Machine learning can forecast whether a cystic fibrosis (CF) patient should be sent for a lung transplant with a 35% enhancement in accuracy over current methods. These were the results of collaborated research done between Oxford University’s Alan Turing Institute and the Cystic Fibrosis Trust.

Alan Turing, Institute fellow and Oxford professor Mihaela van der Schaar led the research published in Scientific Reports. It is the foremost machine learning study to implement a dataset of 99% of CF patients living in Britain.

Referring to an unnamed extract of UK CF Registry data, van der Schaar and her co-author, Ph.D. student Ahmed Alaa, built an algorithmic framework that utilizes machine learning to automate the procedure of creating a prognostic model for CF patients. AutoPrognosis, the algorithmic model, has an affirmative predictive value of 65%.

Alan Turing Institute fellow and Oxford professor Mihaela van der Schaar said: “The outcomes of our research with the Cystic Fibrosis Trust demonstrate that with the right in-depth expertise, anonymized data from a large population, and input from clinicians, we can create algorithmic methods to support clinicians in their day-to-day decision-making.

“I am grateful to the Trust for their support and advice and for insights from patients with cystic fibrosis we have worked within the course of this study. We look forward to continuing to work together to ensure that our work is useful for stakeholders such as patients, families of patients, clinicians and policymakers, for instance.”

 “For doctors and clinical teams, making decisions with their patients on whether they should be considered for a lung transplant is difficult. Accurate methods to help make that call are vital.”

The researchers believe that, in the future, the machine learning techniques developed in their study could prove beneficial for other diseases.