A recent study published in Anesthesiology by Hatib etal. [Anesthesiology 10 2018 Vol. 129, 663-674] from the University of California (UC) at Irvine Medical Center demonstrated that large sets of real-time data—high-fidelity arterial waveforms—applied to machine learning algorithms could identify patients experiencing onset of hypotension up to 15 minutes before its occurrence. UC Irvine used Bernoulli One to collect more than 500,000 waveforms, which were then used to train a machine-learning algorithm to predict hypotension.
Between 2006 and 2011, the Health Technology Foundation (HTF), a non-profit organization that advocates for the development of safe and effective health IT, conducted a series of surveys designed to capture the impact of device alarms on clinical workflow and hospital practices.
Over the past decade, there have been many improvements in the healthcare industry. The number of different technologies used across hospitals is immense. Many of these technological advances have streamlined workflows, brought efficiencies to processes, improved patient safety and care, and reduced clinical workload.
The average hospital room contains between 15 and 20 medical devices. Each patient will generate about 135 alarms each day—or about 11 alarms per hour for a 12-hour nursing shift.
The ECRI Institute, an independent authority on the medical practice and product safety, recently published its Top 10 Patient Safety Concerns for 2019. All the items in the report are important, but items 6, 8 and 10 merit additional scrutiny. They include, respectively:Detecting Changes in a Patient’s Condition, Early Recognition of Sepsis across the Continuum, Standardizing Safety Efforts across Large Health Systems