AI-Assisted OCT Clinical Phenotypes of Diabetic Macular Edema: A Large Cohort Clustering Study
Journal of Clinical Medicine · 07.11.2025 · 14 (22) · 7893
DOI: 10.3390/jcm14227893 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 07.11.2025. Verfasst von Edoardo Midena und 53 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, University of Padova, 35100 Padova, Italy. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Purpose
To characterize, using clustering analysis, the OCT morphological and clinical phenotypes of diabetic macular edema (DME) in a very large population (>2000 DME eyes) using standardized and validated OCT-based biomarkers.
Methods
A cross-sectional study was conducted on OCT scans collected from 2355 eyes of 1688 patients with DME and performed during real-world clinical practice. OCT scans were automatically analyzed by a software able to automatically quantify OCT key biomarkers: intraretinal fluid (IRF), subretinal fluid (SRF), hyperreflective retinal foci (I-HRF), and external limiting membrane (ELM) and ellipsoid zone (EZ) interruption. Clustering analysis was performed using the above-mentioned biomarkers, including the distribution of IRF across the three ETDRS rings.
Results
The overall population was predominantly composed of type 2 diabetes patients (89%), with a mean diabetes duration of 15.6 ± 10.7 years and mean best corrected visual acuity (BCVA) of 63 ± 18 ETDRS letters. Multivariate clustering identified four morphological phenotypes with distinct patterns of fluid distribution associated with different I-HRF counts, SRF volume, and percentages of ELM/EZ integrity (p < 0.0001).
Conclusions
This large OCT analysis identified distinct morphological subtypes of DME, confirming the clinical relevance of key imaging biomarkers. The distribution and severity of DME features differ among clusters, supporting the importance of OCT-based phenotyping in tailoring treatment strategies and understanding disease evolution.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ophthalmology, University of Padova, 35100 Padova, Italy.
- IRCCS-Fondazione Bietti, 00184 Rome, Italy.
- Department of Experimental and Clinical Medicine, Polytechnic University of Marche, 60121 Ancona, Italy.
- Ophthalmology Clinic, Department of Medicine and Science of Ageing, "G. d'Annunzio" University Chieti-Pescara, 66100 Chieti, Italy.
- Ophthalmology, Department of Surgical, Medical, Molecular Pathology and Clinical Care Medicine, University of Pisa, 56126 Pisa, Italy.
- Department of Medicine-Ophthalmology, University of Udine, 33100 Udine, Italy.
ORCID-Profile: Edoardo Midena, Marco Lupidi, Lisa Toto, Giuseppe Covello, Daniele Veritti, Elisabetta Pilotto, Michele Figus, Giulia Midena, Luca Danieli, Enrico Borrelli, Michele Reibaldi, Simone Donati, Paolo Melillo, Paolo Lanzetta, Carlo Cagini, Chiara Maria Eandi, Vincenzo Scorcia, Ciro Costagliola, Gilda Cennamo, Paolo Mora, Roberto Dell'Omo, Marzia Affatato, Marco Nassisi, Francesco Viola, Francesco Cappellani, Giuseppe Giannaccare, Maria Oliva Grassi, Donatella Musetti, Valentina Folegani, Alessandro Invernizzi, Tommaso Bacci, Marco Lombardo, Nicola Valsecchi, Luisa Frizziero
Zitieren
APA
Midena, E., Lupidi, M., Toto, L., Covello, G., Veritti, D., Pilotto, E., Cicinelli, M. V., Lattanzio, R., Figus, M., Midena, G., Danieli, L., Borrelli, E., Reibaldi, M., Tognetto, D., Inferrera, L., Donati, S., Rossi, S., Melillo, P., Lanzetta, P., …, & Frizziero, L. (2025). AI-Assisted OCT Clinical Phenotypes of Diabetic Macular Edema: A Large Cohort Clustering Study. Journal of Clinical Medicine, 14(22), 7893. https://doi.org/10.3390/jcm14227893
Vancouver
Midena E, Lupidi M, Toto L, Covello G, Veritti D, Pilotto E, et al. AI-Assisted OCT Clinical Phenotypes of Diabetic Macular Edema: A Large Cohort Clustering Study. Journal of Clinical Medicine. 2025;14(22):7893. doi:10.3390/jcm14227893
BibTeX
@article{Midena2025,
author = {Midena, Edoardo and Lupidi, Marco and Toto, Lisa and Covello, Giuseppe and Veritti, Daniele and Pilotto, Elisabetta and Cicinelli, Maria Vittoria and Lattanzio, Rosangela and Figus, Michele and Midena, Giulia and Danieli, Luca and Borrelli, Enrico and Reibaldi, Michele and Tognetto, Daniele and Inferrera, Leandro and Donati, Simone and Rossi, Settimio and Melillo, Paolo and Lanzetta, Paolo and Sarao, Valentina and Gregori, Giulia and Cagini, Carlo and Eandi, Chiara Maria and Carnevali, Adriano and Scorcia, Vincenzo and Maggio, Emilia and Pertile, Grazia and Costagliola, Ciro and Cennamo, Gilda and Mora, Paolo and Dell'Omo, Roberto and Affatato, Marzia and Passamonti, Marzia and Parravano, Mariacristina and Lassandro, Nicola Vito and Nassisi, Marco and Viola, Francesco and Castellino, Niccolò and Cappellani, Francesco and Giannaccare, Giuseppe and Boscia, Francesco and Grassi, Maria Oliva and Musetti, Donatella and Folegani, Valentina and Invernizzi, Alessandro and Rossetti, Luca and Bacci, Tommaso and Ricci, Federico and Lombardo, Marco and Romano, Mary and Valsecchi, Nicola and Coppola, Michele and Cavarzeran, Fabiano and Frizziero, Luisa},
title = {AI-Assisted OCT Clinical Phenotypes of Diabetic Macular Edema: A Large Cohort Clustering Study},
journal = {Journal of Clinical Medicine},
year = {2025},
volume = {14},
number = {22},
pages = {7893},
doi = {10.3390/jcm14227893}
}
EUVIMED