MBZUAI Ph.D. student Raza Imam and colleagues presented a new benchmark called MediMeta-C to test the robustness of medical vision-language models (MVLMs) under real-world image corruptions. They found that top-performing MVLMs on clean data often fail under mild corruption, with fundoscopy models particularly vulnerable. To address this, they developed RobustMedCLIP (RMC), a lightweight defense using few-shot LoRA tuning to improve model robustness. Why it matters: This research highlights the critical need for robustness testing in medical AI to ensure reliability in clinical settings, particularly in resource-constrained environments where image quality may be compromised.
MBZUAI doctoral student Umaima Rahman is researching domain adaptation and generalization in deep learning for medical imaging to improve AI model performance across diverse hospitals and equipment. Her work focuses on building models that learn consistent features across different data sources to ensure reliability in various healthcare settings. Rahman emphasizes that generalization in healthcare AI is a necessity, especially in resource-limited settings, and aims to develop AI that assists clinicians rather than replaces them. Why it matters: This research addresses a critical challenge in deploying AI in healthcare, ensuring that models can be reliably used in diverse settings, particularly benefiting developing countries and improving global healthcare accessibility.
MBZUAI is developing AI algorithms to intelligently process data from wearables and home sensors for remote patient monitoring. The algorithms aim to analyze multiple strands of health data to provide a more comprehensive view of a patient's health, distinguishing between genuine emergencies and benign situations. MBZUAI's provost, Professor Fakhri Karray, believes this approach could handle 20-25% of diagnoses virtually, reducing the burden on healthcare systems. Why it matters: This research could significantly improve healthcare efficiency and accessibility in the UAE and beyond by enabling more effective remote patient monitoring and reducing unnecessary hospital visits.
MBZUAI researchers developed MedAgentSim, a simulated hospital environment to evaluate AI diagnostic abilities. The simulation uses LLM-powered agents to mimic doctor-patient conversations, providing a dynamic assessment of diagnostic skills. The system includes doctor, patient, and evaluator agents that interact within the simulated hospital, making real-time decisions. Why it matters: This research offers a more realistic evaluation of AI in clinical settings, addressing limitations of current benchmarks and potentially improving AI's use in healthcare.
MBZUAI doctoral student Mai A. Shaaban and colleagues developed MedPromptX, a system that analyzes chest X-rays and patient data to aid lung disease diagnoses. MedPromptX uses multimodal large language models with visual grounding and few-shot prompting, trained on a new dataset of 6,000 patient records (MedPromptX-VQA) derived from MIMIC-IV and MIMIC-CXR. The system addresses the challenge of incomplete electronic health records by leveraging the knowledge embedded in large language models to interpret lab results. Why it matters: This research advances AI-driven medical diagnostics by integrating diverse data sources and addressing data gaps, potentially leading to quicker and more accurate diagnoses.