Hospital ranking lists — such as those published annually by the US News and World Report and Healthgrades — are a great way for the nation’s largest hospitals to generate good PR. However, they may not be as helpful when it comes to understanding the strengths and weaknesses of individual hospitals and how they compare to one another.
Trilliant Health, a healthcare-focused predictive analytics and market research firm has done just that with a new hospital benchmarking index. Powered by the company’s AI Similarity indexreleased Thursday, promises to serve as a functional tool that healthcare stakeholders can use for strategic planning.
The index compares more than 2,000 urgent care hospitals. Healthcare stakeholders across the industry—including hospitals, payers, device companies, drug manufacturers, and technology providers—can use the tool to inform their strategies for things like competitive analysis, managing clinical quality programs, mergers, acquisitions and sales of products.
Applying mathematical precision to strategic healthcare planning minimizes the risk of capital misallocation for providers, payers and manufacturers of medical products, Sanjula Jain, Trilliant’s principal investigator and senior vice president of market strategy, said in an interview.
To build its index, Trilliant uses claims data from everyone Medicare Advantage plan and “basically any commercial payer,” according to Jane. The data Trillint uses for its index “can basically tell you about any doctor-patient interaction as long as it generates a bill,” she said.
This data allows healthcare stakeholders to answer many questions, such as which drugs are prescribed in which hospitals or where doctors see the most patients. In addition to answering these questions, users can also use the index to “objectively and mathematically compare hospitals,” Jain said.
The index creates similarity scores for hospitals that are designed to show relevant hospital peers based on factors such as financial performance, CMS quality metrics, patient mix and market share. An interactive data visualization tool allows users to isolate variables for specific hospital comparisons. For example, if a user wants to see a hospital’s comparable peers as it relates only to readmission rates and hospital-acquired infections, they can.
“If you’re trying to compare hospitals on hundreds of variables, it becomes a mathematical nightmare to do at scale,” Jain said. “This is where machine learning comes in. Until now, no one has really been able to do an objective comparison because there has been such a computational limitation in the industry.”
Jain credited Trilliant’s team of scientists and engineers with building algorithms to compare hospitals to their respective peers at scale. These algorithms often show that the most reputable hospitals in the country are quite different, she pointed out.
For example, when you enter Johns Hopkins Hospital into the index, you might expect that its peers would be other reputable hospitals such as NYU Langone Medical Center or Cedars-Sinai Medical Center. When you plug it in, however, the index reveals that its real peers are hospitals like Thomas Jefferson University Hospital and Tampa General Hospital.
Hospitals and health systems are trained to think that their peers are sizeable, according to Jane. However, not all of the largest health systems by revenue face the same challenges, and the index can help determine what operational differences each individual hospital faces.
Photo: Filograph, Getty Images