An algorithm might help to arrange a timely advance care planning conversation to agree with patients on their goals and wishes. The timing of such a discussion is crucial, and data have shown that the majority of cancer patients die without a documented conversation about their treatment and end-of-life preferences.
A new study published in JAMA Network Open and simultaneously presented at the American Society of Clinical Oncology (ASCO) Supportive Care in Oncology Symposium in San Francisco, by group of the University of Pennsylvania found that 51.3% of the patients whom the algorithm marked as “high priority” for these conversations subsequently died within six months of their evaluation, compared to 3.4% in the “lower priority” group.
“On any given day, it’s actually pretty difficult to identify which patients in my clinic would benefit most from a proactive advanced care planning conversation” explains lead author Ravi Parikh, MD, an instructor of Medical Ethics and Health Policy at the University of Pennsylvania. “Patients oftentimes don’t bring up their wishes and goals unless they are prompted, and doctors may not have the time to do so in a busy clinic. Having an algorithm like this may make doctors in clinic stop and think, ‘Is this the right time to talk about this patient’s preferences?'”
With a total of 26,525 patients, the researchers divided the sample into a training and a validation cohort, and a randomly selected encounter was included in either the training or validation set. They provided three different predictive models to the patients, finding then approximately half of the high-risk patients died within six months and almost 65 percent died approximately a year-and-a-half later, compared to 7% of low-risk patients.
In a survey of 15 oncologists, they agreed that 58.8% percent of those identified by the algorithm as “high risk” (100 patients of 171) were definitely appropriate for immediate conversations about their wishes.
“We’re excited about the scalability of this decision support method for providers, and not just in oncology” Parikh said. “Our process of using machine learning to flag high-risk patients in real time is broadly applicable, and our approach risk-stratifies patients in a usable way that just hasn’t been available to us before.”