PINC AI™ Data: Three Must-Know Capabilities

Key takeaways:

• Actionable real-world data (RWD) can help life sciences organizations conduct clinical, financial and outcomes-based analyses on drugs, devices, treatments and disease states.
• Combined with natural language processing (NLP) technology, PINC AI^™ solutions provide longitudinal patient data that can inform evidence-based clinical practice.
• NLP can read more than two million records per hour, identify trends and understand clinicians’ free-text notes to help deploy evidence-based guidance at the point of care.

Standardized and connected real-world data (RWD) is needed to generate real-world evidence (RWE) that can support innovation and development, regulatory submissions and show proof of improved patient outcomes.

Obtaining the broad inclusive data that’s needed can be challenging — that is, unless life sciences organizations have the right partner. In 2022, this data challenge led more than 80 percent of life sciences companies to state their intent to partner with data and data science companies to ensure RWD informed their decision-making. PINC AI™ is leading the way.

PINC AI™ data helps fuel research and coalesces insights from more than 1,188 sites to provide data for evidence- and population-based analyses.

Life sciences organizations can utilize PINC AI^™ data to generate real-world insights to optimize research studies and clinical trials, discover new treatments, provide proof of therapy efficacy and accelerate drug development with the goal to improve outcomes and the future of healthcare. Below are three capabilities of PINC AI^™ data to remember.

1. Tech-Enabled RWD for Early Disease Identification and Intervention

Life sciences organizations and clinicians are continuously looking for ways to use data to address the gap between disease diagnosis and treatment. This requires much earlier identification of specific disease states by looking for subtle signs that are often found in the unstructured narrative or clinician notes in patient charts.

PINC AI^™ data combined with natural language processing (NLP) technology is well suited for uncovering these details helping to identify which risk factors and clinical signs and symptoms are most predictive of subsequent disease development.

For instance:

• The PINC AI™ Applied Sciences team (PAS) utilized artificial intelligence (AI), NLP and a data ontology designed to mine the unstructured narrative of clinicians’ notes and pathology reports for statements like “Mom seems a bit agitated” or “Mom is confused” to identify patients for early Alzheimer’s Disease (AD) intervention.
• In oncology, PAS partnered with AstraZeneca and Clinithink and utilized Clinithink’s CLiX NLP technology to identify patients with incidental pulmonary nodules (IPNs) to flag for intervention before potential lung cancer progression – with roughly 152,000 patients “caught” early.
• PAS worked with GE Healthcare and St. Luke’s University Health Network to introduce a patient-centric care model for breast cancer diagnosis – with a goal of helping patients go from appointment to diagnosis and connection to a treatment plan in just 48 hours or less.
• To pinpoint maternal and infant health risks and those resulting from pregnancy to prevent negative health impacts, researchers need to look no further than the PINC AI™ Maternal Health Database, which links inpatient data of mothers to their infants and can illuminate the entire pregnancy journey from prenatal to post-partum and beyond.

2. RWD/RWE to Enhance Clinical Trials

Drugs, devices and therapies can take around 10 years to create and cost upwards of $1 billion to bring to market. Adding to the high cost is the fact that more than 80 percent of clinical trials in the U.S. fail to meet their patient recruitment timelines and lack diverse population representation.

RWD from the PINC AI^™ Healthcare Database (PHD) and tech-enabled solutions such as AI, machine learning (ML) and NLP can help clinicians overcome these challenges; enhance clinical trial design, feasibility and execution; and improve life cycle management.

In the past, traditional clinical trial sites were selected solely based on experience and relationships with Principal Investigators (PI) and/or at the site level. Data and innovative solutions including NLP are changing that by estimating eligible patient population volumes with a new level of granularity and efficiency previously unattainable when screening sites to match trial protocols. These technologies are allowing clinical trial developers to assess the suitability of sites on a larger scale based on appropriate patient populations, investigator availability, experience in therapeutic area and historical performance metrics. Based on this assessment, sites that have the best chance to outperform enrollment expectations can be selected.

Tech-Enabled RWD allows clinical trial staff to rapidly, accurately, and at scale screen for potential patients instead of needing to manually identify patients who met complex inclusion/exclusion (I/E) criteria.

With Tech-Enabled RWD/RWE, clinical research timelines can be compressed, and solutions have the potential to be delivered at reduced costs. Tech-Enabled RWD/RWE can also increase diversity in clinical trials by helping identify barriers to enrollment and informing strategies to reach underrepresented populations.

3. RWD/RWE to Support Regulatory Submissions

The regulatory landscape continues to evolve, and life sciences organizations must align their research and medical solution development with the latest guidance. The 21st Century Cures Act has caused more regulatory agencies to recognize the promise of RWD/RWE. When combined with clinical trial research, it can help shorten the regulatory approval process of U.S. Food and Drug Administration (FDA) and European Union Medical Device Regulation approvals. This act also allows RWD to be included in label updates and expansions, reducing the need for additional clinical trials.

Investing in RWD is crucial as payers, regulatory bodies and health systems increasingly demand proof that a medical solution delivers value by doing what it is intended to do.

The right RWD/RWE from real-world outcomes extracted from the PHD can not only prove efficacy, but can also help support regulatory submissions, demonstrate medical device safety and earn waivers from payers for prior authorization or other forms of utilization management, thereby likely expanding the market of eligible patients and payers that will cover the cost.

PINC AI™ data is the perfect solution for all your RWD/RWE needs.

• More than 20 years’ worth of data from 45 percent of U.S. hospital discharges, 812 million hospital outpatient and clinic encounters and 131 million office visits.
• Data tokenization that allows linkage with very specialized data sources.
• Data spans the continuum of care, medication/device SKU-level utilization and different types of coverage from cash and commercial payer to Medicare and Medicaid.

For more on this topic:

• Learn more about PINC AI™ Applied Sciences (PAS) and how your organization can use PINC AI™ Data.
• Discover ways to leverage real-world data to save money, time and support solution development.
• Learn how the PINC AI™ Innovation and Research Collaborative can inform your clinical trial strategy.

The insights you need to stay ahead in healthcare: Subscribe to Premier’s Power Rankings newsletter and get our experts’ original content delivered to your inbox once a month.