Advanced Computing in the Age of AI | Thursday, March 28, 2024

Big Data Commands at Mount Sinai Hospital 

For the 160-year-old Mt. Sinai Hospital in New York City, organizing and making sense of its patient data has been a necessity to streamline its operations, but doctors are increasingly seeing ways in which it has opened the doors for more cost-effective patient care.

Through it, physicians have been able to tailor treatment plans to each patient, making sure that a drug is best suited not only for the patient’s condition, but also is ideal given their genetics. Already the hospital has seen 30-day readmission rates for Medicare patients drop by 56 percent after adopting its smart data initiative.

And cut readmissions rates bring with it cost savings as well. So far, the hospital has saved over $20 million every year since it turned to big data analytics in 2003.

Each night, the Mount Sinai Data Warehouse collects clinical, operational and financial information generated at the hospital and its faculty practice associates. The Icahn School of Medicine’s Minerva supercomputer then sweeps through 1.5 petabytes of these data to point out patient patterns that physicians may have missed.

Last year Mount Sinai added to this by installing a $120 million system to consolidate medical records, which the organization recently followed up on by installing a new computing cluster to join a $3 million super nearby. Mount Sinai has also reported more than $50 million in additions to its data infrastructure, including a 2,200 square-foot facility and another 70 teraflops of peak compute power.

“We can measure everything that’s going on now,” says Dr. Joel Dudley, director of Biomedical Informatics at Mount Sinai, in an interview with CruxialCIO. “We can embrace the complexity of human biology and disease, look at millions or billions of data points. How do we leverage all the tools we have available to build a 10-thousand foot view of human disease?”

The answer comes from combining not just reports directly related to a patient’s condition, but also looking deeper into family history and genetics to paint a comprehensive image of what’s happening biologically.

Still, despite the improvements that Mount Sinai has seen, Dudley says that there are still a number of problems in implementing big data analytics, particularly when it comes to fitting this in with doctors’ day-to-day routines.

“Doctors aren’t going to just use an iPad app. There’s no way in heck they’re going to just learn new systems and how to switch between them,” Dudley explains. Mount Sinai has already designed their systems around existing hospital workflows to overcome this hurdle, but it has yet to be seen how other healthcare organizations will approach the issue.

EnterpriseAI