Is it responsible to transfer a patient who is in the Intensive Care Unit (ICU) to the nursing ward? The doctor's decision is now supported by artificial intelligence (AI) or artificial intelligence. In doing so, the Amsterdam University Medical Center (UMC) is ahead of the rest.
The Amsterdam hospital announces this in a press statement (1).
The Amsterdam UMC emphasizes that transferring an ICU patient carries risks. Moving too early can mean that the patient's health deteriorates. Bringing him back to the ICU increases the risk of death. Letting a patient stay too long in the ICU may take up a bed that someone else could have used better.
"All very undesirable with the relatively low number of ICU beds in the Netherlands, a lack of ICU nurses and high absenteeism since corona," says Paul Elbers, intensivist at Amsterdam UMC. With a possible new corona wave ahead, optimal use of ICU beds is of great importance.
Elbers and his colleague Patrick Thoral, together with software developer Pacmed, came up with something to improve the movement of ICU patients: Pacmed Critical. The software collects information from ICU patients in real time. Artificial intelligence compares this data with that of thousands of patients who have been in the ICU in the past. Using this data, the software predicts how likely a patient is to end up in the ICU again within a week.
Pacmed Critical not only shows the outcome of the prediction: it also shows a list of factors on which the prediction is based. Ultimately, it is up to the intensivist whether he follows this advice, or goes by his gut. Thoral explains that he sees the outcome of the software as a second opinion. "And by studying how the software is used in practice, we want to further increase the value for patients and caregivers."
To develop Pacmed Critical, the developers used pseudonymized (2) patient data from some 25,000 people recently treated in the ICU.
The rate of readmissions from the nursing ward to the ICU is between 5 and 10 percent in our country. Albers and Thoral hope to reduce this percentage with the software. The intensivists say they have a worldwide first with Pacmed Critical. "As far as I know, it is the only medical decision support based on artificial intelligence used in this way in a hospital. I mean decision support at the ICU patient's bedside, where algorithms and developed models are fed directly and in real-time with data from the electronic patient record," Thoral says.
"A huge milestone," is how Wouter Kroese of Pacmed calls the software. "It is incredibly important that AI is finally making the step into medical practice. This must be done responsibly and safely. Together with Amsterdam UMC, we have taken all the necessary steps for that. And we comply with all regulations to be able to use the software as a medical device. We are ready to scale up and expand the software so that it can help solve capacity and staffing challenges in hospitals throughout the Netherlands and beyond."
https://www.amsterdamumc.org/nl/vandaag/wereldprimeur-artificial-intelligence-ondersteunt-artsen-bij-beslissing-ontslag-ic-patient.htm
https://www.vpngids.nl/privacy/
