Lab profile
About CHAI
CHAI (Causality in Healthcare AI) Hub conducts groundbreaking research to develop fully explainable causal AI platforms addressing healthcare challenges across prevention, diagnosis, and treatment. The Hub co-develops research challenges with clinical experts, policy makers, and patients to address complex and heterogeneous data structures, with a focus on making AI models more transportable, explainable, fair, and directly relevant for decision support.
Causal AIProblem fingerprintingCausal agentChronological causal discoveryStress test medical AI with counterfactualsMeta-risk assessmentExplainable AICausal inference
01 · Research focus
Research areas and highlights
Topics and recent work as stated on the lab’s own site.
- Problem fingerprintingDeveloping methods to account for data shifts and model drifts in medical imaging datasets to improve fairness and reliability in clinical decision-making.
- Causal agentBuilding specialized causal agents that use tools and memory to act as process-guided assistants for personalized education, causal discovery, and hypothesis-to-analysis workflows.
- Chronological causal discoveryDeveloping methods for finding cause-effect relationships in irregular and non-stationary time-sensitive healthcare data.
- Stress test medical AI with counterfactualsTesting medical AI algorithms with counterfactual scenarios to ensure fairness and reduce bias in clinical trials and medical imagery datasets.
- Meta-risk assessmentCombining different risk models to reduce uncertainty and improve reliability in cardiovascular disease risk prediction using Scottish health data.
- Identification of causal optimal treatment strategies in management of cardiovascular disease in type 2 diabetes mellitusUsing NHS England data to understand treatment effectiveness in routine clinical practice and identify which patients benefit causally from each treatment.
- Piloting the use of Targeted Maximum Likelihood Estimation for causal inference and federated analyticsTesting TMLE method that combines machine learning with causal reasoning to study medicine safety using real-world healthcare data.
- REACH: Reconfiguration of Emergency Care – A Causal Healthcare ModelDeveloping a causal inference framework to estimate how proposed emergency service changes will affect patient pathways, ambulance demand, and hospital pressures.
- TRUST-PE: Transparent, Reliable, and Unbiased Solution for Pulmonary Embolism Detection and Surgical PlanningDeveloping causal AI methods to make pulmonary embolism detection systems robust to distribution shifts across hospitals and scanners.
- Causal AI to identify potentially modifiable dementia risk factors after midlife psychiatric multimorbidityUsing causal AI methods with mental healthcare records to investigate potentially modifiable treatment and care factors for dementia prevention.
- CAn-TaCKLEUnderstanding causes of head impacts in rugby league tackle events to evaluate policy changes without law trials.
- Causal Survival Models for Psychosis: Insights into Risks and PrognosisDeveloping mathematical models to identify true cause-and-effect relationships in psychosis patient data to predict treatment benefits and side effects.
02 · People
Leadership and researchers
People listed on the lab’s team pages, by role.
Sotirios (Sotos) TsaftarisDirector · Hub DirectorLinkedIn ↗
Sotirios TsaftarisDirector
Amitava BanerjeeCo-Investigator
Sjoerd BeentjesCo-Principal Investigator
Anna CalissanoProject Lead
Hana ChocklerFaculty
Alistair C ChurchCo-Applicant
Fani DeligianniProject Lead, Principal Investigator
Ben GlockerFaculty
Ali GooyaProject Lead
Judith R HarrisonProject Lead
Ava KhamsehCHAI Co-I
Alina KumukovaCo-Principal Investigator
Daniel moralesProject Lead
03 · Research intelligence
Research Intelligence evidence
Publications, grants and clinical trials linked to the lab’s researchers in Health AI Central’s research data.
Publications & preprints
- Comparative Cardiovascular Effectiveness of Glucagon-Like Peptide 1 Receptor Agonists and Sodium-Glucose Cotransporter 2 Inhibitors in Diabetes Mellitus.Journal of the American College of Cardiology · 2026
- Venous and arterial thromboembolic events after COVID-19 during the Omicron period in three European countries.Scientific reports · 2026
- Accelerated deficit accumulation in frailty and associations with adverse outcomes: a longitudinal population data analysis.The lancet. Healthy longevity · 2026
Clinical-trial records
- The PROSECCA Study, Answering New Questions in Prostate CancerNCT06714630 · Recruiting
04 · Updates
Updates and lab news
News and events from the lab’s own site.
- CHAIfestEventJun 2, 2026 · chai.ac.uk
- Edinburgh Science Festival: Sick Day DetectivesEventApr 7, 2026 · chai.ac.uk
- CHAI & CRUK-Scotland Community of PracticeEventNov 7, 2025 · chai.ac.uk
- CHAI Community of Practice: Evidence for RegulatorsEventOct 15, 2025 · chai.ac.uk
- Workshop on Causal AI in Healthcare Policy & PracticeEventOct 6, 2025 · chai.ac.uk
- UKAIRS Festival of IdeasEventSep 8, 2025 · chai.ac.uk
05 · Official presence
Lab sources and channels
The lab’s own pages and accounts.
06 · Related
Related labs and centers
Labs at the same institution and labs working on similar topics.