AI can alert doctors when patients might get sicker

Artificial intelligence (AI) is transforming the healthcare landscape, providing tools that help doctors make better decisions and save patients. A recent study demonstrates the profound impact that artifical intelligence can have in clinical settings.

This research, conducted by experts at Mount Sinai, reveals that AI-generated alerts can significantly improve patient care and outcomes.

Enhancing patient care with AI alerts

The results of the study showed that patients were 43% more likely to have their care escalated and were significantly less likely to die when their healthcare teams received real-time AI alerts. These alerts signaled adverse changes in patients’ health, enabling timely interventions.

“We wanted to see if quick alerts made by AI and machine learning, trained on many different types of patient data, could help reduce both how often patients need intensive care and their chances of dying in the hospital,” explained study lead author Dr. Matthew A. Levin, Director of Clinical Data Science at Mount Sinai Hospital.

“Traditionally, we have relied on older manual methods such as the Modified Early Warning Score (MEWS) to predict clinical deterioration.”

“However, our study shows automated machine learning algorithm scores that trigger evaluation by the provider can outperform these earlier methods in accurately predicting this decline. Importantly, it allows for earlier intervention, which could save more lives.”

Real-time AI alerts in clinical settings

The study was a non-randomized, prospective analysis involving 2,740 adult patients admitted to four medical-surgical units at Mount Sinai Hospital.

Patients were divided into two groups: one received real-time alerts by AI based on predicted health deterioration, while the other did not receive these alerts, although they were created.

In units where alerts were suppressed, patients who met standard deterioration criteria still received urgent interventions.

The findings for the intervention group were promising:

• Patients were more likely to receive medications to support heart and circulation, indicating early action by doctors.
• Patients were less likely to die within 30 days.

A learning health system

“Our research shows that real-time alerts using machine learning can substantially improve patient outcomes,” noted senior study author David L. Reich.

“These models are accurate and timely aids to clinical decision-making that help us bring the right team to the right patient at the right time.”

“We think of these as ‘augmented intelligence’ tools that speed in-person clinical evaluations by our physicians and nurses and prompt the treatments that keep our patients safer. These are key steps toward the goal of becoming a learning health system.”

Implementation and future prospects

Although the study was terminated early due to the COVID-19 pandemic, the algorithm has been deployed in all stepdown units within Mount Sinai Hospital.

These units cater to patients who are stable but still require close monitoring – a critical stage between intensive care and general hospital areas.

A specialized team of intensive care physicians now visits the 15 patients with the highest prediction scores daily, providing treatment recommendations to the attending doctors and nurses.

As the algorithm is continually retrained on larger patient datasets, it improves its accuracy through reinforcement learning.

Beyond this clinical deterioration algorithm, Mount Sinai researchers have developed and implemented 15 additional AI-based clinical decision support tools across the health system.

These advancements mark a significant step towards integrating AI in healthcare, enhancing patient care, and paving the way for more innovative solutions in the future.

Improving patient outcomes

The deployment of AI in healthcare, as demonstrated by the Mount Sinai study, holds immense potential for improving patient outcomes.

Real-time AI alerts not only enable timely interventions but also support healthcare professionals in making informed decisions swiftly.

As AI technology evolves, its role in clinical settings will undoubtedly expand. This promises a future where healthcare becomes more efficient, effective, and patient-centric.

AI tools, like real-time alerts, will enhance decision-making, enabling timely interventions and better patient outcomes. As AI integrates further into healthcare, it will support medical professionals in providing higher quality care.

The continuous improvement of AI algorithms will lead to more accurate predictions and tailored treatments. Ultimately, AI will transform healthcare, making it more responsive and focused on patient needs, leading to improved overall health and well-being.

The study is published in the journal Critical Care Medicine.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–