Questions? +1 (202) 335-3939 Login
Trusted News Since 1995
A service for IT industry professionals · Sunday, September 19, 2021 · 551,769,052 Articles · 3+ Million Readers

Artificial Predictive Tools For Identifying Sepsis May Not Be Any Better Than Human Touch From Doctors and Clinicians

Hospitals across the country are turning to AI technology in order to treat patients with sepsis. However, a recent study raises doubt as to its accuracy.

MCLEAN, UNITED STATES, August 4, 2021 /EINPresswire.com/ --

As our senior population increases in numbers, hospitals across the country are turning to technology in order to treat patients with sepsis. It is for this reason that hospitals are relying on predictive tools. However, a recent study published in the Journal of the American Medical Association (JAMA) raises doubt as to their accuracy.

What is sepsis? It is the body’s response to infections that for the most part has no control over. The infections that lead to sepsis most often start in the lung, urinary tract, skin, or gastrointestinal tract. Almost any type of infection can lead to sepsis, and without treatment, can rapidly lead to tissue damage, organ failure, or death. According to the Centers for Disease Control and Prevention, one-third of patients in the US who die in a hospital had sepsis. Sometimes patients who develop pressure wounds become septic when those wounds become infected.

1.7 million adults develop sepsis annually. Of those, over 250,000 die as a result of sepsis.

The company that developed the tool -- Epic Systems -- does not agree with those findings. The company touts an 80 percent accuracy rate for its predictive model program. However, an article in the Washington Post on the JAMA study, 27,000 patients were part of the study, finding that the model developed predictive scores every 15 minutes, generating alerts on 1 in five patients. The study suggests the model did not identify two-third of sepsis cases, and, identified only 7 percent of patients whose sepsis was missed by a clinician.

The difference between the model created by the developer and the researcher’s assessment may be as simple as billing data.

"In essence, they developed the model to predict sepsis that was recognized by clinicians at the time it was recognized by clinicians," said Karandeep Singh, assistant professor of learning health sciences and internal medicine at Michigan Medicine, in a news release. "However, we know that clinicians miss sepsis."

The combination of the human touch from doctors and clinicians with a patient is key for dealing with patients who have sepsis and are being treated for it.

Often in my practice I come across situations where sepsis is listed as the cause of death on a death certificate. And while that information may be marked down on paper, it takes an experienced trial attorney to investigate the underlying cause, typically with the experience of a medical expert on sepsis, to determine if you have a viable malpractice case.

Mr. Downey is a nursing home abuse and neglect lawyer who has extensive experience handling cases involving sepsis. If your loved one died with Sepsis as a contributing cause, you should investigate whether a malpractice case is warranted. The Law Office of Jeffrey J. Downey will provide an initial, free consultation and evaluate your case to determine if a claim can be pursued. Don’t waste time as all malpractice cases have deadlines in which to file a claim.

If you or a loved one have been injured as a result of medical malpractice or negligence as a result of a health care provider such as a hospital, nursing home, or assisted living facility, contact the Law Office of Jeffrey J. Downey for a free consultation.

Law Office of Jeffrey J. Downey, PC
8270 Greensboro Drive, Suite 810
McLean, VA 22102
Phone: 703-564-7318
Email: jdowney@jeffdowney.com
On the web at www.jeffdowney.com

JEFF DOWNEY
The Law Office of Jeffrey J. Downey, P.C.
+1 703-564-7336
email us here
Visit us on social media:
Facebook
Twitter
LinkedIn

Powered by EIN Presswire


EIN Presswire does not exercise editorial control over third-party content provided, uploaded, published, or distributed by users of EIN Presswire. We are a distributor, not a publisher, of 3rd party content. Such content may contain the views, opinions, statements, offers, and other material of the respective users, suppliers, participants, or authors.

Submit your press release