Palliative Connect, a system powered by predictive analytics, is effective for increasing palliative care consultations for critically ill patients.
Researchers at Penn Medicine have developed a new predictive analytics tool that can help increase the number of palliative care consultations for seriously ill individuals, leading to improved quality of life for patients and their families.
Palliative care is specialized medical care that focuses on providing relief from the symptoms and stress of a serious illness, researchers explained in a study published in the Journal of General Internal Medicine.
Palliative care is appropriate for patients of any age and at any stage of illness, and research has shown that hospitals delivering timely, patient-centered palliative care can both improve the patient experience and reduce healthcare costs.
Want to publish your own articles on DistilINFO Publications?
Send us an email, we will get in touch with you.
“There’s widespread recognition of the need to improve the quality of palliative care for seriously ill patients, and palliative care consultation has been associated with improved outcomes for these patients,” said the study’s lead author, Katherine Courtright, MD, an assistant professor of Pulmonary, Allergy and Critical Care, and Hospice and Palliative Medicine.
The new system, called Palliative Connect, draws on EHR data and machine learning technology to develop a score based on 30 different factors of a person’s likely prognosis over six months. This is the timeframe providers use when deciding whether a palliative care consultation would benefit the patient.
Researchers evaluated Palliative Connect over an eight-week period, from December 2017 to February 2018. During that time, the team monitored 134 patients who had been admitted to a Philadelphia hospital and compared them to a similar group of 138 patients who were in the hospital before researchers implemented Palliative Connect.
The researchers found that in the group with Palliative Connect, consultations increased by 74 percent, going from 22 to 85 consultations. The results also showed that palliative care specialists visited patients earlier in their stay at the hospital – a day and a half sooner on average.
The system also allowed primary care providers to decline triggered consultations, and 43 percent did so. Reasons for declining triggered consultations included primary care teams feeling like they were already meeting patients’ needs, or that a patient didn’t have any palliative needs at that time.
Researchers noted that these results highlight the fact that prognosis isn’t the perfect way to measure the palliative care needs of every patient – it’s just one element of a serious illness. Additionally, the results showed that none of the patients or their caregivers declined a palliative care consultation after it was accepted by the primary care physician.
“This approach helps us get a foot in the door and really explain what palliative care is to patients and their families,” Courtright explained.
“Sometimes, there is this sense from primary teams that patients or families are hesitant or don’t want to talk about palliative care, but, when a palliative care clinician walks into the room and explains what they do, often people really are glad to see us there.”
Researchers believe that this is the first study to test a scalable, data-driven prediction system in a real clinical setting for palliative care. Going forward, the team expects to keep refining the Palliative Connect system. Currently, another study is aiming to evaluate the perspective of physicians, patients, and palliative care specialists to better inform the implementation of palliative care triggers.
“Our goal is for every seriously ill patient to have a conversation with their clinician about their priorities and wishes, and to document those priorities in the medical record,” O’Connor said. “We think that triggers are allowing us to do that, so we’ll continue to evaluate and refine in order to help more patients.”
Date: September 27, 2019
Source: Health IT Analytics
