# OphthaDT: Generative Digital Twins for Forecasting Visual Acuity Trajectories in Ophthalmology

arXiv: https://arxiv.org/abs/2606.22101 · HTML: https://mlsanity.com/paper/2606.22101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 20 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MOTOR: A Time-To-Event Foundation Model For Structured Medical Records](https://mlsanity.com/paper/2301.03150/) (2023)
- [GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learning](https://mlsanity.com/paper/2207.09858/) (2022)
- [Large Language Models are Powerful Electronic Health Record Encoders](https://mlsanity.com/paper/2502.17403/) (2025)
- [EHR2Path: Comprehensive Pathway-Level Modeling of Longitudinal Patient Trajectories from Multimodal Electronic Health Records](https://mlsanity.com/paper/2506.04831/) (2025)
- [TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins](https://mlsanity.com/paper/2601.20906/) (2026)

## Abstract (arXiv)

Precision medicine in ophthalmology requires accurate longitudinal predictions, but the fragmented nature of multimodal clinical data remains a barrier to forecasting. We introduce OphthaDT, an LLM-based digital twin for ophthalmology that serializes longitudinal patient histories from 3,220 patients across four Phase III clinical trials into structured narratives to forecast best corrected visual acuity (BCVA). In benchmarks spanning up to 100 weeks, OphthaDT demonstrated the lowest prediction error in neovascular age-related macular degeneration (nAMD), achieving an average mean absolute error (MAE) reduction of 6.0% compared to all baselines. In diabetic macular edema (DME), OphthaDT demonstrated competitive performance against all baselines while outperforming Random Forest and XGBoost by an average MAE reduction of 2.6% and 6.9%, respectively. Results reveal that OphthaDT's predictive advantage scales with trajectory complexity: whereas linear models remain effective for the more stable treatment responses of DME, OphthaDT's capacity is better suited for capturing the high longitudinal variability of nAMD. Finally, OphthaDT handles irregular sampling without imputation, positioning LLM-based clinical trajectory modeling as a methodology that could reduce patient burden and accelerate drug development.