Real-World Data: A Comprehensive Guide

Real-World Data: A Comprehensive Guide

With technology at the forefront of our daily lives, data is being generated on a minute-by-minute basis. From a healthcare standpoint, researchers and other health system stakeholders have the ability to harness the power of real-world data and the real-world evidence derived from it. Real-world data sources have the potential to unlock actionable healthcare insights not typically garnered from traditional randomized controlled trials (RCTs).

So, it is no wonder that real-world data is an emerging area of interest across the healthcare spectrum and is a key focus area for Veradigm. That's why we've compiled this comprehensive guide to real-world data, complete with links to use-cases, relevant blog articles, white papers, and more.

What Is Real-World Data in Healthcare?

Real-world data (RWD) is defined as "the data relating to patient health status and/or the delivery of health care routinely collected from a variety of sources."

The FDA shares that common real-world data sources include, but are not limited to:

• Electronic health records (EHRs);
• Claims and billing activity;
• Product and disease registries;
• Data gathered from other sources such as mobile devices, wearables such a pedometers and smart watches, etc.

Why Is Real-World Data Important?

Real-world data is important because it enables researchers to go beyond data gathered throughout a traditional RCT. Because RCTs gather data from a controlled sample population, their findings can be limited by the characteristics of the cohort examined in the trial. Additionally, RCTs usually require significant investment and time for data to accumulate.

RWD, on the other hand, can be collected from any number of cohorts or population sub-groups. The insights gained from such data can be extraordinarily valuable. Examining the use of a new medication or treatment protocol in special populations in real-world settings where patient’s behavior, cooccurring treatments and environmental factors are not influenced by participation in an RCT can provide powerful insights.

With the passage of the 21st Century Cures Act, regulatory bodies such as the U.S. Food and Drug Administration (FDA) have begun to place greater emphasis on the use of real-world data and evidence to support regulatory decision making.

How Is Real-World Data Collected?

Real-world data are collected in a variety of ways. Whenever we visit the doctor, file a claim with our insurance company, or strap on our smart watch, we are producing real-world data. The collector of these data (e.g., provider, health plan, technology platform) may have rights to use these data for research.

Data can then be cleansed, standardized and deidentified. Often, additional steps in linkage across sources and mapping to common data models are taken to optimize the data’s utility for analytics and research.

Upholding Data Privacy in the Utilization of Real-World Data

Data privacy in healthcare is crucial not only for maintaining patient trust but also for complying with legal and ethical standards.

Unless consent is obtained and recorded, real-world data is de-identified data. In the United States and in accordance with the Health Insurance Portability and Accountability Act (HIPAA) Privacy Rule, patient health data must be de-identified before it can be analyzed or used for research.

De-identification is a key strategy in protecting patient privacy. This process involves removing or obscuring personal identifiers, such as names, addresses, and social security numbers, from datasets, thereby minimizing the risk of patient re-identification.

There are two primary methods for de-identification:

1. Safe Harbor Method: This approach involves the removal of all 18 types of identifiers defined under the HIPAA Privacy Rule that could directly or indirectly be linked to an individual.

2. Expert Determination Method: This method relies on statistical analysis to ensure the risk of re-identification is very low, considering the available information and the methods used to link datasets.

The Role of AI and NLP in Enhancing Real-World Data Utilization

Artificial Intelligence (AI) and Natural Language Processing (NLP) are revolutionizing the way real-world data (RWD) is utilized in the healthcare sector. These technologies are instrumental in extracting valuable insights from vast amounts of unstructured data generated through various healthcare interactions.

AI in Real-World Data

AI helps in the analysis of RWD by providing advanced data processing capabilities that can predict outcomes, personalize treatment plans, and improve the overall quality of care.

By employing machine learning algorithms, AI can identify patterns and trends that would be impossible for human analysts to detect in a reasonable timeframe. This capability is crucial for developing predictive models that can forecast disease progression, patient responses to treatments, and the likelihood of rehospitalization.

NLP in Real-World Data

NLP transforms the way unstructured data, such as doctor’s notes, discharge summaries, and patient feedback, is utilized. It allows for the extraction of relevant information from text-based sources, turning it into structured data that can be analyzed more effectively.

NLP is particularly important in understanding patient outcomes and experiences, which are often recorded in free-text form. By analyzing this data, healthcare providers can gain insights into treatment effectiveness, side effects, and patient satisfaction.

