Current ophthalmology clinical workflows are plagued by over-referrals, long waits, and complex and heterogeneous medical records. Large language models (LLMs) present a promising solution to automate various procedures such as triaging, preliminary tests like visual acuity assessment, and report summaries. However, LLMs have demonstrated significantly varied performance across different languages in natural language question-answering tasks, potentially exacerbating healthcare disparities in Low and Middle-Income Countries (LMICs). This study introduces the first multilingual ophthalmological question-answering benchmark with manually curated questions parallel across languages, allowing for direct cross-lingual comparisons. Our evaluation of 6 popular LLMs across 7 different languages reveals substantial bias across different languages, highlighting risks for clinical deployment of LLMs in LMICs. Existing debiasing methods such as Translation Chain-of-Thought or Retrieval-augmented generation (RAG) by themselves fall short of closing this performance gap, often failing to improve performance across all languages and lacking specificity for the medical domain. To address this issue, We propose CLARA (Cross-Lingual Reflective Agentic system), a novel inference time de-biasing method leveraging retrieval augmented generation and self-verification. Our approach not only improves performance across all languages but also significantly reduces the multilingual bias gap, facilitating equitable LLM application across the globe.

AI-based DR screening is promising in low- and middle-income countries (LMICs), where limited human resources constrain access to specialist-led programs. However, current systems often degrade under real-world image-quality variations, especially with portable devices that are vital for low- and middle-income countries. This study aims to develop Retsyn, a synthetic-data augmentation framework that improves screening robustness across devices and imaging conditions. RetSyn leverages advanced diffusion models to generate synthetic retinal images with diverse device and imaging quality characteristics. To address the challenges of (1) portable device data scarcity, (2) disease and quality distribution imbalance, and (3) varying image quality, RetSyn uses class and quality-conditioned diffusion for controllable synthesis, a group-balanced loss to increase coverage of minority (quality, disease) pairs, and a Direct Preference Optimization alignment step with a small paired smartphone–tabletop set. The synthesized images are then used to augment classifier training. The effectiveness of RetSyn-generated images was evaluated by training retinal diagnosis models on a combination of real and synthetic data. RetSyn yields consistent gains in-domain and out-of-domain. On low-quality tabletop images, F1 improves from 0.781 to 0.874 (binary) and 0.607 to 0.703 (three-class), while AUROC reaches 0.982 and 0.951, respectively. On out-of-domain portable images, RetSyn attains AUROC 0.813/F1 0.703 (binary) and AUROC 0.804/F1 0.609 (three-class), exceeding group-robustness baselines such as GroupDRO (binary: AUROC 0.786/F1 0.626; three-class: AUROC 0.789/F1 0.544). RetSyn presents an effective and scalable synthetic data framework that significantly enhances the robustness and generalizability of AI-based DR screening models in LMICs. By addressing the critical challenges posed by varying image quality and device characteristics, RetSyn facilitates more reliable deployment of AI diagnostics in underserved regions. Additionally, the release of the first publicly available paired smartphone-tabletop retinal image dataset will support further research into cross-device DR screening solutions. • RetSyn generates synthetic retinal images to enhance AI robustness across varying image qualities and devices. • Group-balanced training and preference optimization enable diverse medical image synthesis with minimal cross-device paired data. • Releases the first publicly available paired smartphone-tabletop retinal dataset. • Performance improved significantly on low-quality and portable device photographs. • Achieves first clinically acceptable results for smartphone-based DR screening in LMICs.

Electronic health records (EHRs) are multimodal by nature, consisting of structured tabular features like lab tests and unstructured clinical notes. In real-life clinical practice, doctors use complementary multimodal EHR data sources to get a clearer picture of patients' health and support clinical decision-making. However, most EHR predictive models do not reflect these procedures, as they either focus on a single modality or overlook the inter-modality interactions/redundancy. In this work, we propose MEDFuse, a Multimodal EHR Data Fusion framework that incorporates masked lab-test modeling and large language models (LLMs) to effectively integrate structured and unstructured medical data. MEDFuse leverages multimodal embeddings extracted from two sources: LLMs fine-tuned on free clinical text and masked tabular transformers trained on structured lab test results. We design a disentangled transformer module, optimized by a mutual information loss to 1) decouple modality-specific and modality-shared information and 2) extract useful joint representation from the noise and redundancy present in clinical notes. Through comprehensive validation on the public MIMIC-III dataset and the in-house FEMH dataset, MEDFuse demonstrates great potential in advancing clinical predictions, achieving over 90% F1 score in the 10-disease multi-label classification task.