Blog > Data Quality > Data Quality in Healthcare: 3 Real-Life Stories

Data Quality in Healthcare: 3 Real-Life Stories

Authors Photo Rachel Levy Sarfin | May 27, 2020

Data quality is crucial, though there are few industries in which it’s a life-or-death issue. The healthcare field is a notable one – a missing value, an additional value, or the wrong value could all lead to serious injury or even a fatality. 

Healthcare organizations must take steps to improve data quality to better protect patients. Read on to learn about three real-life stories of how healthcare organizations increased data quality to boost patient outcomes. 

Ending patient misidentification: The PDDQ framework

According to the US government, patient misidentification is the third-leading cause of preventable death in this country. The problem lies in the fact that as many as 10% of incoming patients are misidentified at hospitals, and the average hospital has a range of eight to 12% of duplicate records. When patient data is shared from disparate sources, the likelihood increases that duplicate records will be generated. 

The Department of Health and Human Services’ Office of the National Coordinator of Health Information Technology decided to craft a solution to this problem. Its Patient Demographic Data Quality (PDDQ) framework is a set of 76 questions that help healthcare organizations evaluate their data quality standards and methodology and improve them. Organizations can see results in as little as three weeks; pilots at Kaiser Permanente yielded lower incidents of duplicates after a month.

Implementing data governance policies for better decisions: OhioHealth

Like many healthcare organizations, OhioHealth, a non-profit charitable healthcare outreach, collected data for decades. It stored information in disparate silos, making it virtually impossible to analyze. As a result, decision-makers had a difficult time coming to conclusions about what was best for the organization. 

OhioHealth recognized that a data warehouse would allow it to improve its data quality by bringing information into one place and weeding out duplication and inaccuracies. Part of that process involved establishing data governance principles. While it was a challenge for OhioHealth to put those principles into practice, it improved the data quality in healthcare and allowed for a smooth implementation of the data warehouse. 

Data quality in healthcare can help reduce prescription errors

Reducing prescription errors: Big data applications 

The Network for Excellence in Health Innovation states that prescription errors cost $21 billion per year. They affect more than seven million patients in the US, and these mistakes lead to 7,000 deaths annually. What if those errors could be significantly reduced, and perhaps someday eliminated? 

There are companies today working on improving data quality in healthcare through big data analysis. They utilize analytics to review electronic health records (EHRs) and identify outlying prescriptions that could endanger patients’ lives. Although EHRs themselves have helped reduce prescription errors, prescribers can still make mistakes by choosing the wrong medications or assigning medications to the wrong patients. 

Improving data quality in healthcare is a major step to enhancing patient outcomes. Data quality is vital – if the quality is poor, physicians might misidentify a patient or prescribe the wrong treatment.

Download our eBook to learn more about measuring the effectiveness of your data quality improvement efforts.