Journal Article

A post-hoc analysis of intravitreal aflibercept-treated nAMD patients from ARIES & ALTAIR: predicting treatment intervals and frequency for aflibercept treat-and-extend therapy regimen using machine learning

Aydin, Sökmen, Youssef, Hossam, Takahashi, Kanji, Machewitz, Tobias, Loktyushin, Alexander, Heimes-Bussmann, Britta, Bauer-Steinhusen, Ulrike, Lommatzsch, Albrecht, Petrovic, Ratko, Okada, Annabelle A., Rothaus, Kai, Ohji, Masahito, Gutfleisch, Matthias, Scholz, Paula

2025

Overview

Purpose To predict potential treatment need during treat-and-extend (T&E) anti-vascular endothelial growth factor (VEGF) treatment in neovascular age-related macular degeneration (nAMD) using an artificial intelligence (AI) model trained using transfer learning. Methods ARIES and ALTAIR were randomized controlled Phase 3b/4 trials assessing intravitreal aflibercept (IVT-AFL) in patients with nAMD. Following treatment initiation with three monthly injections of IVT-AFL, treatment intervals were re-assessed continuously during the study based on prespecified criteria. In this post- hoc analysis, spectral domain optical coherence tomography (SD-OCT) scans from Week (Wk) 8 and Wk 16 visits from patients treated with T&E regimens of 2 mg IVT-AFL over 2 years were utilized to predict individual treatment intervals and frequency. Automated image segmentation of the SD-OCT scans was performed, predictive models of treatment intervals and frequency were developed using machine learning or logistic regression methods, and their performance was evaluated using a fivefold cross-validation. A transfer learning technique was used to adapt existing AI models previously trained on a pro-re-nata therapy regimen to the T&E dataset. Results In total, 205 ARIES and 112 ALTAIR patient datasets were used for training and evaluation. The following results were achieved with an AI model trained using transfer learning (for ARIES) and logistic regression (for ALTAIR). For prediction of the first treatment interval (short [< 12 weeks] or long [≥ 12 weeks]) following treatment initiation, at Visit 4 (Wk 16), the AI model achieved an area under the receiver operating characteristic curve (AUC) of 0.87 and 0.78 for ARIES and ALTAIR, respectively. For assessment of the individual frequency of IVT-AFL in the first and second study years, the model achieved an AUC of 0.84 and 0.79, respectively, for ARIES, and 0.79 and 0.78, respectively, for ALTAIR. For prediction of the last intended individual treatment interval at the end of Year 2, the AI model achieved an AUC of 0.74 and 0.77 for ARIES and ALTAIR, respectively. Conclusion AI trained using transfer learning can be used to predict potential treatment needs for anti-VEGF treatment in nAMD based on SD-OCT scans at Wk 8 and Wk 16, supporting medical decisions on interval adjustments and optimizing individualized IVT-AFL treatment regimens. Key messages What is known Due to the high treatment burden associated with frequent clinic visits and anti-vascular endothelial growth factor injections required for the treatment of patients with neovascular age-related macular degeneration (nAMD), it would be beneficial to be able to predict potential future treatment need, at initial stages of treatment. What is new An artificial intelligence (AI) model, previously trained with a real-world pro re nata -treated cohort, can be re-trained and applied to datasets from patients treated with treat-and extend regimens in the clinical study setting to predict potential treatment need. AI may be used to predict potential treatment needs for intravitreal aflibercept treatment in nAMD based on optical coherence tomography scans at Weeks 8 and 16, supporting medical decisions on interval adjustments and optimizing individualized treatment regimens.

• Publisher: Springer Berlin Heidelberg,Springer Nature B.V
• Subject: Accuracy / Age / Aged / Algorithms / Angiogenesis Inhibitors - administration & dosage / Artificial intelligence / Biomarkers / Clinical trials / Datasets / Deep learning / Female / Fluorescein Angiography / Follow-Up Studies / Fundus Oculi / Humans / Image processing / Internet resources / Intravitreal Injections / Learning algorithms / Machine Learning / Macula Lutea - pathology / Macular degeneration / Male / Medicine / Medicine & Public Health / Ophthalmology / Patients / Prediction models / Receptors, Vascular Endothelial Growth Factor - administration & dosage / Receptors, Vascular Endothelial Growth Factor - antagonists & inhibitors / Recombinant Fusion Proteins - administration & dosage / Regression analysis / Retinal Disorders / ROC Curve / Therapeutic applications / Time Factors / Tomography / Tomography, Optical Coherence - methods / Transfer learning / Treatment Outcome / Vascular endothelial growth factor / Vascular Endothelial Growth Factor A - antagonists & inhibitors / Visual Acuity / Wet Macular Degeneration - diagnosis / Wet Macular Degeneration - drug therapy