EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

The German National Cohort: Ophthalmic Assessment, Baseline Profile, and Potential for Artificial Intelligence–Based Eye Research

Camila Roa, Ansgar Beuse, Alexandra Schweig, Sarah Müller, Klaus Berger, Caroline Brandl, Titus Brinker, Anne Elbrecht, Robert Finger, Gerd Geerling, Karin Halina Greiser, Carsten Grohmann und 15 weitere

Ophthalmology Science · 2026-11 · 6 (11) · 101408

DOI: 10.1016/j.xops.2026.101408 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ophthalmology Science, 2026-11. Verfasst von Camila Roa und 26 weiteren Autor:innen. Beteiligte Einrichtung: Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Leibniz-Gemeinschaft, Bundesministerium für Forschung, Technologie und Raumfahrt, Deutsche Forschungsgemeinschaft.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To describe the ophthalmic examination protocol within the German National Cohort (NAKO)/NAKO Gesundheitsstudie, to report the baseline profile of participants undergoing ophthalmic assessment, and to illustrate the potential as a population-based resource for artificial intelligence (AI) research in eye health.

Design

Baseline analysis of ophthalmic data within the nationwide, population-based multicenter prospective NAKO study.

Participants

Forty-eight thousand four hundred and sixty adults in the ophthalmic level 2 module of 205 053 adults enrolled in NAKO, aged 19-74 years, with a mean age 48.9 ± 12.5 years, and 52.7% were male.

Methods

All participants underwent standardized biomedical examinations and detailed questionnaire-based data collection, including nondilated color fundus imaging, visual acuity testing, and a brief ocular history. Ocular health was summarized using descriptive statistics. Fundus image quality and morphological features (e.g., cup-to-disc ratio and arteriolar-to-venular ratio) were assessed using open-source deep learning models. Standard deep learning architectures were trained on the fundus images to predict age, sex, and blood pressure. Main Outcome Measures: Percentage of fundus images graded as good quality; mean absolute error (MAE) for age and blood pressure prediction; accuracy for sex prediction.

Results

The analysis includes 48 460 participants who completed the ophthalmic baseline examination of NAKO. Mean visual acuity (logarithm of the minimum angle of resolution) was 0.01 ± 0.20 (left eye, mean ± standard deviation) and 0.03 ± 0.21 (right eye). Self-reported ocular disease prevalence was 4.2% for cataract, 2.0% for glaucoma, and 0.9% for macular degeneration; 68.2% of fundus images were classified as gradable using 4 deep learning-based quality grading models. Morphological features showed systematic differences across age groups. Standard deep learning architectures showed comparative performance to the state-of-the-art for age, sex, and blood pressure prediction (2.96 MAE for age prediction, 0.84 accuracy for sex prediction, and 10.78 and 6.97 MAE for systolic and diastolic blood pressure prediction).

Conclusions

The German National Cohort provides a large-scale, nationwide population-based resource with visual acuity measurements and systemic health indicators, as well as color fundus images in about 50 000 NAKO participants. These data lay the groundwork for studying eye health in the general adult population in Germany and can serve as a strong foundation for developing and validating AI tools in eye health research. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Schlagwörter

Stichwörter der Autor:innen

Artificial intelligenceEpidemiologyFundus imageProspective cohort studyQuality control

Autor:innen und Institutionen

  • Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany.
  • Tübingen AI Center, University of Tübingen, Tübingen, Germany.
  • Department of Ophthalmology, University Medical Center Hamburg-Eppendorf (UKE), Hamburg, Germany.
  • University Eye Hospital, Centre for Ophthalmology, University of Tübingen, Tübingen, Germany.
  • Institute of Epidemiology and Social Medicine, University of Münster, Münster, Germany.
  • Department of Genetic Epidemiology, University of Regensburg, Regensburg, Germany.

Förderung

  • Leibniz-Gemeinschaft
  • Bundesministerium für Forschung, Technologie und Raumfahrt
  • Deutsche Forschungsgemeinschaft
  • Hertie Foundation
  • Helmholtz Association

Zitieren

APA

Roa, C., Beuse, A., Schweig, A., Müller, S., Berger, K., Brandl, C., Brinker, T., Elbrecht, A., Finger, R., Geerling, G., Greiser, K. H., Grohmann, C., Günther, K., Heid, I., Karch, A., Keil, T., Krepel, J., Leitzmann, M., Meinke-Franze, C., …, & Berens, P. (2026). The German National Cohort: Ophthalmic Assessment, Baseline Profile, and Potential for Artificial Intelligence–Based Eye Research. Ophthalmology Science, 6(11), 101408. https://doi.org/10.1016/j.xops.2026.101408

Vancouver

Roa C, Beuse A, Schweig A, Müller S, Berger K, Brandl C, et al. The German National Cohort: Ophthalmic Assessment, Baseline Profile, and Potential for Artificial Intelligence–Based Eye Research. Ophthalmology Science. 2026;6(11):101408. doi:10.1016/j.xops.2026.101408

BibTeX
@article{Roa2026,
  author = {Roa, Camila and Beuse, Ansgar and Schweig, Alexandra and Müller, Sarah and Berger, Klaus and Brandl, Caroline and Brinker, Titus and Elbrecht, Anne and Finger, Robert and Geerling, Gerd and Greiser, Karin Halina and Grohmann, Carsten and Günther, Kathrin and Heid, Iris and Karch, André and Keil, Thomas and Krepel, Jessica and Leitzmann, Michael and Meinke-Franze, Claudia and Peters, Annette and Schipf, Sabine and Schulze, Matthias and Schuster, Alexander K and Willich, Stefan N and Leitritz, Martin A and Ueffing, Marius and Berens, Philipp},
  title = {The German National Cohort: Ophthalmic Assessment, Baseline Profile, and Potential for Artificial Intelligence–Based Eye Research},
  journal = {Ophthalmology Science},
  year = {2026},
  volume = {6},
  number = {11},
  pages = {101408},
  doi = {10.1016/j.xops.2026.101408}
}
Kostenlos starten →