A new order announced by French President Emmanuel Macron on Monday means French nurses like Diane Braccani must get vaccinated – Copyright AFP WAKIL KOHSAR
There's been an ongoing debate about the benefits of artificial intelligence to healthcare workers' decision-making abilities, but a new study from Mount Sinai leans even further into beneficial territory, suggesting that real-time alerts to declining health could speed treatment and reduce hospital deaths.
By implementing and evaluating machine learning interventions to improve clinical care and patient outcomes, researchers can develop a critical step in moving clinical deterioration models from the bay to the bedside.
Research has found that when care teams receive AI-generated alerts indicating adverse changes to a hospitalized patient's health, they are 43% more likely to intensify care and are significantly less likely to die.
Traditionally, healthcare professionals have relied on older manual methods, such as the Modified Early Warning Score (MEWS), to predict clinical deterioration. New research shows that an automated machine learning algorithm score that triggers an assessment by a healthcare provider outperforms these previous methods in accurately predicting this deterioration.
To demonstrate this, a nonrandomized prospective study was conducted on 2,740 adult patients admitted to four medical-surgical units at Mount Sinai Hospital in New York. Patients were split into two groups: those who received real-time alerts based on the predictability of deterioration and sent directly to a “rapid response team” of nurses, physicians, or intensivists, and those who had alerts generated but not sent.
In wards where alarms were suppressed, patients who met standard deterioration criteria received urgent intervention from the emergency response team.
Data from the intervention group showed patients were more likely to be prescribed medications to support their heart and circulation, indicating that their doctors were taking action earlier, and they were less likely to die within 30 days.
The researchers therefore concluded that real-time alerts using machine learning could significantly improve patient outcomes, suggesting that “augmented intelligence” tools could speed up in-person clinical assessments by doctors and nurses.
The study has been published in the journal Intensive Care MedicineThe study is titled, “Real-time machine learning alerts to prevent escalation of care: a non-randomized clustered pragmatic clinical trial.”
In addition to the clinical deterioration algorithm, the researchers developed and deployed 15 additional AI-based clinical decision support tools across the Mount Sinai Health System.
