M42, a UAE-based healthcare company, has launched an AI-powered tool specifically designed for prostate cancer diagnosis. The technology aims to enhance the accuracy and efficiency of detecting prostate cancer, potentially improving patient outcomes through earlier intervention. This diagnostic solution represents a step forward in integrating artificial intelligence into clinical practice within the region. Why it matters: This development signifies a notable advancement in the application of AI in healthcare in the UAE, potentially positioning the country as a leader in medical AI innovation and improving public health.
Researchers proposed a severity-aware weighted loss method to fine-tune Arabic language models for medical text generation, prioritizing severe clinical cases. This approach utilizes soft severity probabilities, derived from an AraBERT-based classifier, to dynamically scale token-level loss contributions during optimization on the MAQA dataset. The method consistently improved performance across ten Arabic LLMs, with AraGPT2-Base increasing from 54.04% to 66.14% and AraGPT2-Medium from 59.16% to 67.18%. Why it matters: This novel fine-tuning strategy addresses a critical limitation in medical AI by enhancing the safety and reliability of Arabic medical large language models, particularly in high-stakes clinical scenarios.
This paper benchmarks the performance of large language models (LLMs) on Arabic medical natural language processing tasks using the AraHealthQA dataset. The study evaluated LLMs in multiple-choice question answering, fill-in-the-blank, and open-ended question answering scenarios. The results showed that a majority voting solution using Gemini Flash 2.5, Gemini Pro 2.5, and GPT o3 achieved 77% accuracy on MCQs, while other LLMs achieved a BERTScore of 86.44% on open-ended questions. Why it matters: The research highlights both the potential and limitations of current LLMs in Arabic clinical contexts, providing a baseline for future improvements in Arabic medical AI.
MBZUAI researchers have introduced MIRA, a novel framework for improving the factual accuracy of multimodal large language models in medical applications. MIRA uses calibrated retrieval to manage factual risk and integrates image embeddings with a medical knowledge base for efficient reasoning. Evaluated on medical VQA and report generation benchmarks, MIRA achieves state-of-the-art results, with code available on GitHub.
MBZUAI and the Department of Health – Abu Dhabi (DoH) have signed an agreement to collaborate on AI research across genomics, precision medicine, robotics, and AI-powered diagnostics. Signed on October 13, 2025, the MoU aims to drive breakthroughs in disease prevention, early detection, and therapeutics. The partnership seeks to translate AI research into tangible improvements in patient care within Abu Dhabi and beyond. Why it matters: This partnership signifies a major push to establish Abu Dhabi as a leader in biomedical research and AI-driven healthcare innovation.
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.
KAUST and the International Medical Center (IMC) have signed an MoU to collaborate on medical research related to wellness, quality of life, and population health management. The partnership aims to develop AI applications for diagnosis and treatment, along with research in precision medicine and advanced therapies. The collaboration aligns with Saudi Vision 2030's goals to build a sustainable, knowledge-driven healthcare future. Why it matters: This agreement signifies a push to integrate AI and precision medicine into practical medical solutions within the Saudi healthcare system.
MBZUAI alumnus Numan Saeed is applying machine learning to medical imaging and cancer research as a research scientist at the University. He collaborates with UAE hospitals like Sheikh Shakhbout Medical City and Cleveland Clinic to build datasets and gather clinical feedback. Saeed's team is developing a model focused on head and neck cancer using the HECKTOR dataset and local data. Why it matters: This research contributes to the UAE's healthcare ambitions by enabling earlier diagnosis and personalized care through AI-driven analysis of medical images.