Home / Others / When will I die? AI can now predict the moment of death in a disturbing advance for medical care

When will I die? AI can now predict the moment of death in a disturbing advance for medical care



It can be morbid, but knowing when you're going to die would make your life easier since you could start preparing and attaching loose ends. Scientists at Stanford University have used Artificial Intelligence to predict whether the patient will die within three months to a year, to help doctors better recommend palliative care.

Related: Do you need a job? Why artificial intelligence will help human workers will not hurt them

The objective, according to the researchers, is not to replicate a spooky story directly from a science fiction program, but to help improve lives. As the study authors write in their article, previous research has shown that 80 percent of Americans would like to spend their last days in the comfort of their own homes. Only 20 percent do so, in part because doctors do not offer an accurate prognosis and patients often end up receiving advanced treatments.

  GettyImages-810249852 Researchers have developed an algorithm using deep learning to predict mortality. YAMIL LAGE / AFP / Getty Images

"Too often, advanced disease becomes a medical crisis and patients end up in the ICU, where events can achieve a momentum of their own, resulting in interventions increasingly aggressive that do not serve patients and their families well, "study co-author and research scientist Ken Jung wrote to Newsweek in an email. 19659009] He emphasizes that palliative care is more than just the care that is received when a person is dying and must involve making sure that the patient's wishes are known and cared for. In addition, palliative care works to maintain a high quality of life by assisting with pain management and social support. As Jung explained to Newsweek, the palliative care service goes through references of the primary care team of the patient and professionals working in this field include doctors and nurses, social workers, nutritionists and chaplains, according to the Institute National Health

"First-line care teams do not always recognize the need," Jung said. "They often focus on treating the acute complaints that brought the patient to the hospital, or they may be overly optimistic about a particular patient's prognosis."

His team developed an AI algorithm that studied the health records of approximately two million patients admitted to two hospitals. The algorithm determined the morality of the patient within the next three to 12 months.

"The idea behind the use of the algorithm is … so that palliative care specialists can communicate with the patients for whom the algorithm recommends, then the team will review the patient's medical history and communicate with their doctor to see if help is needed.

"Only after [receiving a] palliative care doctors would get in touch with patients," Jung wrote.

Researchers donate I do not fully understand how their deep learning algorithm determined mortality, but, say the researchers, this is not a concern since their project tries to identify people who could use palliative care.

"Palliative care intervention is not tied to why someone is getting sick" , said Jung Spectrum a publication of the Institute of Electrical and Electronics Engineers. "If it were a hypothetical case different from & # 39; al Who will die and we have to choose treatment options? In that case we want to understand the causes of the treatment.

To help To alleviate potential ethical concerns, scientists emphasize that these are only the initial stages of research and that the algorithm will never be used alone.


Source link