Written by: Rachana Kolluru, Product Manager, Solutions Management, Veradigm
Real-world data (RWD) includes health data from patients during their engagement with the healthcare system, including data collected from healthy patients as well as from patients experiencing a disease or condition. RWD includes information from electronic health records (EHRs), disease and product registries, administrative claims, and digital health technologies. Each of these sources of information can have a role in reframing and advancing innovation.
This article discusses how real-world health data drives innovation in three areas that are crucial to life science organizations: personalized medicine, chronic disease management, and drug development and repurposing.
Personalized medicine (or precision medicine) is a burgeoning treatment model that depends on large-scale deployment and analysis of data to tailor medical decisions, practices, interventions, and products to meet the specific needs of groups and individual patients.
Genomic sequencing is one example of personalized medicine. Physicians can combine insights from a patient’s DNA sequence with clinical and lifestyle RWD to tailor medical treatment. Another way RWD is used in personalized medicine is clinical data integration. This integration combines RWD from EHRs, patient registries, clinical trial data and previous treatments, outcomes, and comorbidities. All this information allows healthcare providers to tailor treatment to each individual patient’s needs by showing what is most effective.
Making sense of the large datasets produced by RWD can be difficult. Machine learning and AI can be used to get actionable insights from these large datasets. These actionable insights can be turned into predictive analytics. Predictive analytics, in turn, can help forecast disease progression, treatment outcomes, and potential adverse events. For example, a physician using predictive analytics may recommend one intervention over another based on the analysis of treatment adherence, patient demographics, genetic information, and environmental factors.
Real-time monitoring tools can provide a continuous flow of patient health data that may help demonstrate treatment efficacy and monitor early disease onset and progression. Wearables and sensors provide convenient methods for continuously tracking important health metrics and could result in the early detection of complications and personalized treatment adjustments. Home-based diagnostic tools like blood pressure cuffs or pulse oximeters may provide data streams that result in reducing the number of hospital visits and watching for signs of disease progression. With real-time monitoring, healthcare providers can quickly adjust interventions.
The U.S. Centers for Disease Control defines chronic disease as conditions that last one year or more and require ongoing medical attention or limit activities of daily living or both. Managing chronic disease is a major challenge for health systems around the world, which have been developed to deal with acute, episodic care. Managing chronic disease can be difficult for physicians due to the long-term nature of the disease, the introduction of multiple comorbidities requiring coordinated treatment, and the evolving nature of the disease.
Real-world data can provide insight when managing chronic disease. Anonymized and aggregated data can inform predictive models that help identify patients at higher risk of disease progression and complications. Physicians using predictive models can then anticipate when interventions are necessary and assign extra monitoring as needed.
Using RWD to identify larger patterns and trends allows physicians to tailor treatment plans based on the patient’s age, lifestyle, comorbidities, and previous responses to treatment—all available in the EHR and other sources of RWD. Using RWD, physicians can also monitor medication adherence, providing insight into where more help or support might be needed.
Treatment effectiveness, in particular, can be aided by RWD. For researchers studying chronic disease management, RWD can be valuable in comparing the efficacy of different treatment approaches:
Determining which treatments are effective, for which sets of people, and in which contexts is an ongoing question for those managing chronic disease. Comparative effectiveness studies may well be the next logical step in assessing real-world effectiveness. By using service charge data captured in EHRs or matched claims data, costs can be integrated with performance measures. These performance measures can demonstrate average patient use and compliance, allowing beneficiaries and payers to afford high-quality care. Given that more extensive collections of EHR data are becoming available, more cost-effective comparisons can be made. Veradigm EHR and Veradigm Cardiology and Metabolic Registries are two comprehensive sources that can be used for ongoing comparative effectiveness studies.
Real-world data helps innovate drug development and repurposing by providing useful information about how medications perform outside randomized clinical trials. RWD can also contribute valuable information for the regulation of drug safety.
RWD can provide information for researchers to better understand patient populations, which may lead to more targeted and efficient recruitment for clinical trials. The selection of more diverse applicants from a variety of demographics and healthcare settings can improve the validity of the trial and provide more generalizable results.
RWD may also innovate drug development by helping bring new drugs to market sooner. Clinical trials that modify study protocols as RWD becomes available may speed the study toward conclusions. For instance, if RWD reveals that a certain group of patients responds more favorably, the trial can adjust to that information.
Drug repurposing is finding new uses for existing drugs. RWD can help uncover real-world treatment patterns and outcomes and show off-label uses that may not have been part of the initial clinical trial. For instance, drugs for treating diabetes mellitus have been used for cosmetic weight loss, and drugs for malaria and parasites have been used to treat COVID-19.1
Veradigm has one of the largest research-ready EHR databases, with more than 154 million patient records available from multiple EHR systems. Veradigm has direct access to raw structured and unstructured data through multiple EHR systems. Veradigm proprietary NLP models are used to extract rich clinical insights from semi-structured and unstructured EHR data enabling researchers to better understand therapeutic decisions, disease progression and patient outcomes across diverse populations. Contact Veradigm for more information about using RWD for your research.
References: