug-induced Parkinsonism. After adjusting for potential confounders, participants in the highest quartile of cup-to-disc ratio had a significantly higher likelihood of Parkinson's disease compared with those in the lowest quartile (OR = 1.74, 95 % CI = 1.07-2.86, p = 0.02). No significant association was found between cup-to-disc ratio and drug-induced Parkinsonism. CONCLUSIONS: These findings suggest that optic nerve morphology information derived from deep learning analysis of fundus photographs-a noninvasive, convenient, and reproducible method-may help assess specific neurogenerative processes in Parkinson's disease.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Cohort Studies, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan; Department of Ophthalmology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan. Electronic address:…
- Department of Neurology, Neurological Institute, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
- Department of Health Care Administration and Management, Kyushu University Graduate School of Medical Sciences, Fukuoka, Japan.
- Department of Ophthalmology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
- Department of Ophthalmology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan; Department of Epidemiology and Public Health, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
- Laboratory of Clinical Epidemiology, Department of Data Science, Center for Clinical Sciences, Japan Institute for Health Security, Tokyo, Japan.
Förderung
- Japan Science and Technology Agency
- Japan Agency for Medical Research and Development
- Ministry of Education, Culture, Sports, Science and Technology
- Japan Society for the Promotion of Science
Zitieren
APA
Ueda, E., Watanabe, M., Maeda, M., Oda, F., Fujiwara, K., Nakamura, S., Tsuda, Y., Mimura, W., Isobe, N., Sonoda, K. H., & Fukuda, H. (2025). Association of deep learning-derived optic nerve morphology with Parkinson's disease and drug-induced Parkinsonism: Findings from the LIFE Study. Journal of the Neurological Sciences. https://doi.org/10.1016/j.jns.2025.123751
Vancouver
Ueda E, Watanabe M, Maeda M, Oda F, Fujiwara K, Nakamura S, et al. Association of deep learning-derived optic nerve morphology with Parkinson's disease and drug-induced Parkinsonism: Findings from the LIFE Study. Journal of the Neurological Sciences. 2025. doi:10.1016/j.jns.2025.123751
BibTeX
@article{Ueda2025,
author = {Ueda, Emi and Watanabe, Mitsuru and Maeda, Megumi and Oda, Futoshi and Fujiwara, Kohta and Nakamura, Shun and Tsuda, Yuki and Mimura, Wataru and Isobe, Noriko and Sonoda, Koh-Hei and Fukuda, Haruhisa},
title = {Association of deep learning-derived optic nerve morphology with Parkinson's disease and drug-induced Parkinsonism: Findings from the LIFE Study},
journal = {Journal of the Neurological Sciences},
year = {2025},
doi = {10.1016/j.jns.2025.123751}
}
EUVIMED