A professor from the University of Chicago Booth School of Business has devised a new way to address one of the most controversial issues associated with the current CMS hospital star-rating system. In his recent study, “An Efficient Frontier Approach to Scoring and Ranking Hospital Performance,” forthcoming in the INFORMS journal Operations Research, Dan Adelman proposes an alternative methodology to scoring U.S. hospitals that addresses some of the limitations underlying the CMS’ Hospital Compare ratings. His findings are illustrated in a new searchable database of hospital quality ratings. Developed in collaboration with Chicago Booth Review, the database compares his system’s ratings against the government’s system.
According to Adelman, the central problem with CMS’ current approach – which uses what statisticians call the latent variable model – is that a hospital’s rating may go down even if it improves along every performance measure, relative to all other hospitals. Adelman argues that using an efficient frontier approach when calculating hospital ratings would result in more equitable comparisons that are not prone to such dramatic and unexpected swings. The key to this approach is that every hospital is given its own, unique set of measure weights that score it as close as possible to the best performing hospitals under the same weights. This contrasts with the CMS approach, which uses a common set of parameters across all hospitals in estimating the latent variable for a specific hospital.
- An Efficient Frontier Approach to Scoring and Ranking Hospital Performance. Operations Research. 1 Dec 2019
- Efficient Frontier Hospital Ratings: https://review.chicagobooth.edu/content/efficient-frontier-hospital-ratings