Big data is changing the trial game
As big data analysis capabilities have increased over the last five years, so have the possibilities for radically improving efficiency and success rates in clinical trials. Digital transformation at the level of general healthcare, including the prevalence of digitized records, the proliferation of data-capturing wearables market and other sources of patient-related information mean that researchers now have access to a range of invaluable data collected during patients’ normal course of care outside of the clinical trial setting.
This Real World Data (RWD) presents a wealth of information about drug and treatment efficacy, and it’s changing the way clinical trials are designed and executed. Here’s why.
What is Real World Data?
The term Real World Data refers to health-related data generated during the course of a patient’s routine care or post-treatment life that relates to their health status. This data comes from sources outside of the clinical trial itself, such as healthcare records, insurance claims and billing activity, medication order records, or from the patient’s own data generation via wearables or other at-home medical devices.
From Real World Data, researchers can synthesize Real World Evidence (RWE), which is the clinical evidence generated by the analysis of RWD that reflects the safety, efficiency, benefits and risks associated with the drug under testing.
What are the sources of Real World Data?
Real World Data can be sourced from any reliable point of origin outside of the clinical trial itself, many of which appear fairly unconventional. RWD sources include:
- Clinical sources, including EHR records, pathology/histology data, discharge and progress reports.
- Medication sources, including order records, Point of Sale data, concomitant therapies and prescription refills.
- Claims, including medical and prescription drug claims, and other treatment usage data.
- Family history, including historical data on health conditions relating to the patient’s extended history, smoking in the household and alcohol use.
- Mobile health, including data gathered by fitness trackers and wearables delivering clinical-grade information on heart rate, PulseOx levels, sleep, calories and more.
- Social media, including patient support groups, blogs and posts.
- Environmental sources, including data on air quality, climate factors, community infections, and OHSA data.
Real World Data applications
Real World Data is being applied in the drug discovery process in a number of important ways.
Guiding pipeline and portfolio strategy
Pharmaceutical companies can use RWD to guide strategic decision-making, including estimating disease prevalence and incidence and predicting the scope of the potential patient population. Increasingly, researchers are bringing RWD into earlier phases of the product development process to help guide the allocation of resources and maximize the potential for success.
Optimizing study design
Researchers can use RWD to optimize study design through advanced feasibility determinations, improved cohort recruitment and predictive enrichment, and lowering trial costs through the development of “synthetic” control arms built from pre-gathered RWD. Researchers are also using RWD to make more informed decisions regarding required enrollment sizes, trial site selection and trial patient diversity.
Post-launch safety and efficacy surveillance
RWD is emerging as an invaluable data source for post-launch drug safety and efficacy assessments. To assess the safety and efficacy of a drug, researchers need visibility of drug performance and potential associated risks across a longer period of time and against a broader scope of variables than possible during the limited time period of a trial.
How advanced data management is unlocking major value in the drug discovery pipeline
Clinical trials are producing more data than ever before, especially with the increasing use of RWD. The sheer volume of data being generated every day from clinical trials, M&A activity, press releases and publications has become impossible for human researchers to monitor and analyze effectively.
Increasingly, pharmaceutical R&D teams are turning to AI-enabled data monitoring and insights management platforms to help them keep on top of the impenetrable data volume flooding their areas of research. Similari is one such platform.
By monitoring millions of data points in a defined arena of inquiry, Similari is able to collate key insights which help inform data-driven decisions, identify true white spaces and avoid research duplication and dead ends.
Find out how Similari can augment your R&D capabilities by trying a free demo today.