Contributor: 3 Ways to Better Leverage Data for Health Equity

Achieving health equity will depend on the quality of huge volumes of health care data and how effectively we can make them accessible and actionable for key stakeholders.

The COVID-19 pandemic put a spotlight on the health disparities across the United States and is fueling overdue discussion on how they can be systematically addressed to achieve the bigger goal of delivering the best care everywhere. Much of this discussion is focused around how to best leverage the valuable troves of health care data generated every day across the ecosystem.

Because health care data are inconsistently collected and utilized, it can be difficult to identify inequalities and understand the causes. Further, much as 80% of health care data are unstructured, making it virtually impossible to glean patient and population insights that can be acted upon.

Ultimately, the country’s ability to achieve health equity will come down to how significantly we can improve the quality of huge volumes of health care data and how effectively we can make them accessible and actionable for key stakeholders.

Ensure Accurate Clinical Documentation

Making better use of data starts with accurate collection, particularly in the clinical setting where it is often the richest. Data collection begins with observation but also requires meaningful measurement and proper recording to make it useful. Clinicians are historically adept at observation and medical decision-making but have struggled with the recording aspect.

Access to standard and enhanced content sets that make it easy for clinicians to search and capture diagnoses, procedures, medical devices, laboratory tests, medications, and social determinants of health at the point of care can make capturing key aspects of a patient’s health a much easier task.

Extract Valuable Data From Unstructured Text

Not all relevant information gathered during the clinical encounter will fit neatly into an electronic medical record field, so oftentimes the rich patient insights are documented in free text fields. Social determinants of health such as food insecurity or lack of reliable transportation to medical appointments are examples of what frequently show up in clinician notes.

This unstructured text provides the critically important context needed to ensure patients can be successful in managing their disease and adhering to their treatment plan. Fortunately, natural language processing technology has emerged and can more easily surface this information so it can be codified into widely recognized terminology and then incorporated into the medical decision-making process or used for population health initiatives.

Normalize Data From Disparate Sources

The ability to normalize clinical data to standard terminologies is the key to ensuring common understanding. As payers and providers increasingly collaborate in value-based arrangements to better serve patients, they not only need to share information to provide a more holistic view of a patient’s needs, but they also, and perhaps more importantly, need the ability to accurately interpret and act on it.

For example, many payers are taking health equity head on through value-based care payment models that target better outcomes for specific needs like maternal and fetal health in underserved populations. To help facilitate optimal outcomes, payers need to access to important results such as glucose challenge testing, fundal height measurements, and fetal movement, which are often found in semi-structured data fields and not codified to standard terminology.

To move the needle on outcomes and lower costs, payers must normalize these observations to a common standard for use in analytics, reporting, and care management programs.


By putting the unique needs of individual patients at the center of data collection and exchange practices and applying those insights at a population level, the health care industry will be able to make important progress in ensuring the system works for everyone.

Karen Kobelski is the vice president and general manager of Clinical Surveillance, Compliance & Data Solutions at Wolters Kluwer. She brings more than 25 years of experience to her position, which expands her previous leadership role over the Safety & Surveillance group to also include the Health Language portfolio of data normalization solutions.