Comprehensive Data Analytics For Reducing Hospital Readmissions | Neil Smiley | RxEconsult
Menus

All Health Articles

Reducing Readmissions Among Medicare Patients With Comprehensive Data Analytics Category: Healthcare Administration by - September 25, 2017 | Views: 3763 | Likes: 0 | Comment: 0  

Data analytics and hospital readmissions

In recent years, readmission rates at hospitals across the country have come down. Still, roughly one in five Medicare patients are readmitted within 30 days. Providers are eager to lower them even more. Not only are low rates considered a measure of effective and responsible care, they are key indicators used in today’s value-based care. Fortunately, hospitals can significantly lower their readmission rates through the use of comprehensive data analytics that takes into account multiple risk factors.

Readmission rates are regularly tracked by the Centers for Medicare and Medicaid (CMS),, which for several years has been publicly reporting 30-day readmissions for conditions including acute myocardial infarction, heart failure, pneumonia and hip and knee replacements. Publicly reporting these increases the transparency of hospital care, provides useful information for consumers choosing care, and assists hospitals in their quality improvement efforts, according to the CMS.

For years, most hospitals have been assessing readmission risk through some form of risk stratification – either manual assessments or automated risk scoring running in conjunction with electronic health records. LACE is a popular risk algorithm used by hospitals that combines 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. Typically, patients with high scores are flagged for more intensive therapies and interventions.

However, risk prediction models that stratify patient populations at the time of admission often fail to include data from encounters prior to admission as well as additional clinical markers that emerge during a patient’s hospital stay. Risk assessment models should leverage data from across care settings to identify high-risk patients and match them to interventions. Data analytics also serve a vital role in measuring the fidelity of patient engagement through evidence-based programs and evaluating clinical and economic outcomes to enable continuous improvements.

Poor medication adherence following hospitalization costs the U.S. healthcare system roughly $100 billion annually and is the most significant cause of readmissions. There are numerous medication-specific data markers that can signal risks, including gaps in medication fill patterns prior to admission, a number of concurrent medications, social determinates, and flagging of medications that are difficult for patients to manage, such as certain blood thinners. 

By combining medication adherence risk factors with other clinical encounter data, healthcare organizations can use predictive analytics to strategically prioritize delivery of medications for patients that have a high readmission risk. With a data-driven approach, an organization with limited staffing can concentrate their resources on the 30% of the inpatient population that represents more than 60% hospital’s total readmission risk. The typical all-cause readmission rate for a hospital across all inpatient stays may be around 9%, whereas the top 30% of patients at highest risk for medication adherence failure can have readmission rates of more than 20% if they are not getting their medications prior to discharge. A data-driven medication delivery program can also pay for itself because the incremental labor cost of pharmacy techs needed to round at bedside to deliver medications to the top 30% of high-risk patients is often offset by incremental pharmacy gross margins.

By combining data analytics with automated workflow solutions, organizations also can enable more efficient post-discharge pharmacist calls to patients vulnerable to medication adherence problems. And data-driven systematic surveillance that identifies gaps between prescribed medications and refill patterns can help inform proactive engagement with patients who have abandoned chronic medications that could lead to re-hospitalization.

Reducing readmissions will continue to be an important strategy for health systems as healthcare shifts to value-based care. A comprehensive data-driven medication management program to address points of medication adherence failure can provide a cost-effective and tangible strategy for health systems to reduce readmissions.

About the Author

Neil Smiley is the Founder and CEO of Loopback Analytics. Loopback Analytics' comprehensive platform manages at-risk patient populations outside of the clinical environment to monitor and document health care interventions. 


For More Healthcare Insights Join Us On Twitter
and Facebook. Join The Community To Publish Articles.

Copyright 2018 RxEconsult. All Rights Reserved | Privacy Policy | Terms of Use | Sitemap