Machine Learning and Medical Statistics

Alongside investigating how the environmental impacts of climate change are connected to human health, our research also aims to improve healthcare for all. Healthcare is an essential part of everyday life, but healthcare systems are increasingly under pressure due to under-resourcing, more complex and co-occurring conditions, and environmental impacts.

As part of this mission, our research applies our expertise in AI and machine learning to medicine more generally. Using real-world evidence, we produce research on disease diagnosis, occurrence and outcomes, to work towards health equity for all.

A key area of this research is improving how rare, chronic or co-occurring conditions are researched, and the impact of this on patient care. Many of our projects help to improve clinical tools like prediction models or patient sub-groups, which all have a direct impact on patient care. We also advocate for better research and data of conditions, to provide the best possible care for patients.

Featured Projects

	Ethnicity, Equity and AI
	Rare heart diseases during the COVID-19 Pandemic
	Patient Groups in Osteoarthritis
	Osteoporosis Fractures and Hearing Loss
	Heart Disease in Fracture-Risk Patients
	Genetic Causes of Co-Occuring Conditions

Links and Publications from other projects

	HIPPOCRATES: Promoting early identification and improving outcomes for patients with psoriatic arthritis
	Post-operative determinants of chronic pain after primary knee replacement surgery: Analysis of data on 258,386 patients from the National Joint Registry for England, Wales, Northern Ireland and the Isle of Man (NJR)
	Association of Tramadol vs Codeine Prescription Dispensation With Mortality and Other Adverse Clinical Outcomes
	Using national electronic health records for pandemic preparedness: validation of a parsimonious model for predicting excess deaths among those with COVID-19-a data-driven retrospective cohort study
	Random effects modelling versus logistic regression for the inclusion of cluster-level covariates in propensity score estimation: A Monte Carlo simulation and registry cohort analysis
	Use of machine learning for comparing disease risk scores and propensity scores under complex confounding and large sample size scenarios: a simulation study
	Machine Learning for Feature Selection and Cluster Analysis in Drug Utilisation Research
	Impact of Reduced Sampling Rate on Accelerometer-Based Physical Activity Monitoring and Machine Learning Activity Classification
	Trends of Dispensed Opioids in Catalonia, Spain, 2007-19: A Population-Based Cohort Study of Over 5 Million Individuals
	2022 American College of Rheumatology/EULAR Classification Criteria for Giant Cell Arteritis
	2022 American College of Rheumatology/EULAR classification criteria for Takayasu arteritis
	A two-class approach to the detection of physiological deterioration in patient vital signs, with clinical label refinement