New Machine Learning Technologies Could Improve Disease Prediction in CF

Diana Campelo Delgado avatar

by Diana Campelo Delgado |

Share this article:

Share article via email
machine learning

Machine learning, a method of data analysis, could improve disease prediction and bring precision medicine for cystic fibrosis (CF) one step closer to reality, according to researchers at the University of Cambridge, in the U.K., who have developed novel artificial intelligence (AI) technologies to allow for clinical predictions in chronic health conditions such as CF.

These technologies were presented at the North American Cystic Fibrosis Conference (NACFC) 2020.

“Cystic fibrosis is an excellent [example] of a hard-to-treat, chronic condition. It is often unclear how the disease will progress in a given individual over time, and there are multiple, competing complications that need preventative or mitigating interventions,” Andres Floto, PhD, research director of the Cambridge Centre for Lung Infection at Royal Papworth Hospital, said in a press release.

An AI method called machine learning is an emerging field of computer science that predicts outcomes based on the ability to identify patterns in previously generated information. However, when applied to health conditions, predicting disease progression and outcomes can be difficult.

“Prediction problems in healthcare are fiendishly complex,” said Mihaela van der Schaar, PhD, director of the Cambridge Centre for AI in Medicine. “Off-the-shelf machine learning solutions, so useful in many areas, simply do not cut it in predictive medicine.”

To overcome these challenges, researchers developed new prediction models using machine learning approaches that can be applied to CF and other chronic diseases.

These new tools allow for accurate predictions of disease outcomes. In the past, researchers could predict only lung failure in CF patients based on data from the U.K. Cystic Fibrosis Registry — a database that includes demographic, genetic, and disease-related information of 99% of CF patients in the U.K.

“Almost everyone with cystic fibrosis in the UK entrusts the Registry to hold their patient data, which is then used to ensure the best care for all people with the condition. What’s exciting is that the approaches developed by Professor van der Schaar take this to a completely new level, developing tools to harness the complexity of the CF data,” said Janet Allen, MD, director of strategic innovation at the Cystic Fibrosis Trust.

“Turning such data into medical understanding is a key priority for the future of personalised healthcare,” Allen added.

New dynamic predictions will include disease course, health risks, additional associated health conditions (comorbidities), among many other factors influencing disease progression.

According to the team, these innovative predictive tools have the potential to help clinicians and researchers advance precision medicine, ultimately aiding patients who have long-term health conditions.

“Our medical [machine learning] technology has matured rapidly, and it is ready to be deployed,” van der Schaar said. “The time has come to bring its clear benefits to the individuals who need it most — in this case, the people living with cystic fibrosis.”