Death Panels Next? FDA Approves A.I. Model That Predicts Your Chance Of ‘Sudden Expiration’

    The Food and Drug Administration (FDA) has approved the very first artificial intelligence (AI) computer that monitors a patient’s vitals to help forecast sudden death up to six hours before the grim reaper shows up.

    Excel Medical, a medical device data company in Florida, developed the deep learning algorithm called WAVE Clinical Platform for the eradication of unexpected hospital deaths.

     

    WAVE automatically calculates the risk of the patient through subtle changes in vitals, which provides hospital staff with critical information of when the patient is expected to kick the bucket. The algorithm monitors the patient on a continuous basis, a task that is very challenging for hospitals, as the demographic crisis strains the U.S. healthcare system.

    Stephen McBride of Mauldin Economics describes the situation:

    Few investors understand the magnitude of the looming demographic crisis and its ramifications. The first Baby Boomers turned 70 last year. At the same time, the US fertility rate is at its lowest point since records began in 1909. This disastrous combination means by 2030, those aged 65 and older will make up over 20% of the population.

     

    In realtime, on top of the patient’s vitals, the algorithm also factors in digital medical records, past medical history, family history, medications, age, and vital signs. Below is an example of the alert system interface.

     

    Speaking to Digital Trends, ExcelMedical’s Chief Strategy Officer Mary Baum said, “We do not have enough physicians or nurses, and we have an aging population who are sicker and who need more resources and services.”

    According to IFL Science,

    It has also just become the first AI platform of its kind to be cleared by the US Food and Drug Administration (FDA). This decision was based on a series of studies at the University of Pittsburgh Medical Center that showed the AI platform could prevent unexpected deaths in hospitals. Another more recent study, using similar technology by Stanford University, outlined on the preprint server arXiv, explains how a deep-learning algorithm can correctly predict an otherwise-unexpected death in 90 percent of cases.

    The University of Pittsburgh Medical Center (UPMC) administered phase 1, 2, and three of the clinical trials for the AI computer. According to the clinical, UPMC’s control cohort had six unexpected deaths, while the AI trail cohort had zero.

    The WAVE platform incorporates an algorithm called the Visensia Safety Index (VSI), developed by Oxford University. Excel licenses the algorithm, which was approved for use in 2011. The new clearance from the FDA, granted earlier this month, is for the algorithm’s use in tandem with Excel Medical’s platform.

    Here is the University of Pittsburgh Medical Center (UPMC) decision tree for hospital staff members when an AI alert of a patient is triggered.

     

    “Everything we do as an organization aligns toward and supports the goal of eradicating unexpected deaths in hospitals,” says Lance Burton, General Manager of Excel Medical. “People may say zero unexpected deaths is unattainable. We say anything other than zero is unconscionable.”

    To sum up, AI’s gift to humanity is the knowledge of when you supposed to die six hours before. As for the baby boomer generation, what would you do in your last six hours? Further, what happens when the technology progresses to 12-hours, and or even days in advance of your death. How will the human psyche process such knowledge?

    How long before the same A.I. can predict your sudden death a few years out? …and decide whether you’re worth keeping around?

    Loading...

    LEAVE A REPLY

    Please enter your comment!
    Please enter your name here