University Hospitals Birmingham (UHB) has joined forces with medical technology company Qureight to develop more diverse artificial intelligence (AI) models. The aim is to improve diagnosis of lung disease, and in particular idiopathic pulmonary fibrosis (IPF), which scars the lungs, causing breathlessness and coughing. The survival rate from the disease is typically worse than for most cancers. UHB wants to ensure patients from minority ethnic backgrounds receive tailored and effective treatments. A lack of medicines and treatments is one of the reasons for IPF’s poor survival rates, although AI-powered tools could help address the issue.
Through analysis of existing IPF patient data, AI tools could unlock new insights that could aid researchers in developing new treatments. Birmingham’s diverse population will provide Qureight with more diverse data than is usually available, allowing the development of artificial intelligence diagnosis models that better reflect population diversity. In particular, scientists will look at lung scan data to build a better understanding of how complex lung disease manifests and develops in specific communities.
While radiology doctors currently analyse CT scans of the lungs as a diagnosis and monitoring process, the process is open to interpretation bias, and a shortage of such specialists makes the process slow and difficult. In addition, the limited data available is mainly from white European patients, who may experience lung disease in a specific way.
Qureight’s artificial intelligence will combine patient data from scans, lung function tests, blood tests and demographic records to better understand complex lung conditions. By partnering with UHB, the company hopes to bring more applicability to its AI beyond clinical trials.
“Our partnership with UHB will be pivotal to how we harness our world leading AI solutions, to benefit patients from across the spectrum of complex lung diseases,” says Dr Muhunthan Thillai, co-founder of Qureight and a chest physician. “One of the biggest problems with AI in healthcare is the lack of applicability to real world patients. AI is already being used by Qureight in complex lung disease clinical trials in Europe and the USA, but a more diverse patient population is key to its future success.”
“Allowing access to patient data that truly reflects the unique diversity of Birmingham’s population will be invaluable to the planning and delivery of more equitable patient care – not just in cities like ours,” adds Dr Anjali Crawshaw, a consultant respiratory physician at University Hospitals Birmingham NHS Foundation Trust.