AI for Humans and Health
Healthcare systems worldwide face growing challenges from aging populations, chronic disease management, and workforce shortages. The WHO estimates a global deficit of 18 million healthcare workers by 2030, while healthcare costs consume an increasing share of GDP across developed nations. Meanwhile, advances in AI and computational methods present unprecedented opportunities to transform medical diagnosis, treatment planning, and healthcare delivery. The medical imaging market alone is projected to exceed $50 billion by 2027, with AI-enabled solutions increasingly central to clinical workflows and decision support systems.
In our group we strive to understand and create transformative AI-driven approaches that directly impact human lives with a particular focus on health and well-being. We leverage interdisciplinary expertise in AI, machine learning, natural language processing, and human-computer interaction, working closely with partners in healthcare, psychology, and other relevant disciplines. Our research examines how AI can facilitate human decision making, communication, and collaboration, and how people and machines can work together to address complex challenges in health and well-being.
Members
- Professor Andrew Howes - Professor (E&R)
- Professor Aline Villavicencio - Professor (E&R)
- Professor Xujiong Ye - Professor (E&R)
- Dr Mohammed Abdelsamea - Senior Lecturer (E&R)
- Dr Fabrizio Costa - Senior Lecturer (E&R)
- Dr Hang Dong - Lecturer (E&R)
- Dr Ahmed Karam Eldaly - Lecturer (E&R)
- Dr Zeyu Fu - Lecturer (E&R)
- Dr Yanda Meng - Lecturer (E&R)
- Dr Huma Samin - Lecturer (E&R)
- Dr Siyang Song - Lecturer (E&R)
- - Lecturer (E&R)
- Dr Rodrigo Wilkens - Lecturer (E&R)
- Dr Lei Zhang
Current research projects
- Causal Counterfactual visualisation for human causal decision making in healthcare: Developing advanced visualization methods to support clinical decision-making
- AI-Based Support for Mental Health Communication: Creating technologies to enhance communication in mental health contexts
- Self-learning AI-based digital twins for accelerating clinical care in respiratory emergency admissions: Building computational models to improve emergency care
- Diagnosing metaphyseal fractures in children under two: Applying advanced imaging analysis to improve diagnostic accuracy
- Advanced AI-based Digital Twins for Emergency Respiratory Care: Developing predictive models for respiratory emergencies
- Automatic MRI image interpretation and 3D motion analysis for diagnosis of knee disorders: Creating systems for improved musculoskeletal diagnostics
- Automated assessment and triaging of ENT patient cases: Developing tools to enhance ENT care delivery and patient triage
- Holistic Hateful Video Detection and Localisation via Multi-Modal Graph Learning
Research topics
- Medical Image Analysis and Computer Vision
- Clinical Decision Support Systems
- Human-AI Collaboration and Human-in-the-loop Systems
- Explainable AI for Medicine and Healthcare
- Natural Language Processing for Health Communication
- Causal AI in Healthcare
- Knowledge Graphs for Healthcare
- Health Digital Twins and Simulation
- Multi-granularity Learning and Geometric Deep Learning
- Cognitive Science and Computational Models of Decision-making
- Machine Learning for Disease Detection and Diagnosis
- Multimodal Learning in Healthcare
- Self-supervision and Transfer Learning for Medical Applications
- Uncertainty Quantification in Medical AI
- Statistical Signal and Image Processing
- Energy Functional Optimization for Computer Vision
- Mental Health Technologies and Communication Support
- Lexical Semantics and Multilingual NLP
- Health Informatics and Data Integration
- Patient-centred AI Systems and Clinical Applications
