Healthcare data are the "driving force" of clinical informatics, according to the American Medical Informatics Association (AMIA). With EHR systems serving as central repositories for healthcare data across the care continuum, these platforms have immense value to the field of health informatics.
In this article, EHRIntelligence outlines three use cases for EHR data in the growing field of clinical informatics.
Clinical Informatics Basics
Clinical informatics, also known as health informatics, is "the science of how to use data, information, and knowledge to improve human health and the delivery of healthcare services," as defined by AMIA.
Often confused with data science, data analytics, and health information management, clinical informatics is a field of study that pulls these subdomains into one discipline to advance healthcare delivery.
Informaticists (also known as informaticians) help healthcare providers, public health researchers, epidemiologists, healthcare networks, and health insurance providers discover ways to leverage healthcare data to improve care delivery.
Since the passage of the HITECH Act in 2009, EHR adoption has grown exponentially across the healthcare industry. As of 2021, nearly 78 percent of office-based physicians and 96 percent of all non-federal acute care hospitals had adopted an EHR.
EHRs include key data relevant to patient care, including demographics, progress notes, problems, medications, vital signs, past medical history, immunizations, laboratory data, and radiology reports, according to CMS.
Widespread EHR adoption has helped healthcare providers more easily access patient data for clinical decision support. Additionally, health information exchange (HIE) networks that connect EHR data from across the care continuum are helping improve care coordination.
The surge in EHR usage has come with a surge in electronic healthcare data, allowing for increased opportunities to improve healthcare through research using these data.
Informaticists can leverage EHR data for a variety of use cases, including population health research, data analytics, and clinical trial recruitment.
Using EHR Data for Population Health Research
Traditional clinical research methods like surveys require manual data collection, which is burdensome and limits the data to a select group of people. Additionally, the use of claims data for clinical research can prevent challenges, as it is not always accurate due to lag time from the date a provider submits a claim to the date a healthcare payer fulfills the claim.
On the other hand, EHR data can serve as a real-time source of information for researchers without the need to conduct surveys, speeding up investigation.
For example, a recent study leveraged EHR data to examine the association between neighborhood food environment and the risk of incident type 2 diabetes across different community types.
Previous studies revealed a link between food insecurity and hypoglycemic events in patients with diabetes. However, these findings were limited to the direct screening of food insecurity among a select number of patients across a handful of urban environments, limiting generalizability.
Researchers linked individual-level EHR data and neighborhood-level attributes with the food environment, including the proportion of total food-serving establishments that were fast-food establishments and the ratio of the total retail food outlets that were grocery stores.
Data used for the study came from the US Veterans Administration Diabetes Risk (VADR) cohort, a cohort of veterans without type 2 diabetes constructed by the New York University Grossman School of Medicine and George Mason University through the VA national EHR.
Ultimately, the study found that the neighborhood food environment was associated with increased type 2 diabetes risk for Veterans in multiple community types.
Using EHRs for Health Data Analytics
Learning healthcare systems systematically integrate internal data with external evidence to drive improvements in care delivery.
While EHR systems can facilitate this goal for individual institutions, aggregating data from multiple institutions can provide even greater clinical value through increased sample size.
Several major EHR vendors offer customers access to de-identified EHR data for clinical research purposes. For example, Oracle Real-World Data (RWD) is a de-identified big data source that allows clinicians and researchers to query and interact with longitudinal data for clinical research.
Additionally, EHR vendor Epic's de-identified patient database, Cosmos, is a HIPAA-limited data set combining the EHR data of over 220 million patients. Individuals from healthcare systems that contribute data to Cosmos can query data in Cosmos through a secure web application.
A 2021 study presented practical examples of how Cosmos could further efforts in chronic disease surveillance, syndromic surveillance, immunization adherence, adverse event reporting, and health services research.
"A low barrier of entry for Cosmos allows for the rapid accumulation of multi-institutional and mostly de-duplicated EHR data to power research and quality improvement queries characteristic of learning healthcare systems," the researchers noted.
For instance, the researchers leveraged Cosmos to investigate asthma surveillance by patient sex.
"Cosmos enables combining elements of administrative data, vital signs, and demographics to study EHR asthma prevalence, and the likelihood of a clinically noted exacerbation along strata of sex and body mass index (BMI)," the study authors wrote. "The ability to query vital sign data such as BMI makes the latter assessment more reliable than relying on diagnosis data alone."
In their analysis, the prevalence of asthma was significantly greater in morbidly obese women than in morbidly obese men. Additionally, Cosmos data revealed that morbidly obese asthmatic women were more likely to experience clinically significant exacerbations compared to morbidly obese asthmatic men.
Using EHR Data for Clinical Trial Recruitment
Recruitment is one of the biggest challenges to successful clinical trials, with 86 percent of trials falling behind planned recruitment schedules and 40 percent failing to meet recruitment goals.
Researchers use various recruitment strategies for clinical trial enrollment, including mailings, social media, newspaper, and radio advertisements.
With the widespread use of the EHR, researchers can identify and directly contact specific groups of individuals within a healthcare system based on study inclusion and exclusion criteria. Then, Notifications about clinical trials through secure patient portals can inform potentially eligible patients about opportunities to participate in research.
Through targeted EHR outreach, researchers can recruit populations that have historically been underrepresented in research, such as children, older adults, and racial or ethnic minorities. Additionally, electronic search methods within the EHR are less time-consuming and expensive than manual chart review and may reduce screening-related workload by up to 90 percent.
As digital health transformation progresses and the amount of electronic healthcare data grows across the country, the EHR will continue to serve as a valuable tool for clinical informatics.