How to leverage real-world data for better patient care
Real-world data (RWD) creates exciting new opportunities to improve patient safety. This data helps to bridge the gap between research and healthcare practice, allowing life sciences companies and care providers to understand how patients use and respond to drugs in real-world situations.
Nearly half of the organisations responsible for developing leading pharmaceuticals don't currently use RWD to drive drug research and development. They are missing valuable opportunities to help patients and drive better value.
When utilised correctly, real-world data can inform treatment plans, prevent adverse events, and uncover new opportunities for enhanced care.
How patients benefit from real-world data
RWD encompasses a vast and diverse range of sources, including electronic health records (EHRs), claims and billing data, patient registries, patient-reported outcomes, wearables, and specific patient data related to health status. This information provides a more comprehensive view of people’s real-world experiences and outcomes.
Key benefits of leveraging RWD include:
- Faster risk and safety signal detection
The wide range of available information empowers pharmacovigilance (PV) teams to better understand treatment patterns, disease incidence, and prevalence in a large, diverse patient pool. With RWD, safety professionals have more data points to enhance signal identification and trend monitoring. Frequently updated datasets allow for more timely analyses.
Additionally, PV teams can employ cognitive computing (the use of computerised models to simulate the human thought process in complex situations) to cut through the noise in RWD and analyse data faster and more accurately to identify trends quickly. This analysis might uncover patterns within patient populations, negative (or positive) drug interactions, or other behaviours impacting drug efficacy. The resulting insights enable a proactive safety response. Instead of simply responding to issues, RWD empowers PV teams to actively help prevent adverse events.
- Unknown benefit identification
Many medications have uses beyond those tested in a clinical trial. For example, SSRI antidepressants treat generalised anxiety disorder, PTSD, and other conditions, in addition to depression.
Diverse, robust post-market RWD datasets combined with spontaneous reporting signals can provide additional insights into unanticipated outcomes, including positive events associated with a drug or treatment. AI methods such as data mining, clustering, and knowledge graphs show patterns or relationships indicating a correlation, prompting further analyses to uncover meaningful insights.
Additionally, RWD data enables long-term disease and outcome tracking, so life sciences companies can better understand disease courses, drug impacts, patient needs, and treatment opportunities.
- More personalised medicine
Not every drug is suitable for every individual. Outcomes vary based on lifestyle, genetic factors, health history, background, treatment adherence, and countless other variables. Patients frequently receive prescriptions proven effective in clinical trials or known to work for the general population - but the medication may not fit the particular person’s circumstances. For example, while anti-inflammatories help many people, they’re potentially dangerous for someone taking blood thinners or suffering from liver cirrhosis.
Personalised medicine accounts for individual variabilities, so providers can deliver tailored care, resulting in better patient outcomes. The wider variety of datasets made available by leveraging RWD enables better assessment of biological factors and social determinants of health when making healthcare decisions.
PV teams can use curated fit-for-purpose data linked with anonymous patient-level data for additional context to identify a cohort, intervention, or outcome of interest. Cognitive computing helps build patient profiles and isolate risk factors, which inform medication prescribing and identify alternative treatment options. For instance, researchers analysed RWD to determine that anticholinergic drugs are associated with cognitive decline in elderly patients. This type of information leads to optimal medication use.
Analytics unlock the value of real-world data
Access to RWD won’t benefit patients without the right tools to extract meaning from that data. The growth in RWD sources and variety increases data management and signal detection complexity. Manual management processes take significant time and cognitive effort from safety professionals, slowing incident responses and detracting from high-value strategic tasks.
Technological advancements like AI-powered pharmacovigilance software allow teams to automate data collection, management, and analysis. Automation gathers and extracts safety case attributes from structured and unstructured fields stored in many disparate sources, increasing efficiency and accuracy in the data intake process.
Cognitive computing combs through the hundreds of thousands of terabytes of data to reveal deeper insights in less time than manual review alone, so safety teams can apply their medical reasoning to the findings quickly. These in-depth, hypothesis-free signal data analyses enable more robust benefit-risk and treatment safety profiles.
To best leverage RWD, companies should look for an end-to-end safety platform that supports:
- Seamless integration and data federation: Platforms should create a unified database that will work seamlessly with current and future ecosystems.
- Cross-platform analytics: The solution must be capable of analysing information and connecting out-of-the-box with an array of different data sources.
- Intelligent automation: Platforms should use explainable, proven algorithms that cut through the noise and identify trends in large data sets.
- Self-service reporting and dashboarding: Stakeholders must be able to gain quick and easy access to data.
PV and drug development sit on the precipice of a revolution with RWD poised to change patient care for the better. While increased data sources and caseloads present signal monitoring challenges, those resources create opportunities to drive positive change. Organisations must embrace this data and invest in processes and tools to optimise RWD’s value to patient care. The assets are available - it’s time to leverage them.