Neil Smiley
How to improve readmission rates with a population of at-risk patients
October 13, 2017
By Neil Smiley
Upon admission, most hospitals utilize some form of risk stratification, either manual assessments or automated risk scoring running alongside their EHR.
LACE is a popular risk algorithm used by hospitals, which uses a combination of length of stay, acuity, comorbidities and history of emergency department visits to rank a patient’s readmission risk on a scale of 1 to 19. Patients with high readmission risk scores are then flagged for more intensive therapies and interventions.
However, just using a static risk prediction model to stratify patient populations at the time of admission is not enough. Hospitals with high populations of at-risk patients must leverage data analytics at every step along the care continuum, including:
• Identifying high-risk patients.
• Matching patients to interventions.
• Engaging patients through evidence-based programs.
• Evaluating clinical and economic outcomes.
Identifying high-risk patients
Hospitals have the opportunity to significantly improve on basic risk prediction models like LACE by integrating a more robust set of real-time data markers that are updated throughout a patient’s care journey. For example, LACE does not utilize data on social factors, medications, labs or unstructured data such as admitting complaint and clinical notes.
In addition to understanding what data is available, it is also essential to understand when data is available. For example, it’s not uncommon for a final diagnosis to arrive five to seven days after discharge. Prediction models usually have to rely on “proxy data” such as admitting complaint, medication lists, lab values and natural language processing of free form text to allow for early identification of patients with high-risk conditions.
Unless hospitals are part of a fully integrated health system, they will also need to collaborate with upstream and downstream care partners to fill in data gaps across the care continuum. Each hospital will vary in coding conventions and care practice patterns. Prediction models must be adaptive to these differences in order to fully leverage the most up-to-date information at each implementation site.
Once a prediction algorithm is deployed, hospitals should have a regular process to evaluate model performance. Risk prediction models will need to be periodically adjusted to reflect changes in underlying coding systems and care practices, and to capitalize on new data markers as they become available. Risk models should also be leveraging machine learning to steadily improve prediction accuracy as more outcome data becomes available.
Matching patients to interventions
Once high-risk patients have been flagged, data analytics should also be leveraged to match patients to the most appropriate interventions using individual patient risk characteristics and the inherent constraints associated with each intervention program. Patients with the highest risk scores may not always be the best candidates. For example, patients with 10 or more medications are typically less responsive to phone-based medication adherence programs and may need home visits instead.
Creating a data feedback loop for each program that analyzes which patients respond and which don’t enables a data-driven approach to refine program eligibility criteria and improve intervention methods.
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.
Upon admission, most hospitals utilize some form of risk stratification, either manual assessments or automated risk scoring running alongside their EHR.
LACE is a popular risk algorithm used by hospitals, which uses a combination of length of stay, acuity, comorbidities and history of emergency department visits to rank a patient’s readmission risk on a scale of 1 to 19. Patients with high readmission risk scores are then flagged for more intensive therapies and interventions.
However, just using a static risk prediction model to stratify patient populations at the time of admission is not enough. Hospitals with high populations of at-risk patients must leverage data analytics at every step along the care continuum, including:
• Identifying high-risk patients.
• Matching patients to interventions.
• Engaging patients through evidence-based programs.
• Evaluating clinical and economic outcomes.
Identifying high-risk patients
Hospitals have the opportunity to significantly improve on basic risk prediction models like LACE by integrating a more robust set of real-time data markers that are updated throughout a patient’s care journey. For example, LACE does not utilize data on social factors, medications, labs or unstructured data such as admitting complaint and clinical notes.
In addition to understanding what data is available, it is also essential to understand when data is available. For example, it’s not uncommon for a final diagnosis to arrive five to seven days after discharge. Prediction models usually have to rely on “proxy data” such as admitting complaint, medication lists, lab values and natural language processing of free form text to allow for early identification of patients with high-risk conditions.
Unless hospitals are part of a fully integrated health system, they will also need to collaborate with upstream and downstream care partners to fill in data gaps across the care continuum. Each hospital will vary in coding conventions and care practice patterns. Prediction models must be adaptive to these differences in order to fully leverage the most up-to-date information at each implementation site.
Once a prediction algorithm is deployed, hospitals should have a regular process to evaluate model performance. Risk prediction models will need to be periodically adjusted to reflect changes in underlying coding systems and care practices, and to capitalize on new data markers as they become available. Risk models should also be leveraging machine learning to steadily improve prediction accuracy as more outcome data becomes available.
Matching patients to interventions
Once high-risk patients have been flagged, data analytics should also be leveraged to match patients to the most appropriate interventions using individual patient risk characteristics and the inherent constraints associated with each intervention program. Patients with the highest risk scores may not always be the best candidates. For example, patients with 10 or more medications are typically less responsive to phone-based medication adherence programs and may need home visits instead.
Creating a data feedback loop for each program that analyzes which patients respond and which don’t enables a data-driven approach to refine program eligibility criteria and improve intervention methods.
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.