Data Analytics as if Lives Depended on It
Predictive data is at work as we speak, saving lives. That’s because the healthcare has begun to embrace analytics to improve patient outcomes, and there is still vast potential to do more.
Data can make a life-saving difference at the most critical juncture, the emergency room. That’s the word from Kuang Xu of Stanford University and Carri Chan of Columbia University, who recently published a study that proposed the employment of predictive analytics could reduce delays up to 15% in emergency rooms – which can make a difference in saving lives.
As they explain, implementing patient arrivals in ERs, noting that predictive analytic models may help alleviate s high congestion, which results in patient waiting times. Predictive analytics can help ER managers “identify when congestion is going to increase and proactively diverts patients before things get ‘too bad.’” Xu and Chan estimate that predictive analytics “can reduce delays by up to 15%.”
Full article on Xu and Chan’s study here.
Essentially, the new model calls for preemptive action instead of reactive response, reducing ER wait times for all involved.”
Analytics is more than at the theoretical stage in the healthcare world. A few months back, as part of my work with Forbes Insights, I had the opportunity to speak with Dr. Robert Grossman, dean and CEO of NYU Langone Medical Center, who has been applying analytics to his organization’s quality of services.
Grossman’s team began collecting data on patients’ lengths of stay, discharge times, number of open beds, and infection rates, as well as metrics related to medical research, such as lab space/dollar density and grant money awarded. The data is then provided to administrators and clinicians through a dashboard. Delivering efficiency is one positive result from this data-driven information, Grossman illustrates. “If a patient comes to NYU, and they come through emergency, you don’t want them to wait five hours for a doctor,” he says. “We have that on a dashboard, and have reduced the average wait time to see a doctor to usually less than 10 minutes,” he says.
The dashboard also includes information on the number of open beds at any given moment, and the percent of patients who were discharged before noon each day. With just a few clicks, the dashboard can show the average time from “wheels in” to “wheels out” for each operating room, each surgeon, or for each different type of procedure performed at the institution.
Medical center professionals such as nurses, physicians and front-line workers also have access the metrics specific to their roles. For in instance, nurses follow the “Discharge Before Noon” performance measurement and, by using the dashboard, are able to see if their units are within target and how they compare to others.
Prior to the information being posted on the dashboard, the medical center’s Discharge Before Noon measurements was below target. After this metric was posted the dashboard, and once the medical center community knew it was being watched closely by the Dean and others, the data improved. “Our rate of Discharge before Noon is 4.5%,” Grossman says. By comparison, the industry average is about eight percent.”
It’s commendable that organizations are able to run smarter and more forward-thinking because of data analytics. It’s even better that analytics is now helping to save lives.