- Home
- Projects
- AI-driven healthcare surveillance and proactive care recommendation in smart environments
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.
Part of DAQIQ · دقيق: Diabetes Analytics for Quality of life through Individualised care in Qatar.
- Status
- Active
- Duration
- 2026–2027
- Funding
- HBKU Thematic Research Grant Program (USD 96,000)
- Team
- 2 people
- Publications
- 1
In plain language
We are building AI that learns from the health devices people use every day, such as glucose meters and wearables, together with medical knowledge, to suggest the right care at the right time.
Why it matters
- Diabetes changes day to day, but most care is planned around occasional clinic visits.
- Connected devices already record a great deal about daily health. Turning that data into timely, trustworthy advice could prevent problems before they start.
Overview
People living with diabetes generate a steady stream of health data at home and in care settings, from glucose meters, wearables and other connected devices. Today, most of this data is never used to guide care.
This project develops AI for smart health environments that monitors these signals, links them with clinical knowledge in knowledge graphs, and recommends proactive, personalised care. It builds on our KEM-IoMT model for medical service recommendation in diabetes.
Objectives
- Design a knowledge-graph framework that links device data, patient records and clinical knowledge.
- Develop AI that detects meaningful changes in health signals early.
- Recommend personalised, context-aware care and services, with explanations clinicians can check.
- Evaluate the approach for accuracy, privacy and safety.
Approach and data
- Knowledge-graph construction from Internet of Medical Things data, health records and medical ontologies.
- Knowledge-graph embeddings and graph-based machine learning for surveillance and recommendation.
- Privacy-preserving design suitable for health settings in Qatar.
Key results
- Our knowledge-graph embedding model for diabetes service recommendation (Computers in Biology and Medicine, 2025), the foundation for this project
- KEM-IoMT
Timeline
- 2026Framework design and data integration.
- 2027Model development, evaluation and reporting.
Publications 1
-
KEM-IoMT: knowledge graph embedding-enhanced accurate medical service recommendation against diabetes
Khan N, Mufti MR, Arif M, Ali A, Shah Z
Computers in Biology and Medicine 194: 110463, 2025
Journal articleAI-driven healthcare surveillance and proactive care recommendation in smart environmentsDr. Nasrullah KhanDr. Amjad AliDr. Zubair Shah
Get involved
Collaborate on smart diabetes care
We welcome clinicians, device and data partners, and researchers working on connected health.