Seven Ways Digital Health Companies can Leverage Real-World Data (RWD)
Thanks to my sponsor Veradigm, for helping make this article possible.
It’s no secret that the healthcare industry produces an enormous amount of data. In fact, about 30% of the world’s data volume is being generated in our sector. And with near ubiquity of the electronic health record (EHR), this data is more organized and accessible than ever before.
This healthcare data, captured in the routine course of healthcare delivery and even at home, holds immense potential. It's a trove of real-world data (RWD) that, when harnessed and analyzed, can transform into real-world evidence (RWE) – a powerful tool to enhance health outcomes and optimize healthcare costs.
In this article, I’ll share more about RWD and how companies can leverage RWE to grow their business. We’ll cover:
Real-world data (RWD) vs. real world evidence (RWE)
Real-world data (RWD) is the industry term referring to the information that is regularly gathered about patients' health and the care they receive. This data comes from various places, including:
EHRs
Claims and billing activity
Product and disease registries
Wearables and other digital health technologies
Health-related data from social media
Patient-powered research networks (PPRNs)
A single data point might offer insight into an individual's health, but aggregating data from millions of patients can provide incredible insights for advancing public health.
The true value of RWD lies in its potential to be transformed into actionable insights that can significantly impact patient care and healthcare policies. Data can reveal trends, uncover inefficiencies, and provide evidence for more effective treatments.
RWD are the countless data points that, once analyzed, become RWE. RWE is the meaningful information that can help drive better health outcomes, more personalized medicine, and more efficient healthcare systems.
Real-world data (RWD) vs. randomized controlled trials (RCTs)
RCTs and RWD each play a distinct and complementary role in advancing research.
While RCTs have long been considered the gold standard in clinical research for their methodological rigor, the increasing availability of RWD in recent years means RCTs are no longer the only—and often not the best—answer to research needs.
By randomly assigning participants to either the treatment group or the control group, RCTs effectively isolate the effects of an intervention, minimizing bias and confounding factors. This controlled environment improves the likelihood of evidence quality and reliability, particularly useful for establishing causality and initial efficacy of new treatments.
RCTs, however, do face certain limitations. They can be time-intensive and costly, and their strict participant criteria in controlled environments may not fully capture the diverse real-world patient population.
RWD can help RCTs be more effective by providing deeper, richer data which would open access to more patients and contemplate more variables. That is because RWD, especially from an EHR, may contain more data from diverse demographic groups compared to data collected in controlled settings. This consideration is referred to as Diversity, Equity, Algorithmic fairness, and Transparency (DEAT), and is an important ethical issue to consider in any research project.
RWD and RCTs are not mutually exclusive; instead, they are synergistic. The integration of RWD and RCTs is increasingly recognized as vital for a more comprehensive understanding of medical interventions, leading to more informed healthcare decisions and policies that reflect the complexities of real-world healthcare delivery.
How to generate RWE
Let’s go over the ways to gain insights from data, including:
Retrospective analysis (learn from the past):
Retrospective analysis involves examining existing data to understand trends and patterns, patient outcomes, and treatment effectiveness.
Why? By understanding what has happened in the past, startups can make informed decisions about product development, market positioning, and business strategies.
Prospective studies (gather new data):
Prospective studies involve collecting data moving forward from a specific start point. This approach allows startups to gather data under specific conditions or in response to certain interventions.
Why? You can use these studies to test hypotheses in real-world settings, such as the effectiveness of a new medical device or digital health tool, and adapt their strategies based on the findings. Prospective studies can be used for:
Safety studies
Custom clinical registries
Clinical trial support
Clinical measure enhancement
Real-time analytics (immediate insights):
Real-time analytics involves analyzing data as it becomes available. For startups, this means using technologies like machine learning and AI to analyze data from wearables, EHRs, or other digital platforms as it's being generated.
Why? This approach is helpful for startups needing immediate insights to make quick decisions, such as adjusting a health app's functionality based on user engagement or responding to emerging health trends.
Predictive analytics (forecast future trends):
Predictive analytics uses historical data to predict future events or trends. For startups, this could mean analyzing patterns in patient data to forecast medication needs or healthcare resource utilization.
Why? You can use these predictions to strategically plan product launches, personalize healthcare interventions, or identify potential market demands before they arise.
