Search this Section

Artificial intelligence and data analysis

MRI brain scan

Artificial intelligence and data analysis have immense potential for improving healthcare, complementing expert clinical knowledge to increase speed and efficiency of diagnosis and care, reducing healthcare costs and enabling personalised medicine.

Artificial intelligence capabilities

Facial recognition - courtesy of BlueSkyeAI

Our research capabilities cover many technical disciplines, from motion analysis, image segmentation to shape and object analysis. These have been applied in diverse clinical areas.

Tracking the shape and motion of bones in articulated joints from CT images, reconstructing these in 3D, and detecting abnormalities
Assistive robotics and intelligent sensing
Respiratory motion correction in MRI/PET images.
Facial recognition system and eye tracking software which is being used for ADHD and autism diagnosis and monitoring of mental health conditions (This has led to the formation of spin-out company BlueSkyeAI)
Estimate of gestational age, to support premature babies in low income countries
Early detection of peripheral neuropathy for diabetic patients using corneal confocal microscopic images.
Diagnosing cancers from MRI scans and idiopathic lung fibrosis from lung CT scans
Identifying the composition of pharmaceutical tablets from Raman spectroscopy data

Key research groups:

Cyber-physical Health and Assistive Robotics Technologies (CHART)

Mixed Reality Lab (MRL)

Intelligent Modelling and Analysis (IMA)

Human Factors Research Group

Artificial Intelligence at Nottingham

Data analysis capabilities

Testing handheld technology in wards

Using a wide variety of computational techniques, including data mining, pattern analysis and fuzzy logic, we turn data into information to support clinicians in diagnostics and decision making.

Discovery and evaluation of diagnostic biomarkers
Identification and classification of diseases
Big data management
Modelling human decision making
Molecular diagnostic capabilities
Internet of Things
Reduction in prescription errors

Key research groups and centres

Horizon Digital Economy Research Hub

Intelligent Modelling and Analysis (IMA)

PRIMIS - Specialist Primary Care health informaticians

Computational Optimisation and Learning (COL)

Human Factors Research Group

Digital Research Service

Medicine identification

A partnership between the Universities of Nottingham and Strathclyde and GSK will accelerate research into the discovery of new medicines, using AI and machine-learning technologies for the efficient identification of next generation medicines.

The five-year ESPRC funded programme will see the partners deliver a new suite of methods and approaches to tackle some of the major challenges in the discovery, development, and manufacture of medicines. The total project funding is £12.9 million, including a £5.5 million grant award from the EPSRC.

The research programme aims to enable the production of transformative medicines at lower costs with reduced waste production and shorter time for manufacture.

Researchers will apply cutting edge Artificial Intelligence and machine-learning technologies to the efficient identification of next generation medicines.

Digital pathology

MRI scan of the brain

The University and NHS partners are working on major initiatives to develop and use artificial intelligence for disease diagnosis and treatment optimisation.

Major projects include

InLightenUs - Diagnostics for early detection of disease using cutting edge light microscopy technology

Lead contact: Professor Amanda Wright

Capacity, Confidence, Care - Using Artificial Intelligence and Machine Learning to support Breast Screening - A shared imaging test system for the East Midlands consortium EMRAD

Lead contact: Simon Harris

PathLAKE - Diagnosis to reduce chemotherapy treatment

Lead contact: Professor Emad Rakha

National Pathology Imaging Collaborative (NPIC) - Developing new AI systems capable of analysing digital pathology images

Preventative healthcare

We have developed and tested a system of computer-based machine learning algorithms to predict the risk of early death due to chronic disease in a large middle-aged population.

This will allow personalised preventative medicine and risk management for patients.