Friday, March 29

The AI ​​already decides in American hospitals the order to attend in the ER


Artificial intelligence is used for much more than retouching your photos in each selfie. In the United States, AI has begun to help hospitals with patients who need it most… without them even knowing it.

Hospitals are betting that artificial intelligence can help identify and treat the highest-risk patients in their emergency departments, hospital wards, and intensive care units, for hazards such as: infectious sepsis, impending cardiac arrest, or stroke.

Artificial intelligence algorithms are processing vast amounts of data in electronic medical records, looking for patterns to predict future outcomes and recommend treatments.

In this way they are creating early warning systems to help hospital staff detect subtle but serious changes in a patient’s condition that are not always visible and to predict which patients who are about to be discharged are at higher risk of relapse of their disease.

These systems are just one of a wide range of AI projects in healthcare, from helping to detect cancer in radiology images to identifying drugs to be tested in patients with different diseases.

But This predictive technology holds particular promise for transforming care and improving patient safety in ER and ICU settings, provided that systems can be designed to avoid some of the medical, technological, and ethical problems that have arisen from mixing the science of machine learning with the art of medicine.

In this sense, a team of engineers and doctors has developed a prediction model called Advance Alert Monitor, which can identify half of the patients who are going to get worse.

Also Read  French nuclear energy is experiencing a crisis, but its aging is nothing more than a mirage

It continuously analyzes patient data and assigns scores that predict the risk of ICU transfer or death. Time horizon allows staff to reach patients when they are still relatively stable and may need only enhanced review or monitoring.

DNA

Vaccines against cancer, herpes and chickenpox: mRNA technology at the service of medicine

To minimize “alert fatigue”, results are not displayed directly to hospital staff, but are monitored remotely by specially trained nurses so that bedside nurses can focus on caring for patients.

If a patient’s score reaches a certain threshold, the remote nurse contacts the rapid response nurse on the wardwho in turn initiates a formal evaluation and contacts the patient’s physician, who may initiate a rescue program that could include transfer to the ICU.

In a study conducted in 19 hospitals over nearly three years, published last November in the New England Journal of Medicine, the team reported that the predictive model was associated with lower hospital mortality, a lower incidence of admissions to the ICU and a shorter length of stay.

Leave a Reply

Your email address will not be published. Required fields are marked *