From the October 2017 issue of HealthCare Business News magazine
Engaging patients through evidence-based programs
New intervention programs often begin with an evidence-based model that has been shown to work effectively in another setting. However, when academic evidence-based interventions are translated to a real-world setting, the methods and intensity often differ from the original study. Unless these differences are tracked, problems of program execution may be confused with problems of patient selection or intervention methods.
Data analytics can be used to establish a “fidelity score” that tracks how closely an implemented program follows the ideal design protocol. Calculating a fidelity score for each patient and each program allows managers to differentiate between problems with program execution vs. potential misalignment of the program strategy itself.
Evaluating clinical and economic outcomes
Even hospitals that have good risk predictions, use data to match patients to the appropriate programs and track program fidelity may still lack an effective measurement framework. Readmission programs can feel like “spray and pray.” How can you be confident which programs are working and what needs to be done to improve program outcomes over time?
An effective measurement framework must be able to distinguish the impact of an intervention program from the effects of other initiatives and environmental noise. Whereas risk prediction models rely on emerging data markers, hospitals should be using “fully baked” data for program evaluation. At a program level, economic and clinical outcomes should be compared to a contemporaneous, risk-adjusted comparison group that did not receive the intervention.
The gold standard for measurement is a randomized clinical trial. However, in the real world, it’s not always feasible to establish a formal control group. More often, a comparison group must be constructed by selecting patients that did not receive the intervention and are statistically similar to the intervention group.
Closing the loop
There are many causes of readmissions. In response, hospitals will need a portfolio of intervention programs to address the diverse risk factors of their high-risk population. Simply deploying a static risk stratification model is not enough. Organizations need an integrated learning loop system that enables continuous improvement in identifying, matching, engaging and evaluating readmission reduction programs.
About the author: Neil Smiley founded Loopback Analytics in 2009 to deliver an advanced Software-as-a-Service platform health care providers can use to prevent costly readmissions. The Loopback Analytics team currently works with the largest pharmacy, hospitalist group, health system, payer and senior housing provider in the nation, providing proven intervention solutions that improve clinical outcomes and reduce the total cost of care.
Back to HCB News
