EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development of a Deep Learning Model to Estimate Anemia from Palpebral Conjunctiva Taken with a Portable Slit-Lamp Microscope

Yo Nakahara, Eisuke Shimizu iD, Takahiro Mizukami iD, Hiroki Nishimura iD, Shintaro Nakayama, Tetsuo Ishikawa iD, Masatoshi Hirayama, Risa Hokama, Kazuhiro Sakurada, Kazuno Negishi iD

Bioengineering · 17.07.2026 · 13 (7) · 824

DOI: 10.3390/bioengineering13070824 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 17.07.2026. Verfasst von Yo Nakahara und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Extended Intelligence for Medicine, The Ishii-Ishibashi Laboratory, Keio University School of Medicine, Tokyo 1608582, Japan. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Science and Technology Agency, Japan Agency for Medical Research and Development, Japan Society for the Promotion of Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Anemia is a common systemic condition associated with adverse maternal, perioperative, and cardiovascular outcomes. Although timely screening is clinically important, diagnosis still relies on invasive blood testing. Palpebral conjunctival pallor has traditionally been used as a noninvasive indicator of anemia, but its diagnostic accuracy remains limited. This study aimed to develop and validate a deep learning system to estimate hemoglobin (Hb) concentration and screen for anemia using palpebral conjunctiva images captured with a smartphone-compatible slit-lamp microscope.

Methods

In this prospective observational study, 225 Japanese participants (20–92 years) underwent conjunctival imaging and blood testing. Palpebral conjunctiva videos were obtained using the Smart Eye Camera. Video frames were processed using automated anterior-segment segmentation and conjunctiva extraction. A ConvNeXt-based regression model was trained to predict Hb values. Anemia was defined using sex-specific Hb thresholds.

Results

From 225 videos, 53,776 frames were extracted, yielding 9903 quality-filtered conjunctiva images (training: 8082; test: 1821). Video-level predicted Hb values moderately correlated with measured Hb (r = 0.42). For anemia screening, frame-level analysis achieved an AUC of 0.75, with accuracy of 0.76, sensitivity of 0.71, and specificity of 0.79. Video-level aggregation achieved 69% accuracy.

Conclusions

Deep learning analysis of palpebral conjunctiva images acquired with a portable slit-lamp microscope demonstrated the feasibility of non-invasive hemoglobin estimation and anemia screening. Although the proposed approach achieved moderate performance, further improvements in model accuracy and prospective multi-center validation are required before clinical implementation.

Schlagwörter

Stichwörter der Autor:innen

ConvNeXtanemiadeep learninghemoglobinpalpebral conjunctivasmart eye camerasmartphone

Autor:innen und Institutionen

  • Department of Extended Intelligence for Medicine, The Ishii-Ishibashi Laboratory, Keio University School of Medicine, Tokyo 1608582, Japan.
  • Medimo Inc., Tokyo 1050001, Japan.
  • OUI Inc., Tokyo 1070062, Japan.
  • Department of Ophthalmology, Keio University School of Medicine, Tokyo 1608582, Japan.
  • Yokohama Keiai Eye Clinic, Yokohama 2400065, Japan.
  • Division of Applied Mathematical Science, RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences, RIKEN, Yokohama 2300045, Japan.

ORCID-Profile: Eisuke Shimizu, Takahiro Mizukami, Hiroki Nishimura, Tetsuo Ishikawa, Kazuno Negishi

Förderung

  • Japan Science and Technology Agency
  • Japan Agency for Medical Research and Development
  • Japan Society for the Promotion of Science
  • New Energy and Industrial Technology Development Organization
  • the Japan Agency for Medical Research and Development
  • Japan Society for the Promotion of Science (JSPS) KAKENHI

Zitieren

APA

Nakahara, Y., Shimizu, E., Mizukami, T., Nishimura, H., Nakayama, S., Ishikawa, T., Hirayama, M., Hokama, R., Sakurada, K., & Negishi, K. (2026). Development of a Deep Learning Model to Estimate Anemia from Palpebral Conjunctiva Taken with a Portable Slit-Lamp Microscope. Bioengineering, 13(7), 824. https://doi.org/10.3390/bioengineering13070824

Vancouver

Nakahara Y, Shimizu E, Mizukami T, Nishimura H, Nakayama S, Ishikawa T, et al. Development of a Deep Learning Model to Estimate Anemia from Palpebral Conjunctiva Taken with a Portable Slit-Lamp Microscope. Bioengineering. 2026;13(7):824. doi:10.3390/bioengineering13070824

BibTeX
@article{Nakahara2026,
  author = {Nakahara, Yo and Shimizu, Eisuke and Mizukami, Takahiro and Nishimura, Hiroki and Nakayama, Shintaro and Ishikawa, Tetsuo and Hirayama, Masatoshi and Hokama, Risa and Sakurada, Kazuhiro and Negishi, Kazuno},
  title = {Development of a Deep Learning Model to Estimate Anemia from Palpebral Conjunctiva Taken with a Portable Slit-Lamp Microscope},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {7},
  pages = {824},
  doi = {10.3390/bioengineering13070824}
}
Kostenlos starten →