Clinically-Oriented Screening Model for Diabetic Retinopathy Severity Grading and Diabetic Macular Edema Detection

Menezes, Sanchika; Chawla, Rohan; Shaikh, Nawazish; Venkatesh, Pradeep; Tandon, Radhika; Rana, Srinivas

doi:10.24963/ijcai.2026/819

Clinically-Oriented Screening Model for Diabetic Retinopathy Severity Grading and Diabetic Macular Edema Detection

Sanchika Menezes, Rohan Chawla, Nawazish Shaikh, Pradeep Venkatesh, Radhika Tandon, Srinivas Rana

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 7362-7370.

https://doi.org/10.24963/ijcai.2026/819

Keywords

Computer Vision: Computer Vision
Multidisciplinary Topics and Applications: Multidisciplinary Topics and Applications
Machine Learning: Machine Learning

Abstract

Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of preventable blindness worldwide. Automated screening tools are critical for timely detection at scale, particularly in low-resource settings where access to ophthalmologists is limited. We propose DRDME-Net, a deployment-driven joint learning framework that formulates DR grading as an ordinal regression task and DME detection via a continuous surrogate, rather than conventional classification. This design yields stable risk scores tightly aligned with operational clinical decision-making thresholds. Evaluation on facility and community cohorts demonstrates that DRDME-Net achieves strong performance across severity boundaries. Insights from an initial feasibility pilot further demonstrate its scalability in real-world workflows. These results highlight the potential of DRDME-Net to expand equitable access to timely detection, reduce preventable vision loss, and provide a practical template for integrating AI into population screening initiatives.

Sanchika Menezes, Rohan Chawla, Nawazish Shaikh, Pradeep Venkatesh, Radhika Tandon, and Srinivas Rana. 2026. Clinically-Oriented Screening Model for Diabetic Retinopathy Severity Grading and Diabetic Macular Edema Detection. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7362–7370. https://doi.org/10.24963/ijcai.2026/819

@inproceedings{ijcai2026p819,
  title     = {Clinically-Oriented Screening Model for Diabetic Retinopathy Severity Grading and Diabetic Macular Edema Detection},
  author    = {Menezes, Sanchika and Chawla, Rohan and Shaikh, Nawazish and Venkatesh, Pradeep and Tandon, Radhika and Rana, Srinivas},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7362--7370},
  year      = {2026},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2026/819},
  url       = {https://doi.org/10.24963/ijcai.2026/819},
}

TY  - CPAPER
TI  - Clinically-Oriented Screening Model for Diabetic Retinopathy Severity Grading and Diabetic Macular Edema Detection
AU  - Menezes, Sanchika
AU  - Chawla, Rohan
AU  - Shaikh, Nawazish
AU  - Venkatesh, Pradeep
AU  - Tandon, Radhika
AU  - Rana, Srinivas
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7362
EP  - 7370
DO  - 10.24963/ijcai.2026/819
UR  - https://doi.org/10.24963/ijcai.2026/819
ER  -