The researchers aim to create an AI-powered model for early detection of lung cancer risk.

Researchers are developing artificial intelligence that they hope will help identify patients at highest risk of lung cancer before symptoms appear.

A team from Nottingham Trent University and Nottingham University Hospitals NHS The trust aims to build an AI-powered model that can autonomously gather subtle cues and markers in patient data to identify those at risk for further investigation.

In the UK alone, around 48,500 new cases of lung cancer are diagnosed each year and around 35,000 people die from the disease.

The team aims to tackle the current challenge of European health systems by manually identifying people at risk of certain diseases and helping to reduce the financial burden by ensuring that they use services. Those who need them the most.

This would involve developing a system to identify factors that might make an individual more at risk and then train it to produce ‘synthetic’ data that can pick up even the weakest signals. Could be the problem.

The aim is to help save lives by identifying the disease before it becomes symptomatic, as it may be too late for lung cancer patients.

The Nottingham team is a UK partner in PHASE-IV-AI, a €7.6m project funded by the European Union’s Horizon Europe research and innovation programme.

The project involves 20 partners from ten European countries and aims to unlock the full potential of AI and data analytics in healthcare in a secure and privacy-friendly way.

In addition to lung cancer, progress from the PHASE-IV-AI project will also be validated by other partners in prostate cancer and ischemic stroke. Lung cancer and prostate cancer are among the top three priorities in the fight against cancer in Europe, while neurodegenerative diseases are one of the most relevant problems with the EU’s aging population.

If successful, it is hoped that the Nottingham team’s model can be trained to identify the risk of other serious diseases and be rolled out to hospitals and organizations across Europe to make AI-powered diagnoses. are ready to use.

It is believed that AI can enable real innovations in healthcare, and that AI systems that can process large amounts of data quickly and in detail will improve healthcare and clinical decision-making. can be used as a tool for

Nevertheless, the way information is currently stored in European countries and the limited access to health data may hinder innovation, as training is often needed to develop reliable and responsive AI systems. And validation requires large data sets.

“The hope is that we will be able to develop an AI-powered model for hospitals to use to help them identify the people most at risk,” said Dr Mufti Mehmood, from the Nottingham Trent University School of Medicine. of Science is an associate professor of cognitive computing, said. Technology.

He said: “Countries have vast amounts of clinical practice data and we want to understand how we can use this to identify the right people, to invite them to more focused assessments. We need systems to be able to find people before they start showing symptoms, and ultimately help save lives.

Storing healthcare data is very sensitive, very private, so by generating simulated data we can train the model to act responsibly and provide reasons why it chose an individual.

Dr Mufti Mehmood, Associate Professor of Cognitive Computing, School of Science and Technology, Nottingham Trent University

Professor David Baldwin, lung cancer consultant at Nottingham University Hospitals NHS Trust, said: “Identifying the right people for cancer screening is vital to ensure that as many people benefit as possible. Do not harm those who have a low risk of lung cancer.

“AI offers an opportunity to improve the way we target screening programs to make them clinically and cost-effective. AI can change practice in many other areas of lung cancer care as well.” doing. AI tools can help reduce the workload of specialists like radiographers and radiologists, as well as improve treatment costs and patient outcomes.

Source:

Nottingham Trent University

Leave a Comment