Recent research has provided insights into how artificial intelligence (AI) technology is making remarkable progress in the early identification of serious eye inflammation, especially in patients with neovascular age-related macular degeneration (nAMD). A study conducted by a team of researchers from Emory AI.Health and Cleveland Clinic has demonstrated promising outcomes in utilizing machine learning in combination with precision medicine to forecast which patients may develop eye inflammation as a severe side effect of anti-VEGF drugs.
As detailed in the Heliyon journal, the researchers examined images of 67 eyes from a retrospective clinical trial involving nAMD patients. By extracting specific texture-based features from routine optical coherence tomography (OCT) scans, the researchers identified patterns in eye scan images that indicated inflammation before it became clinically apparent. The machine learning model developed by Emory AI.Health achieved an accuracy rate of 76% before anti-VEGF treatment and 81% at the time of injection, highlighting its potential as a valuable tool for early detection.
Anant Madabhushi, Ph.D., executive director of Emory AI.Health and principal investigator of the study, conveyed the personal significance of the research, noting that “Macular degeneration is personal to me because my father suffers from it. As our population ages, more people will experience nAMD. Anti-VEGF agents can slow down macular degeneration but come with risks.” Madabhushi also underscored the possible impact of the study on clinical decision-making, suggesting that the data provides valuable insights for clinicians to make better treatment decisions, potentially reducing the dosage or combining these agents with anti-inflammatory drugs to prevent severe complications.
Sudeshna Sil Kar, Ph.D., the primary author of the study and associate scientist at Emory AI.Health, stressed the validation of their AI algorithms in a retrospective clinical trial and the potential of precision medicine in ophthalmology. Looking ahead, Kar expressed hope in incorporating their algorithms in prospective clinical trials to identify patients likely to develop adverse events in real-time.
For further details on the study, the publication “Optical coherence tomography-derived texture-based radiomics features identify eyes with intraocular inflammation in the HAWK clinical trial” in Heliyon (2024) by Sudeshna Sil Kar et al provides additional information. DOI: 10.1016/j.heliyon.2024.e32232.
Citation: AI technology advances early detection of severe eye inflammation, new research shows (2024, July 9) retrieved 9 July 2024 from https://medicalxpress.com/news/2024-07-ai-technology-advances-early-severe.html