Seven ways companies can leverage RWE
Most digital health companies today, including startups, deal with health data in some way. And while that data is usually created by its users, companies can also leverage RWE from the EHR to expand their business.
Here are some key areas where startups and other companies can utilize RWE:
1. Identifying unmet needs for product development and strategy
RWE can help organizations identify gaps in healthcare, enabling the development of products or services that address unmet medical needs. By analyzing real-world data, startups can build products more aligned with the actual needs and behaviors of patients.
2. Clinical trials and research
RWE can be used to help design more effective and efficient clinical trials, identify suitable trial participants, and enhance patient recruitment strategies. RWE can also be invaluable for monitoring the safety and efficacy of products post-launch, which is crucial for maintaining regulatory compliance and product improvement.
3. Personalized medicine
RWE enables the analysis of large datasets to understand how different patient groups respond to treatments or interventions, paving the way for more personalized medicine. This can help a startup differentiate its offering and improve patient outcomes.
4. Commercial strategy
RWE can be used to demonstrate the effectiveness and cost-efficiency of a product to payers and employers, facilitating reimbursement and broader market access.
5. Pricing data
By understanding claims data, organizations can set more competitive and realistic pricing for their products.
6. Regulatory compliance and approval
RWE can complement clinical trial data in regulatory submissions, potentially speeding up the approval process for new drugs or medical devices.
7. Better care delivery
Healthcare delivery startups can develop platforms or tools that use RWE to assist healthcare providers in making more informed decisions, thus improving the quality of care.
Buyer beware: all real world data are not created equally
RWD can present its own set of challenges. If not gathered from a reliable source, it can be heterogenous, fragmented, and difficult to work with. Plus, many RWD sources are considered “secondary” sources because the data were initially collected for purposes other than research. As a result, they may include gaps and biases reflecting their original function.
These factors make it critical to understand RWD sources’ characteristics and limitations to determine their utility for addressing specific research questions.
The FDA defines data’s “fitness for use” in terms of relevance and reliability.
Relevance means that key data elements are available in sufficient numbers and contain sufficient detail to capture the outcome of interest.
Reliability focuses on several key aspects of data:
Accuracy: Is the data correct?
Completeness: Is data missing?
Provenance: How were the data generated, transmitted, and stored?
Traceability: How was data collected (e.g., how were data elements defined and what was the time window when they were collected)?
Reliability information is generally available for RWD sources such as registries and those directly collecting data as part of a study but may be lacking for secondary RWD sources. There is no single method for assessing data fitness because suitability greatly depends on the context in which the data will be used.
The good news is that the rise in RWD coincides with increasingly sophisticated artificial intelligence (AI) and machine learning (ML) tools. AI/ML excels in handling large, complex, and diverse datasets, including unstructured and multi-modal data. Deep learning, for instance, is adept at deriving abstract representations from complex and unstructured datasets. Techniques like natural language processing (NLP) can efficiently process textual data, such as clinical notes in EHRs, transforming them into real-valued vectors for further analysis.
Summing it up
Healthcare data, predominantly RWD, is a treasure trove of insights waiting to be unlocked. Constituting a significant portion of the world's data volume, RWD offers a unique lens into patient health and healthcare delivery, sourced from diverse points like EHRs, claims data, registries, and wearable technologies.
The transformation of this extensive data into RWE stands as a testament to the power of data in improving healthcare. RWE not only complements the rigors of randomized controlled trials (RCTs) but also bridges crucial gaps, providing a more comprehensive understanding of medical interventions in real-life scenarios.
For startups in the healthcare sector, this represents an incredible opportunity. Leveraging RWE, startups can identify unmet medical needs, optimize clinical trials, make healthcare more personalized, strategize market entry, and ensure regulatory compliance, thereby driving innovation and enhancing patient care.
I’m optimistic that the convergence of a rapidly growing data landscape and AI heralds a new and exciting era in healthcare. We now have both extensive data and the sophisticated tools necessary to decode this wealth of information, laying the foundation for a healthcare future where informed, data-driven decisions significantly improve patient care and outcomes.
Plug for my sponsor: If you are looking for a reliable source of RWD, Veradigm provides companies of all sizes with data that is well managed and easy to work with. Learn more at their website.