Artificial intelligence is redefining the boundaries of what is possible in medicine. On World Health Day 2026, which is being held this year under the global theme: “Together for health. Support science,” researchers at Mohamed bin Zayed University of Artificial Intelligence in Abu Dhabi are demonstrating this in a practical way.

The race towards early detection of Alzheimer's

According to the World Health Organization, a new case of dementia appears somewhere in the world every three seconds. While there is still no cure for this disease, the next stage may see the emergence of something as valuable as a treatment: an early warning system that allows for timely intervention .

Researchers at Mohamed bin Zayed University of Artificial Intelligence in Abu Dhabi have developed an AI system called MAGNET-AD that can predict the onset of Alzheimer's disease up to two decades before any symptoms appear. This system represents a significant step forward in early detection, as it uses a spatiotemporal neural network to identify biological patterns that are difficult to detect through traditional clinical assessment. A landmark study published in The Lancet Public Health journal estimates that the number of dementia cases will reach 152 million worldwide by 2050.

“Early detection is everything in the case of incurable diseases,” said PhD candidate Salma Hassan. Her team also developed a complementary system called ClinGRAD that simultaneously analyzes brain MRI images, genomic data, and clinical records to classify dementia subtypes with 98.75% accuracy. This work was peer-reviewed and published in the proceedings of MICCAI 2025 , one of the world’s leading conferences in medical imaging, and was evaluated on the ANMerge multicenter and multimodal dataset to demonstrate its robustness across diverse patient populations. This level of accuracy is crucial in a field where a dementia diagnosis can reduce life expectancy by 3 to 30 years, depending on the age of onset, according to a systematic review published in January 2025 in the BMJ that included more than five million patients.

This work on Alzheimer’s is one of five areas where Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), the world’s first graduate-level research university dedicated to AI, is expanding the horizons of medical capabilities. On this World Health Day, this research achievement serves as a striking example of the rapid pace at which AI is moving from the paper to real-world impact .

The retina is a window into the body's health.

One of the most counterintuitive discoveries in modern medicine is that some of the most important indicators of the body's health can be detected through the retina .

Researchers at Cleveland Clinic Abu Dhabi demonstrated last year that a simple eye exam can detect early signs of diabetes, high blood pressure, Alzheimer's, and heart disease without surgery and before the patient experiences any symptoms. This development has significant implications for public health screenings in the UAE, where the International Diabetes Federation estimates that diabetes affects approximately 16% of the adult population—one of the highest rates globally.

In parallel, the team is developing artificial intelligence systems that combine retinal angiography with electrocardiogram (ECG) data for the early detection of heart failure . According to the researchers, these systems are designed not to replace physicians, but to provide an additional digital perspective that captures what might be missed by a human observer under normal circumstances .

Healthcare in the local language

For millions of people in the Middle East and Africa, limited access to quality healthcare is not only a barrier of distance but also of language and health culture, which remain largely unaddressed. The “Smart Arab Doctor” was designed by Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) and powered by the BiMediX family of medical AI models developed in-house by Dr. Hisham Sholakal and his team, to bridge this gap. The project has garnered several international accolades, including the 2024 Meta Lama Award for Impactful Innovation and the 2025 NVIDIA Academic Grant .

This system is based on BiMediX , a comprehensive medical language model in Arabic and English that enables reliable medical understanding and effective communication across different languages. It has been downloaded more than 140,000 times on the Hugging Face platform. Building on this foundation, BiMediX2 expands the system's capabilities to include the understanding of medical images such as X-rays, MRIs, and CT scans, while also supporting Arabic and English. These capabilities were subsequently enhanced with MediX-R1 and MedAgentSim , improving clinical reasoning and enabling more dynamic interaction with patients across diverse healthcare scenarios. Most recently, in an ongoing project, the model's language capabilities have been expanded to include Hindi, spoken by more than 600 million people worldwide, with support from the joint Foundational Research Grant between Mohamed bin Zayed University of Artificial Intelligence and the Technology Innovation Institute.

The team has published its research at leading AI and medicine conferences, including EMNLP and MICCAI , and has made its models, data, and code available as open source, in line with Mohamed bin Zayed University of Artificial Intelligence’s commitment to advancing AI research in the Middle East and globally. By integrating into platforms like Telegram and mobile applications, and supporting both text and voice interaction, the system is designed to reach users with limited health literacy in remote and underserved communities, providing them with basic medical guidance in their own language, 24/7 .

Six million reasons to master ultrasound scans

According to the World Health Organization, congenital anomalies affect approximately one in 33 births worldwide, amounting to nearly six million cases annually. Associate Professor Mohamed Yaqoob has dedicated his career to bridging this gap. His ScanNav technology, the world’s first AI-based system for assessing fetal anomalies, has evolved from a laboratory in Oxford to FDA approval and then to deployment across GE Healthcare’s global network, supporting the care of millions of women each year. At Mohamed bin Zayed University of Artificial Intelligence, this work has evolved into the FetalCLIP model, an AI model trained on over 210,000 ultrasound images—the largest dataset of its kind—capable of detecting fetal heart defects and providing precise anatomical measurements with unprecedented speed and accuracy. The team later developed the MobileFetalCLIP model, which offers the same capabilities as FetalCLIP in a lightweight form factor designed to work on peripheral devices, thus expanding its use to include resource-limited environments where reliable embryo testing is needed .

Simulation of life itself

In November 2025, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) and GenBio AI won the UAE AI Award in the “AI Research” category for their work on the AIDO AI-powered digital object project. AIDO is a large-scale simulation of human biology, encompassing everything from gene activity and protein behavior to cell and organ system functions. The project’s foundational models, focusing on DNA , RNA , proteins, and cells, can predict the properties of molecules and cells, while the Gene Expression Transducer (GET ) can predict gene behavior under specific conditions before any laboratory experiment is conducted. The goal is to make drug discovery faster, safer, and cheaper, ultimately leading to a fundamental understanding of the underlying causes of disease .

These breakthroughs collectively illustrate the practical meaning of "supporting science," not just in principle. And in Abu Dhabi, with the Mohamed bin Zayed University of Artificial Intelligence, this future is already taking shape.

-I finish-

#Company Data

Disclaimer regarding the content of press releases
The content of this press release is provided by a third-party provider. We do not assume any responsibility for, nor do we have any control over, such content. This content is provided on an "as is" and "as available" basis and is not edited in any way. Neither we, nor our affiliates, will be liable for the accuracy, endorsement, or completeness of any opinions, views, information, or materials contained in this content.
This press release is provided for informational purposes only; the content does not constitute legal, investment, or tax advice, nor does it offer any opinion on the suitability, value, or profitability of any particular portfolio or investment strategy. Neither we nor our affiliates will be liable for any errors or inaccuracies in the content, or for any actions you take based on that content. You expressly agree and acknowledge full responsibility for your use of the information contained in this press release.
To the extent permitted by applicable law, Refinitiv, its parent company, subsidiaries, affiliates, relevant shareholders, directors, officers, employees, agents, advertisers, content providers, and licensors (collectively, the 'Refinitiv Parties') shall not be liable (jointly or severally) to you for any direct, indirect, consequential, special, incidental, punitive, or exemplary damages; This includes, but is not limited to, losses of profits, savings, or revenues, whether due to negligence, tort, contract, or other theories of liability, even if the parties to Refinitiv were advised of the possibility of any such damages or losses occurring or actually anticipated them.