Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 59 min ago
Peer-reviewedCC BY 4.0Cells

Artificial Intelligence as a Catalyst for Cell-Based Therapies in Retinal Disease

  • Girish K. Srivastava1,2,3
  • Priyank Shukla4
  • Sara Crespo Millas5
  • Yogeswaran Lokanathan3,6
6 affiliations
  1. 1Departamento de Cirugía, Oftalmología, Otorrinolaringología y Fisioterapia, Facultad de Medicina, Universidad de Valladolid, 47003 Valladolid, Spain
  2. 2Instituto Universitario de Oftalmobiología Aplicada (IOBA), Universidad de Valladolid, 47011 Valladolid, Spain
  3. 3Department of Tissue Engineering & Regenerative Medicine (DTERM), Faculty of Medicine, Universiti Kebangsaan Malaysia, Kuala Lumpur 56000, Malaysia
  4. 4Personalised Medicine Centre, School of Medicine, Ulster University, C-TRIC Building, Altnagelvin Area Hospital, Glenshane Road, Londonderry BT47 6SB, UK
  5. 5Hospital Clínico Universitario de Valladolid, 47003 Valladolid, Spain
  6. 6Advance Bioactive Materials-Cells UKM Research Group, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
Read full textPDFDOICite

Abstract

Retinal degenerative diseases, including age-related macular degeneration (AMD), retinitis pigmentosa (RP), and Stargardt disease, represent leading causes of irreversible vision loss worldwide, collectively affecting hundreds of millions of people. Cell-based therapies, particularly those leveraging induced pluripotent stem cells (iPSCs), retinal pigment epithelium (RPE) transplantation, and CRISPR-Cas9 gene editing, have emerged as promising treatment modalities that may preserve, replace, or partially restore retinal function. However, these approaches face significant challenges in patient stratification, manufacturing consistency, surgical precision, and long-term outcome monitoring. Artificial intelligence (AI), encompassing machine learning (ML), deep learning (DL), and computer vision, is increasingly being integrated across the cell therapy pipeline to address these limitations. This review comprehensively explores the role of AI in enhancing cell-based retinal therapies, spanning disease diagnosis and patient selection, stem cell quality control and differentiation optimization, CRISPR off-target detection, retinal organoid characterization, scalable manufacturing, and post-transplantation monitoring through multimodal retinal imaging. Throughout, we distinguish direct retinal cell-therapy evidence from retinal-adjacent, cross-domain, and conceptual evidence. We also propose an AI-powered end-to-end pipeline that connects patient profiling through gene editing, cell production, and transplantation to longitudinal outcomes tracking (a forward-looking framework that needs to be clinically validated in future). While AI offers powerful tools to enhance efficacy, reproducibility, and personalization, it does not replace the clinical and biological foundations of cell therapy. Critical challenges remain, including data scarcity, algorithmic interpretability, regulatory compliance, and clinical validation. This review concludes that the strategic integration of AI has plausible potential to become supportive infrastructure for scalable and reproducible cell-based treatments for retinal diseases, although its necessity has not been demonstrated and prospective clinical validation is still required, and biological insight and rigorous empirical verification remain fundamental.

Related

  1. Artificial intelligence-based diagnostic model construction and quantitative analysis of retinal vein occlusion lesions using color fundus photographs
    Wenjuan Wu, Li Sun, Xingye Wang +9
    Frontiers in cell and developmental biologyPeer-reviewedCC BYFull textGeneral biochemistryEurope PMC
  2. Regenerative therapies using pluripotent stem cell-derived retinal organoids
    Michiko Mandai
    Taiwan Journal of OphthalmologyPeer-reviewedCC BY-NC-NDFull text1 citedMolecular biology & gene regulationDOAJ
  3. Editorial: Decoding the gut-brain axis: implications for neurodegenerative disease therapies
    R. M. Damian Holsinger, R. M. Damian Holsinger
    Frontiers in Aging NeurosciencePeer-reviewedCC BYFull textMolecular biology & gene regulationDOAJ
  4. The First 40 Years of Molecular Ophthalmology Part One: Inherited Retinal Disease: The 2026 Friedenwald Lecture
    Edwin M. Stone
    Investigative Ophthalmology & Visual SciencePeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationPMC
  5. iPSC-derived RPE and retinal organoids from two phenotypically different Stargardt disease patients show differences in ABCA4 function
    Arnau Navinés-Ferrer, Pilar Méndez-Vendrell, Laura Siles +3
    iSciencePeer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCell biologyCell PressCrossrefPMC

Cite

BibTeXRIS
BibTeX
@article{srivastava2026artificial,
  title = {{Artificial Intelligence as a Catalyst for Cell-Based Therapies in Retinal Disease}},
  author = {Girish K. Srivastava and Priyank Shukla and Sara Crespo Millas and Yogeswaran Lokanathan},
  journal = {Cells},
  year = {2026},
  month = oct,
  doi = {10.3390/cells15201887},
  url = {https://www.mdpi.com/2073-4409/15/20/1887},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Artificial Intelligence as a Catalyst for Cell-Based Therapies in Retinal Disease
AU  - Girish K. Srivastava
AU  - Priyank Shukla
AU  - Sara Crespo Millas
AU  - Yogeswaran Lokanathan
PY  - 2026
DA  - 2026/10/16
JO  - Cells
DO  - 10.3390/cells15201887
UR  - https://www.mdpi.com/2073-4409/15/20/1887
AB  - Retinal degenerative diseases, including age-related macular degeneration (AMD), retinitis pigmentosa (RP), and Stargardt disease, represent leading causes of irreversible vision loss worldwide, collectively affecting hundreds of millions of people. Cell-based therapies, particularly those leveraging induced pluripotent stem cells (iPSCs), retinal pigment epithelium (RPE) transplantation, and CRISPR-Cas9 gene editing, have emerged as promising treatment modalities that may preserve, replace, or partially restore retinal function. However, these approaches face significant challenges in patient stratification, manufacturing consistency, surgical precision, and long-term outcome monitoring. Artificial intelligence (AI), encompassing machine learning (ML), deep learning (DL), and computer vision, is increasingly being integrated across the cell therapy pipeline to address these limitations. This review comprehensively explores the role of AI in enhancing cell-based retinal therapies, spanning disease diagnosis and patient selection, stem cell quality control and differentiation optimization, CRISPR off-target detection, retinal organoid characterization, scalable manufacturing, and post-transplantation monitoring through multimodal retinal imaging. Throughout, we distinguish direct retinal cell-therapy evidence from retinal-adjacent, cross-domain, and conceptual evidence. We also propose an AI-powered end-to-end pipeline that connects patient profiling through gene editing, cell production, and transplantation to longitudinal outcomes tracking (a forward-looking framework that needs to be clinically validated in future). While AI offers powerful tools to enhance efficacy, reproducibility, and personalization, it does not replace the clinical and biological foundations of cell therapy. Critical challenges remain, including data scarcity, algorithmic interpretability, regulatory compliance, and clinical validation. This review concludes that the strategic integration of AI has plausible potential to become supportive infrastructure for scalable and reproducible cell-based treatments for retinal diseases, although its necessity has not been demonstrated and prospective clinical validation is still required, and biological insight and rigorous empirical verification remain fundamental.
SN  - 2073-4409
ER  -