Clinical research is in the midst of a data explosion, and that’s a good thing. Technological advances are enabling access to secure and de-identified data sources for researchers, and the optimization of this data holds enormous potential for conducting clinical trials more efficiently, both from a cost and timeline perspective.

The incorporation of real-world data (RWD), data gathered from actual patient experiences, in many ways represents an important step toward a fundamentally better understanding of states of disease and health. Biomarkers, electronic health records (EHR), genomic data, imaging data, labs, social media, wearable sensors, and more provide enormous new sources of RWD that can aid in new discoveries for the quality, efficacy, and safety of new drug therapies. 

For instance, when treating a patient, clinicians will have the opportunity to assess treatment course changes and outcomes among other similar-looking patients across the broader healthcare system. In addition, pharmaceutical companies can use RWD to establish follow-on research planning, develop value dossiers, and determine patient treatment options.

But how can we sort through RWD to find data points that provide additional support for what is known about a drug’s effect on a disease? Better still, how can all this data be optimized to demonstrate breakthrough insights and new patterns in relation to the drug and the disease?

Closing the gaps

Critical to analyzing any dataset is to identify and understand where the data come from and where the gaps in the data might be. For example, data from health networks may offer different findings than data from insurance companies, because the population represented in each data source differs. Differences will also be reflected in the type of data reported by each source—a hospital may gather information related to the patient’s health such as temperature, blood pressure, or medication dosage whereas an insurance company will have confirmation of the tests performed and medication dispensed. Understanding these differences will help researchers to extrapolate unique findings and make better data-derived decisions.

Collection of data from real-world experiences and clinical settings often results in the creation of several disparate, siloed datasets, and accessing and analyzing these large datasets can be unwieldy and resource intensive. Sponsor expectations, advances in data management technology, and improved analytics have added market pressure for researchers to work with CRO partners who can help them to maximize the value derived from RWD.

To meet these challenges, many are turning to technology platforms that enable data interoperability. That is platforms that collect, amalgamate, and consolidate data into a singular form or centralized repository so that it can be interpreted in a holistic view. Thanks to new cloud-based platforms patients, doctors, and trial administrators can talk and share data, essentially in real-time.

These platforms can gather and transmit RWD from a patient participating in a research study from the comfort of their own home. For example, patients can wear a connected mHealth sensor with a unique identifier that remotely and continuously collects their real-world patient data, such as blood pressure and blood glucose levels, then sends the information via Bluetooth, to the patient’s mobile device.

From there, the data is routed through a cloud repository that aggregates, summarizes, and disseminates the targeted data into an electronic data capture (EDC) system to ready it for analysis, often through machine learning or AI. The data analytics are then combined with other patient data collected for the clinical trial and continue onto downstream processes such as medical review, biostats efficacy, and safety analysis, etc.

The RWD analytics output can also influence changes in clinical trial design—such as how medical affairs’ experts may identify the “long responders” to specific treatment approaches, and how commercial organizations evaluate the effectiveness of patient services programs. Ultimately, this data can become real-world evidence submitted for regulatory approval of a new drug or therapy.

Keeping it “real”

Ultimately, clinicians and patients must be able to relate the results of clinical trials to their own professional and personal experiences. Data gathered from the highly controlled environment of a clinical study may not actually depict the “real world” that many patients and care providers will experience. The result is important limitations in our understanding of the effectiveness and safety of various medical treatments.

That’s why leveraging RWD from a wider population is so important. With a more diverse, inclusive data set, clinical researchers can deepen their understanding of how diseases and treatments behave within different patient populations and adjust patient care accordingly.

For example, today only 5% of cancer patients take part in clinical trials, a number so low that some trials are forced to stop early if too many participants withdraw. RWD makes it possible to use EHRs to automatically identify patients who qualify for trials and get this information to their physicians. This means that one day patients will be able to simply select participating in a clinical trial as a care option during a routine doctor visit. And remote data collection coupled with telemedicine means that patients don’t need to come to the clinic as often, or sometimes not at all. This can eliminate or greatly reduce what patients often identify as the most inconvenient part of clinical trials—travel.

There is no doubt that studies including a fuller and more diverse range of individuals and clinical circumstances could ultimately lead to better scientific evidence for application to decisions about use of medical products and healthcare decisions. All of the implications highlighted are potentially game- changing on their own. But as an industry, we must work together to ensure they are implemented and that providers and sponsors are able to use both clinical and RWD to make the best decisions when it comes to the care of their patients.