British Scientists Developing Advanced Pulmonary Hypertension Imaging
Computer software combined with artificial intelligence can generate advanced imaging techniques for serious diseases such as pulmonary hypertension (PH), improving healthcare, British scientists say.
This was the focus of a workshop on digital radiology at Imperial College Academic Health Science Centre (AHSC) that brought together medical researchers, computer scientists, mathematicians and IT experts.
“There are tremendous opportunities to develop and improve the delivery of care through AI and other digital technologies,” Jonathan Weber, director of the AHSC, said in an Imperial College news release written by Maxine Myers.
“From redefining drug discoveries to helping predict and prevent diseases using health record data, AI will have a transformative effect on doctors and patients,” Weber added.
During the workshop, the participants learned about Imperial’s research in digital radiology, machine learning, AI, and mathematics. They also discussed radiology challenges in hospitals, including increasing demands for its use in medical investigation.
“I hope the delegates at our event were inspired and will look at ways to work together on AI research projects that can help change the way we deliver care and lead to better outcomes for patients,” Weber said.
Declan O’Regan of Imperial College’s MRC London Institute of Medical Sciences (LMS) was one of the imaging experts who spoke.
His team developed software that creates virtual 3-D patients’ hearts that replicate the way the organ contracts with each beat. Combined with AI algorithms, the software can rapidly learn and detect the features of cardiac function that predict heart failure and death.
The software tested the new imaging approach with MRIs collected from 256 recently diagnosed PH patients. The software copied the movement of patients’ hearts at more than 30,000 points. Based on this information, it then created a virtual 3-D heart for each patient.
When combined with conventional imaging, hemodynamic, functional, and disease markers, the 3-D models help predict PH patient survival.
The new tool can help stratify PH patients as high- or low-risk, allowing doctors to improve their treatment strategies.
It has the potential to predict the outcomes of patients with other heart conditions as well.