AI Closer To Predicting When Cancer Patients Will Die
Stanford University School of Medicine has developed an algorithm that utilizes artificial intelligence to help predict which cancer patients will die within three to 12 months to provide better and more accurate treatment options for them.
The algorithm correctly predicted patients’ remaining life expectancies in nine out of 10 cases in early tests, dean of the Stanford University School of Medicine Lloyd Minor told the Wall Street Journal.
Minor clarifies that “AI isn’t going to make decisions for patients or for doctors, and it’s not going to deny nor discourage care.”
But studies have shown that “physicians tend to over-estimate prognoses, which in combination with treatment inertia results in a mismatch between patients wishes and actual care at the end of life,” according to the Stanford study. “[A]pproximately 80% of Americans would like to spend their final days at home if possible, but only 20% do.”
Palliative care treats the side effects of going through treatment of serious diseases such as cancer, as opposed to hospice care, which comes after the illness is treated and defeated, according to the U.S. National Library of Medicine.
“[P]hysicians may not refer patients likely to benefit from palliative care for multiple reasons such as overoptimism, time pressures, or treatment inertia,” according to the Stanford report.
The Stanford researchers collected data from hundreds of thousands of medical records. By using Deep Learning and Electronic Health Record (EHR) data, currently a pilot program, the algorithm evaluates and decides “which brings patients who are likely to benefit from palliative care services to the attention of the Palliative Care team.”
“I don’t pretend AI is a panacea,” Minor said. “An algorithm isn’t going to make decisions for doctors or patients, but it can help inform their choices by providing them with insight they’ve never had before.” He also said it “empowers them to spend that time doing what brings them joy, and to be with those whom they love.”
Send tips to firstname.lastname@example.org.
Content created by The Daily Caller News Foundation is available without charge to any eligible news publisher that can provide a large audience. For licensing opportunities of our original content, please contact email@example.com.