What To Know
- ICSRs are good at indicating there may be an issue, but they require safety scientists or risk physicians to process sometimes thousands of cases and bring in outside sources of known medical knowledge on their own in order to land on a determination.
- When PV teams uncover a disproportionate number of AEs for a product, they analyze underlining cases and other evidence to confirm or reject a causal relationship between the AEs and the suspect product.
Signal detection — a critical pharmacovigilance (PV) activity — actively uncovers patient safety risks in vaccines and medical drugs. After a pharmaceutical company releases a treatment, signal detection typically involves monitoring individual case safety reports (ICSRs) and literature from several sources.
ICSRs capture data that supports reporting adverse events (AEs), product problems, and consumer complaints associated with regulated products.
When PV teams uncover a disproportionate number of AEs for a product, they analyze underlining cases and other evidence to confirm or reject a causal relationship between the AEs and the suspect product. This process involves many manual steps and relies heavily on basic signal detection software to complete.
ICSRs are good at indicating there may be an issue, but they require safety scientists or risk physicians to process sometimes thousands of cases and bring in outside sources of known medical knowledge on their own in order to land on a determination. Additionally, ICSRs don’t always provide enough detailed information for safety scientists or risk physicians to reach a definitive conclusion about patient reactions to specific treatments. Lastly, safety scientists only gain visibility after health professionals or patients report an adverse event — and not all adverse events are reported.
Life science organizations must incorporate operational efficiency advancements like advanced cognitive computing into workflows to manage rising case volumes, increased signal noise, and unnecessary manual tasks.
Benefits of advanced cognitive computing
Advanced cognitive computing accelerates the analysis of case series, a group of case reports involving patients given similar treatment, by finding data trends that would otherwise be undiscoverable. Clustering and knowledge graphs help decrease errors for PV signal teams and create insights for target prioritization in drug discovery and clinical settings.
This year, more drug sponsors and contract research organizations (CROs) will use these technologies to create more efficient PV signal teams. By adopting advanced cognitive computing, organizations unlock exciting new opportunities to increase their strategic contributions and drive growth. The technology delivers insights quickly and efficiently to assist PV signal teams in identifying risk, avoiding non-compliance, and maximizing risk physician output.
Ditching the status quo
The status quo for signal detection leans too much on reported AEs, which can produce noisy data that leads to false conclusions or a false sense of accuracy. Risk physicians review hundreds of drug-event pairs, and sometimes, fewer than 5% lead to action. That means 95% can be categorized as noisy data leading PV teams on an ineffectual pursuit.
One solution? PV signal teams can employ a disproportionate method at thresholds for products with well-established safety profiles. However, setting these parameters only improves productivity so much. Teams must leverage real-world data (RWD) along with ICSR data to ensure patient safety. Sources of RWD include:
RWD adds another layer of data that can support faster risk detection and reduced signal noise. Additionally, organizations can more quickly uncover correlations between drugs and benefits.
Adoption of RWD
Regulators understand the value of RWD sources and lead the way in innovative signal detection approaches using RWD. The FDA, for example, created the Sentinel Initiative to answer questions on approved medical products, including drugs, vaccines, and medical devices. The national electronic system creates computer programs that analyze electronic healthcare data and study relationships and patterns in medical billing information and EHRs.
The life sciences industry as a whole has been slower to adopt RWD. In fact, only 32% of life sciences organizations connect with RWD to drive drug development. Midsize to enterprise organizations are more likely to use RWD because their internal processes are more mature. Smaller biopharma often do not yet leverage RWD due to lower overall case volumes, fewer products in the market, and leaner operations.
As safety case volumes continue to rise, innovation must intervene. PV signal teams must leverage advanced cognitive computing and RWD to streamline the safety signal process, balance their growing workloads, maintain regulatory compliance, and stay ahead in their industry.
Editor’s Note: With over 15 years of experience across data analytics, Elizabeth has a passion for exploring the intersection of data science and human reasoning, with experience bringing AI-powered software to market to drive safety and clinical outcomes for patients and clinicians. In her current role, she leads the teams managing our Data Platform, LifeSphere Clarity and LifeSphere Signals, Risk Management product lines.
