Diameter DH Predict

Background

In 2009, a landmark study in the New England Journal of Medicine profiled readmission rates for Medicare patients. It found that 1 in 5 patients are readmitted within 30 days and that suboptimal care continuity was a source of poor quality and high cost. This and other research studies may have incentivized the government to reduce hospital readmissions. The Affordable Care Act of 2010 granted the authority for Medicare to penalize hospitals with readmission rates above the national average.

There are multiple ways to triage patients at risk of readmission. While dozens of predictive models have been developed and published over the past several years, several suffer from two major drawbacks.

1. Some existing readmission models require manual patient review, meaning clinicans must spend excess clinical time assembling patient information for entry in a worksheet or semi-automated tools.

2. Some automated models require time-intensive and expensive implementation, including extensive data mapping, normalization, and warehousing. These models often fail to deliver timely predictions and positive return-on-investment.
Diameter Health's approach to readmission prediction solves these challenges by only using data collected in existing clinical workflows and leveraging interoperability standards to automatically access clinical data from electronic health records. This provides lightweight and quicker implementations at a cost that provides favorable ROI.

Return on Investment

Using Diameter Health's prediction tools to triage high risk patients with additional engagement may provide a large return-on-investment for both hospitals and accountable care organizations.

Diameter DH Predict 00262 Government Quality Measures Readmission Diameter Health
Evidence: 
  1. Horwitz, LI, Partovian, C, Lin, Z, et al. Development and Use of an Administrative Claims Measure for Profiling Hospital-wide Performance on 30-Day Unplanned Readmission. Annals of Internal Medicine Ann Intern Med. 2014;161(10_Supplement). doi:10.7326/m13-3000.
    View Reference  
CID: 
00262