The integration of AI and NLP in processing RWD is more important than ever due to the increasing volume and complexity of data being collected. These technologies not only enhance the efficiency of data analysis but also improve the accuracy of the insights gained, leading to more informed decision-making in clinical and operational contexts.

Real-World Data for Life Science Research

Real-world data can be a powerful tool for life science researchers. Used alone or in conjunction with data gathered from RCTs, RWD can help researchers gain insights into how therapies are performing in the real-world. Moreover, incorporating RWD into clinical research can help provide evidence for expanding the approved indications for the use of a medication into new types of patients, for new conditions, or for patients whose needs are not currently being met.⁴

Many life science organizations, including biopharma companies and contract research organizations (CROs), are beginning to fully embrace RWD. In fact, a survey of life-science organizations found that over 90% of respondents currently use RWD in clinical development and decision-making.

For life-science research organizations to keep up with the competition, routinely incorporating RWD into their projects is becoming a must.

Real-World Data for Payers

Health plans and payers also realize the value that real-world data can bring to the table. Many payer groups understand how the evidence generated from RWD can promote informed safety monitoring, utilization management, and cost/value analysis. While it varies from organization to organization, some see benefit in utilizing RWD and RWE to inform pharmacy and therapeutic (P&T) committee decisions.

RWD can also help payers determine the coverage of specific procedures, make contracting decisions with providers, assess the health of their populations, and track and report quality of care among other myriad benefits.

When evaluating value-based care outcomes, including the use of medicines, payers are increasingly turning to real-world approaches. In some cases, payers have begun to tie payment for treatment to both short and long-term effectiveness of medicines and other treatments. These effectiveness measures are only possible because of access to, and analysis of, high-quality RWD.

Real-World Data for Physicians

Physicians are an integral part of the generation of real-world data. Much of the RWD available for study is made possible because a healthcare provider entered patient data into an electronic health record (EHR).

Because of its myriad benefits to the healthcare system, there is broad clinical support for the collection and use of RWD to generate RWE. In fact, the American Medical Association (AMA) has adopted a policy to support the generation and use of RWD and RWE to:

• Evaluate effectiveness and safety of medical products, while assuring patient privacy and confidentiality;
• Improve regulatory decision-making;
• Decrease costs;
• Increase research efficiency;
• Advance innovative and new models of drug development, and;
• Improve clinical care and patient outcomes.

The findings generated by the real-world data statistical analysis can help inform a care team's understanding of a patient’s condition and help guide data-driven treatment decisions.

How Is Real-World Data Used In Real-World Evidence?

It is difficult to discuss RWD without also discussing real-world evidence (RWE). RWD are the countless data points that, once analyzed, become RWE. In today’s digital world, the ubiquity of RWD collection has created a wealth of data points from which researchers can build RWE.

If you are interested in learning more about real-world evidence in healthcare, check out our comprehensive guide for a more in-depth look.

What Is the Difference Between Real-world Evidence and Real-World Data?

While "real-world data" (RWD) and "real-world evidence" (RWE) are occasionally used interchangeably, they are two distinct – yet related – concepts.

RWE and RWD: Better Together

In the diagram below, you can see how RWD and RWE are related, and how they can be used in the healthcare system.

While the basic relationship between RWD and RWE is somewhat straightforward, the collection, analysis, and application of each within the healthcare system is quite complex. It requires a great deal of expertise and innovative technology to fully harness the power of RWD and RWE. To see how Veradigm utilizes real-world data and real-world evidence to gain valuable healthcare insights, check out some use-cases linked below.

Real-World Data and Veradigm

Veradigm works with organizations to achieve real-world insight from the point of care throughout the entire patient journey. With the collection, preparation, and analysis of our expansive datasets, our innovative solutions allow clients to discover timely, actionable real-world evidence to improve the patient experience and health outcomes.

Access to our extensive commercially available ambulatory EHR dataset helps our clients leverage de-identified data through innovative analytic technology for outcomes research. In addition, Veradigm is able to add claims data linked by patient to the ambulatory EHR data.

With Veradigm, you can execute actionable retrospective analyses and prospective programs, all with the support of a dedicated research team and custom data visualizations and dashboards so that you can better understand the patient journey from data directly captured at the point of care.