Data, Digital and Real World Evidence

Leveraging patient-level data to generate evidence and insights

The UK spearheads safe access to patient level data through our own direct access to NHS data and facilitated access to Secure Data Environments (SDEs), offering the world’s largest, linked, longitudinal patient-level data set. Leveraging our data analytics capabilities and partnerships with SDEs, CF helps life science companies use this data across the innovation lifecycle, facilitating R&D, prelaunch insights into disease burden and pathway dynamics, and post launch to support uptake of innovation including market research and Real World Evidence (RWE) studies. Through market research and RWE studies, generating patient-level insights and developing data strategies, we help llfe science companies de-risk investment in the UK market through understanding patient needs and pathways to diagnosis and treatment.

Our approach

CF’s unique combination of consultancy, award winning data science and data engineering capabilities, and strong track record in research positions us to support you with meaningful evidence generation and data strategies. We are an established provider of non-interventional studies, with a track record of producing excellent results.

We hold direct access to record-level data on 57 million patients in England and further 10 million patients in the devolved nations (Scotland, Wales, Northern Ireland). We also have curated all other publicly available data to the lowest level of granularity possible including demographic, social determinants, public health, economic data as well as healthcare data including prescribing and all settings of care (including primary care, community, mental health, social care). We are able to access prescribing data at a granular level of GP practice and hospital – not just the “brick” level – creating insights to prescribing patterns. Using this in-house patient level data we can assess the burden of disease and health inequalities and quantify the impact of novel innovations and implementation of change management programmes.

Partnering with SDEs allows us to utilise linked, patient-level datasets for specific therapeutic areas and pathways, demographics and geographies, including linking patient-level prescribing data with primary and secondary care healthcare activity and diagnostic coding of patients and encounters. For legitimate purposes and with the appropriate protocol This data can be be reidentified to target interventions, identify research subjects and population health management programmes in compliance with research ethics and information governance regulations including statue (GDPR) and policy (such as the ‘Five Safes’ principles).

Our offer

We recognise that any research is unique to you, which is why our offer is both bespoke and robust covering the breadth of different purposes:

1. Real World Evidence

Healthcare utilisation is critical for successful market access, innovation uptake and positive clinical outcomes. Stakeholders increasingly demand real world evidence (RWE) during innovation development to refine go-to-market product launch strategies. CF leads in accessing patient-level, integrated dataset access for RWE. Our partnerships with SDEs provide unparalleled access to real-world data, guiding innovation positioning and evaluation and healthcare utilisation for pathway and therapy specific challenges. We understand how to navigate pharmaceutical companies code of compliance and safety requirements as well as research ethics, information governance, and patient consent. Our multidisciplinary team of data scientists, data engineers and healthcare consultants use a suite of advanced analytics to generate tailor-made, evidence-based and actionable insights for your RWE research questions, including addressing health outcomes, health inequalities and uptake of novel products.

2. Health Economics

We understand the complexities of successful market entry, access and adoption strategies, including navigating Health Technology Appraisal (HTA) and payor requirement, across multiple pathways and therapeutic areas. Leveraging our access to patient-level linked datasets, we tailor analyses for HTA submissions (including QALY analyses) ensuring alignment with guidelines for evidence strategy, evidence generation and managed entry. We support mapping of detailed costed pathways, providing economic insights into treatment options, key cost drivers and healthcare resource utilisation. We work with you to develop robust payor value cases, demonstrating the economic impact of interventions for better patient outcomes and cost-effectiveness – insights which can overcome payor-specific challenges and ensure optimal access and accelerate uptake. Our work for life sciences companies is underpinned by having undertaken hundreds of projects on health economics for payors and health systems where we are seen as a trusted partner in their own development of health economics research, costed pathways and business cases.

3. Creating value through Data, Digital and AI Strategy

Rapid advancements in artificial intelligence (AI), digital technologies and data sharing have increased our reliance on data and digital products. We bring unique first-hand experience of having used this data to improve patient pathways and outcomes for pharmaceutical companies as well as for health systems, payors and providers. This experience makes us expert in understanding the value that can be created from these advances as well as understanding the frontier of what is technically possible and reliably deliverable. Crafting a resilient data, digital, and AI strategy for life sciences requires navigating challenges in data management, ensuring robust information governance and cybersecurity measures to protect sensitive information, and embracing evolving regulatory landscapes. We can help you navigate the critical balance between innovation and data security and compliance for pharma in implementing innovation strategies in health systems. We can help you develop you understanding of the landscape, strategy for concrete opportunities you pursue as well as provide both technical expertise to deliver on these plans as well as the relationships and understanding of processes needed to put these plans into practice.

4. Patient-Level Insights

We provide patient-level insights through our access and use of millions of electronic medical record data. By contrast to traditional practices of interviews, panels and audits, whose data collection and insight generation practices are manual, time-consuming, and subject to error, our enhanced data methodology creates rich insights scalable across large areas. In concordance with respective guidelines, we support pharma to assess and examine novel innovation impact on prescribing and uptake pathways, patient compliance and healthcare inequalities towards better health outcomes for all.

5. Case Finding and Reidentification; Research and Uptake

We help clients demonstrate value through case finding to support trials, evidence generation and uptake. Slow patient recruitment, regulatory compliance and clinical trial coordination can have a significant impact on clinical trials. The identification of eligible patients for new diagnostics and therapies is often a major source of delay. The use of patient-level data to identify relevant patients based on demographics, diagnostic codes, healthcare activity and biometric data holds the promise of a complete breakthrough in how patients are identified for research and for uptake. Our access to extensive patient characteristics, healthcare activity, prescriptions outcomes and health economic data, expertise and contacts across health systems and market access insights positions us as a market leader for case finding and reidentification. We develop strategies to use smart-recruiting of research subjects and identify eligible patients for specific therapies. Where pharma wishes to optimise market penetration and innovation adoption, we can smart-targeting cohorts, leveraging RWE, stakeholder engagement, uptake projections, and performance tracking. This can also include facilitating collaborative working to resource and act on these insights to recruit and enrol patients in new diagnostics and therapy.

6. Artificial Intelligence

We combine our data science capabilities with our access to patient-level data to generate bespoke health analytics tools for the life sciences Industry. Using sophisticated machine learning algorithms, we uncover nuanced patters and perform risk stratification to help pharma pinpoint high-risk patients across specific disease areas, optimise strategies to increase uptake by redesigning prescribing pathways and target interventions at all geographic levels. We synthesise large datasets comprised of free text data using generative AI and large language models (LLMs); both for our localised and external assets including medical literature, presentations, white papers and guidelines to enhance delivery effectiveness. The combination of these methods can enable rapid and cost-effective generation of insights that guide changes in behaviour and improvement in outcomes.

7. Evaluation of impact using synthetic control arms and other methods

The life sciences industry partners extensively with health systems and is obliged to publish the details of collaboration and the impact it has had. Health systems themselves experiment with innovations in pathways to seek to improve outcomes. All too often this is a painful process which happens after the event and creates no meaningful insight. (“We think some of this has had some impact – but we just can’t say how much, where or how”) There is no reason this should be the case. CF has developed approaches to evaluate impact using synthetic control arms to allow any intervention captured in national data to be evaluated to see impact relative to what has happened in directly comparable patient populations in other places. We can do that with patient level data for hospital activity and population level data for wider parameters including prescribing. We also are expert in applying data science modelling including multivariate regression, fixed effects modelling, propensity score modelling to tease insights out of the data. And we are able to apply realist evaluation methods with multi-modal research to help create actionable insights.