In an effort to improve access to palliative care, a team of researchers from Stanford (Calif.) University developed an artificial intelligence algorithm to predict patient death, CNBC reports.
Here are four things to know about the algorithm.
1. Less than half of patients admitted to a hospital in need of palliative care receive it, in part because physicians tend to overestimate how long a patient will live, according to CNBC. Resources for palliative care are also limited, which makes accurately referring patients particularly important.
2. To identify those who would most benefit from palliative care, the Stanford researchers developed an AI algorithm to predict those likely to die between three and 12 months following examination. The researchers created the algorithm using data from the EHRs of 2 million patients with advanced illnesses seen at Stanford Hospital and Lucile Packard Children's Hospital in Palo Alto, Calif.
3. The researchers' goal is for physicians to use the algorithm to do an initial screen of patients. If a patient is recommended for palliative care, a physician will review the patient's chart in more depth prior to a referral.
"The human doctor is always in the loop, and the decision of the program is only interpreted as a case worthy of palliative care consult — and not as a prediction of death," Anand Avati, a graduate student in the Stanford Department of Computer Science and lead author on the study, told CNBC.
4. In a research paper submitted to arXiv.org, the study authors suggested, "Our predictions enable the palliative care team to take a proactive approach in reaching out to such patients, rather than relying on referrals from treating physicians, or conduct time consuming chart reviews of all patients."