Algorithm identifies cancer patients in need of advance care planning conversations

October 25, 2019

Many cancer patients do not get the opportunity to discuss their wishes for treatment until their illness has progressed too far, when it may be too late to have those discussions with loved ones or physicians. Now, a Penn Medicine-led team has developed an algorithm that flags patients who would benefit most from a timely conversation about their end-of-life goals and wishes, in an effort to begin that dialogue sooner. In a new study--published today in JAMA Network Open and simultaneously presented at the American Society of Clinical Oncology (ASCO) Supportive Care in Oncology Symposium in San Francisco, CA--researchers found that 51 percent of the patients the algorithm flagged as "high priority" for these conversations subsequently died within six months of their evaluation, compared to less than four percent in the "lower priority" group. These findings suggest the algorithm accurately captures those patients who would benefit most from timely discussions about their goals, values, and preferences for care.

This study is believed to be one of, if not the first, to look into the application of a machine learning algorithm for oncology patients.

"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," said the study's lead author Ravi Parikh, MD, an instructor of Medical Ethics and Health Policy at the University of Pennsylvania and a staff physician at the Corporal Michael J. Crescenz VA Medical Center. "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?'"

The researchers applied three different predictive models to 26,525 patients receiving outpatient oncology care at two hospitals within the University of Pennsylvania Health System. Each used information commonly available in patients' electronic health records: demographic characteristics such as gender and age, standard comorbidity data such as whether a patient has high blood pressure, and laboratory and electrocardiogram data.

Compared to other machine learning techniques, such as "gradient boosting" and "logistic regression," the "random forest model" the team built in this study led to the best predictive results: Roughly half of the high-risk patients died within six months and almost 65 percent died approximately a year-and-a-half later (compared to 7.6 percent of low-risk patients). When 15 oncologists were surveyed, they agreed that 60 percent of those identified by the algorithm as "high risk" were definitely appropriate for immediate conversations about their wishes.

This algorithm was created with help from a team of Penn Medicine researchers who also developed a different algorithm for similar purposes, called Palliative Connect. That system is used to trigger consultations with Palliative Care staff, and was recently found to be particularly effective, increasing consultations by 74 percent. But the study led by Parikh is different in that it is targeted at increasing conversations between patients and the oncologists themselves in the outpatient setting.

"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."

Now that the algorithm has shown promise, Parikh said that it is being implemented at a medical center that was not part of the original pilot for this study. There, researchers are testing whether identifying the best patients for conversations actually does prompt the doctors to initiate those discussions. The researchers are currently working on a randomized controlled trial involving around 100 clinicians that will last between three and six months.

"Initial data from our pilot suggest that using the algorithm can boost these conversations," Parikh said.
The study was supported by the National Institutes for Health (grant numbers 5-T32-CA009615 and T32-GM075766-14).

Other Penn authors on this study include Christopher Manz, Corey Chivers, Susan H Regli, Jennifer Braun, Michael Draugelis, Lynn M. Schuchter, Lawrence M. Shulman, Amol S. Navathe, Mitesh S. Patel, and Nina O'Connor.

University of Pennsylvania School of Medicine

Related Cancer Patients Articles from Brightsurf:

Higher risk of death in cancer patients with COVID-19 may be due to advanced age and more pre-existing conditions, rather than cancer itself
New research presented at this this week's ESCMID Conference on Coronavirus Diseases (ECCVID, online 23-25 September) suggests that the poor outcomes and higher death rates in cancer patients with COVID-19 could be due to them generally being older and having more underlying conditions, rather than due to the cancer itself.

The Lancet: Prostate cancer study finds molecular imaging could transform management of patients with aggressive cancer
Results from a randomised controlled trial involving 300 prostate cancer patients find that a molecular imaging technique is more accurate than conventional medical imaging and recommends the scans be introduced into routine clinical practice.

The art of cancer caregiving: How art therapies benefits those caring for cancer patients
A recent Drexel University study showed coloring and open-studio art therapy benefits stressed caregivers of cancer patients.

Stress in cervical cancer patients associated with higher risk of cancer-specific mortality
Psychological stress was associated with a higher risk of cancer-specific mortality in women diagnosed with cervical cancer.

Cancer tissue-freezing approach may help more breast cancer patients in lower income countries
A new reusable device created by the Johns Hopkins University can help women with breast cancer in lower income countries by using carbon dioxide, a widely available and affordable gas, to power a cancer tissue-freezing probe instead of industry-standard argon.

Lots of patients with cancer, cancer survivors use but don't report complementary/alternative medicine therapies
This study used data from a nationwide survey to estimate how many patients with cancer and cancer survivors use complementary and alternative medicines (CAMS) in addition to or instead of conventional therapies, and how many don't disclose that to their physicians.

Colorectal cancer in patients with early onset is distinct from that in older patients
New research indicates that colorectal cancer diagnosed at an early age has clinical and genetic features that are different from those seen in traditional colorectal cancer diagnosed later in life.

Comparable risk of recurrent venous thromboembolism between patients with unprovoked venous thromboembolism and patients with cancer
Patients with venous thromboembolism (VTE) carry a high risk of recurrence.

Personalized cancer vaccine may increase long-term survival in patients with deadly brain cancer
An international Phase III study led by researchers at UCLA has found that a personalized GBM vaccine may increase long-term survival in some patients.

Ovarian cancer drug shows promise in pancreatic cancer patients with BRCA mutation
A targeted therapy that has shown its power in fighting ovarian cancer in women including those with BRCA1 and BRCA2 mutations may also help patients with aggressive pancreatic cancer who harbor these mutations and have few or no other treatment options.

Read More: Cancer Patients News and Cancer Patients Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to