黑料吃瓜群网

Stanford 黑料吃瓜群网 is using an AI-based model that predicts when a patient is declining and flags the patient's physicians and nurses.

The alert system helps clinicians connect more efficiently and effectively as well as intervene to prevent patients from deteriorating and landing in the intensive care unit, said , MD, a clinical associate professor of medicine and medical informatics director for digital health. Li is the senior author of the study by Stanford Medicine that shows the potential of AI as a facilitator of connection between doctors and nurses. In a news update with Hanae Armitage, Li shared details of the project and how it fosters connection in a ceaselessly buzzing hospital environment. Below are the highlights:

How does the model work?

The algorithm is a prediction model that pulls data 鈥� such as vital signs, information from electronic health records and lab results 鈥� in near-real time to predict whether a patient in the hospital is about to suffer a health decline.

Physicians aren鈥檛 able to monitor all of these data points for every patient all of the time, so the model runs in the background, looking at these values about every 15 minutes. It then uses artificial intelligence to calculate a risk score on the probability the patient is going to deteriorate, and if the patient seems like they might be declining, the model sends an alert to the care team.

How can it benefit hospitals?

This model is powered by AI, but the action it triggers, the intervention, is basically a conversation that otherwise may not have happened.

Nurses and physicians have conversations and handoffs when they change shifts, but it鈥檚 difficult to standardise these communication channels due to busy schedules and other hospital dynamics, Li said. The algorithm can help standardise it and draw clinicians鈥� attention to a patient who may need additional care. Once the alert comes into the nurse and physician simultaneously, it initiates a conversation about what the patient needs to ensure they don鈥檛 decline to the point of requiring a transfer to the ICU.

Implementation and evaluation

The model originally sent an alert when the patient was already deteriorating, so the researchers adjusted it to focus on predicting ICU transfers and other indicators of health decline. The aim was to ensure the nursing team was heavily involved and felt empowered to initiate conversations with physicians about adjusting a patient鈥檚 care.

When the tool聽鈥� that had been running for almost 10,000 patients 鈥� was evaluated, there were significant improvements in clinical outcomes. There was a 10.4% decrease in deterioration events, defined by the researchers as transfers to the ICU, rapid response team events or codes 鈥� among a subset of 963 patients with risk scores within a 鈥渞egression discontinuity window鈥�, which basically means they鈥檙e at the cusp of being high risk. These are patients whose clinical trajectory may not be as obvious to the medical team. For that group of patients, this model was especially helpful for encouraging physicians and nurses to collaborate to determine which patients need extra tending.

Feedback from nurses and physicians

The reactions have overall been positive, but there is concern about alert fatigue, since not all alerts are flagging a real decline, the researchers suggested. When the model was validated on data from patients prior to implementation, the researchers calculated that about 20% of patients flagged by the model did end up experiencing a deterioration event within six to 18 hours. At this point, even though it鈥檚 not a completely accurate model, it鈥檚 accurate enough to warrant a conversation. It shows that the algorithm doesn鈥檛 have to be perfect for it to be effective.

The researchers are now working on improving accuracy to enhance trust. The study by Li; informatics postdoctoral scholar and lead author , MD; , MD, PhD, clinical professor of medicine; , director of operations for primary care and population health; and Jerri Westphal, nursing informatics manager, has been published in聽 JAMA Internal Medicine.

Originally published .

Image credit: iStock.com/ipopba