Multimodal and longitudinal prediction
Predicting type 2 diabetes and its complications years ahead by combining retinal images, ECG, bone scans, genetic, laboratory and lifestyle data.
Dr. Sulaiman Khan, Dr. Farida Mohsen
See the projectsبرنامج السكري الدقيق في قطر
Shaping the future of DAQIQ diabetes care in Qatar.
Based at Hamad Bin Khalifa University, we bring together data analytics, artificial intelligence and the lived experience of people with diabetes, so that care in Qatar fits each person and improves their quality of life.
نهجنا
DAQIQ: two sides, one program
DAQIQ starts with people and their health data, then uses AI to turn them into insights that improve diabetes care. Those insights return to people, and the loop begins again.
Where it starts
People & Data
Lived experience and health data from people in Qatar living with diabetes, shared with consent.
- Long-term studies with people, families and clinics across Qatar, such as the LDQ Cohort
- Clinical, imaging, genetic and everyday data, collected with consent and ethics approval
- Patients and clinicians shaping the questions we ask, in Arabic and English
What comes back
AI & Insights
Analytics and AI that turn that data into individualised care, from prevention to everyday life.
- Earlier, individualised risk prediction from many kinds of data
- Explainable AI that clinicians can question and trust
- Free tools and guides for daily life on DAQIQ Living
Tap either lobe of the loop to explore it.
مجالات بحثنا
The AI behind DAQIQ care
Four lines of research turn health data into insights that clinicians and patients can trust.
Efficient AI and model compression
Pruning and compressing large language and foundation models so that capable AI runs quickly, cheaply and privately in clinics and on everyday devices.
Papers in preparationPhysics-informed neural networks
Neural networks that build in how the body works, such as how glucose and insulin interact, so that predictions stay plausible even when data are limited.
Papers in preparationKnowledge graphs and trustworthy AI
Linking clinical knowledge with patient data in knowledge graphs, so that AI advice can be explained, questioned and checked by clinicians.
Dr. Nasrullah Khan, Dr. Amjad Ali
See the projectResearch designed in Qatar, with and for the people who live here.
بحث من قطر، مع أهلها ومن أجلهم
أثرنا
DAQIQ in numbers
What the program has produced so far. Updated with every new paper, thesis and talk.
- Publications
- 17
- Active projects
- 2
- Theses completed
- 3
- Researchers trained
- 8
- Talks
- 6
مشاريعنا
Current projects
The studies DAQIQ is running now.
Living with Diabetes in Qatar: the LDQ Cohort
A five-year cohort following adults with type 2 diabetes across four care settings, to learn how digital and AI advice shapes diabetes distress and self-management.
AI-driven healthcare surveillance and proactive care recommendation in smart environments
AI that brings together data from connected health devices and clinical knowledge to spot changes early and recommend timely, personalised care for people living with diabetes.
شارك معنا
Be part of DAQIQ.
Whether you live with diabetes, care for someone who does, treat patients, study or do research, there is a place for you in DAQIQ. Choose the option that fits you.
Taking part is always voluntary. Registering your interest means we may contact you when a study opens. It does not enrol you in any study.
الأخبار والفعاليات
News and events
-
Upcoming talk: ORCHID-DR: clinical ordinal-lesion attention with semantic prototypes for robust diabetic retinopathy grading
Dr. Zubair Shah at 7th International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2026), Edinburgh, United Kingdom.
-
Dr. Sulaiman Khan completes his PhD
His thesis used longitudinal Qatar Biobank data to predict type 2 diabetes years before it starts. He continues with DAQIQ as a Research Assistant.
-
HBKU Thematic Research Grant for AI-driven proactive care
DAQIQ received USD 96,000 from the HBKU Thematic Research Grant Program for AI that monitors health signals and recommends timely care, starting in 2026.
منشوراتنا
Latest publications
- 2025
Artificial intelligence–based diabetes risk prediction from longitudinal DXA bone measurements
Khan S, Shah Z. Scientific Reports 15: 25706.
- 2025
Khan S, Biswas MR, Shah Z. Artificial Intelligence in Healthcare (AIiH 2025), Lecture Notes in Computer Science 16038, Springer.
- 2025
Early prediction of type 2 diabetes using multimodal data and tabular transformers
Khan S, Biswas MR, Shah Z. 3rd International Conference on Foundation and Large Language Models (FLLM 2025): 592–599, IEEE.
- 2025
ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
Mohsen F, Safa A, Shah Z. Scientific Reports 15: 27164.
- 2025
Integrating non-linear Radon transformation for diabetic retinopathy grading
Mohsen F, Belhaouari S, Shah Z. Scientific Reports 15: 30706.