SAS Innovate 2024: Observations Relevant to the Pharmaceutical Industry
SAS Innovate 2024 featured content addressing pharmaceutical industry applications, from real-world evidence generation to manufacturing optimisation and analytics platform strategy. This document consolidates observations from sessions directly relevant to pharmaceutical research, development, regulatory affairs and operations, illustrating how advanced analytics platforms are being applied to industry-specific challenges whilst maintaining the governance and validation requirements essential for regulated environments.
Real-World Evidence: Transparency as Competitive Advantage
Shionogi’s AI SAS for RWE System
Shionogi presented their internal system “AI SAS for RWE”, designed to transform the transparency challenge in Real-World Evidence generation into competitive advantage. The system addresses the core problem with RWE studies: their historical lack of standardisation and transparency compared to randomised clinical trials, leading regulators and peers to question validity.
The solution employs a two-pronged approach:
Standardisation: The system transforms disparate Real-World Data from various vendors into a Shionogi defined common data model based on OMOP principles, ensuring consistency where direct conversion of Japanese RWD proves challenging.
Semi-Automation with Radical Transparency: The system semi-automates the entire analysis workflow, from defining research concepts to generating final tables, figures and reports. The innovative aspect involves automatically recording every research process step—from the initial concept suite through specification documents, final analysis programmes and resulting reports—directly into Git. This creates complete, immutable and auditable history of exactly how evidence was generated.
This approach represents more than technical solution; it constitutes strategic positioning. By building transparent, reproducible and efficient systems for generating RWE, Shionogi directly addresses regulatory concerns whilst accelerating the evidence generation process. The transformation of regulatory burden into competitive edge built on integrity marks the discipline’s transition from experimental art to industrial-grade science.
For pharmaceutical companies operating under increasing pressure to demonstrate the validity of real-world evidence to regulatory authorities, this model offers a template for building systems that satisfy both operational efficiency requirements and regulatory scrutiny expectations. The complete audit trail from concept to conclusion addresses fundamental concerns about RWE reproducibility whilst the standardisation layer ensures consistency across diverse data sources.
Manufacturing and Process Optimisation
Digital Twins for Pharmaceutical Manufacturing
Pharmaceutical use cases described digital twin applications in manufacturing contexts. Teams used historical data from penicillin manufacturing batches to train machine learning models, creating digital twins of physical bioreactors. Rather than conducting costly and time-consuming physical experiments, researchers executed thousands of in silico simulated experiments, adjusting parameters in the model to discover the “Golden Batch”—the optimal recipe for maximising yield.
This approach demonstrates analytics platforms evolving beyond data analysis tools into foundational infrastructure enabling intelligent automation. The ability to simulate and optimise manufacturing processes virtually before physical implementation offers pharmaceutical manufacturers several advantages:
- Cost Reduction: Virtual experiments eliminate the expense of physical trial batches, including raw materials, equipment time and analytical testing
- Accelerated Development: Thousands of scenarios can be evaluated in silico in the time required for a single physical batch
- Risk Mitigation: Potential process improvements can be validated virtually before risking actual production batches
- Quality Assurance: Optimal parameter ranges can be identified more precisely than through physical experimentation alone
- Regulatory Support: Complete digital records of process development provide comprehensive documentation for regulatory submissions
For an industry where batch failures represent significant financial losses and where process validation requires extensive documentation, digital twin technology offers a pathway to more efficient development whilst maintaining or enhancing quality standards. The approach proves particularly valuable for biologic manufacturing, where batch-to-batch variability represents a persistent challenge and where physical experimentation involves substantial cost and time investment.
Platform Strategy and Migration Considerations
Strategic Migration: Balancing Capability and Flexibility
A presentation from DNB Bank detailed their migration from SAS 9.4 to SAS Viya on Microsoft Azure, offering insights applicable to pharmaceutical organisations considering similar transitions. The strategic approach proved counter-intuitive: whilst SAS Viya supports both SAS and Python code seamlessly, DNB deliberately chose to rewrite their legacy SAS code library into Python.
The rationale combined two business objectives: expanding the addressable talent market by tapping into the global Python developer pool, and creating a viable exit strategy from their primary analytics vendor to satisfy regulatory requirements for demonstrating realistic vendor transition options.
For pharmaceutical companies, this strategic thinking offers several considerations:
Talent Acquisition: The global pool of Python developers significantly exceeds that of SAS programmers. As pharmaceutical companies compete for data science talent with technology companies and other industries, Python proficiency broadens the recruitment pipeline.
Regulatory Risk Management: Financial regulators require DNB to demonstrate realistic vendor transition capabilities. Pharmaceutical companies face analogous pressures from quality assurance and business continuity perspectives—ensuring that critical analytics capabilities do not create single points of failure.
Technology Flexibility: By maintaining code in open-source languages, organisations preserve options for future platform decisions without facing complete rewrites of analytical libraries.
Platform Value Proposition: The decision illustrates that competitive advantage no longer derives from creating vendor lock-in but from providing powerful, stable and governed environments that fully embrace open-source tools. For pharmaceutical companies evaluating platforms, this suggests prioritising those that deliver value through capability rather than constraint.
However, pharmaceutical organisations must balance these considerations against validation requirements. Rewriting validated clinical programming code from SAS to Python requires revalidation, potentially representing significant effort and cost. The decision requires careful assessment of long-term strategic benefits against near-term validation investments.
Analytics Platform Unification
Resolving the Code Versus No-Code Debate
A healthcare analytics presentation addressed the persistent debate between low-code/no-code interfaces for business users and professional coding environments for data scientists. Two analysts tackled identical problems—predicting diabetes risk factors using a public CDC dataset—using different approaches within the same platform.
The low-code user employed SAS Viya’s Model Studio, a visual interface. This analyst assessed the model for statistical bias against variables such as age and gender by selecting a configuration option, whereupon the platform automatically generated fairness statistics and visualisations.
The professional coder used SAS Viya Workbench, a code-first environment similar to Visual Studio Code. This analyst manually wrote code to perform identical bias assessments. However, direct code access enabled fine-tuning of variable interactions (such as age and cholesterol), ultimately producing a logistic regression model with marginally superior performance compared to the low-code approach.
For pharmaceutical organisations, this unified platform approach offers practical advantages:
Clinical Operations Teams: Medical monitors and clinical data managers can use low-code interfaces to build baseline safety models or generate standard reports without programming expertise, accelerating routine analyses.
Biostatisticians and Programmers: Professional coders can develop sophisticated models, implement complex statistical methods and optimise performance through direct code control, ensuring analytical rigour for regulatory submissions.
Collaboration: Both personas work within the same platform, sharing models, data and governance frameworks rather than operating in isolated tool ecosystems. An analyst in clinical operations can build an initial model that a biostatistician then refines, all within a single validated environment.
Validation Efficiency: A unified platform simplifies validation by requiring qualification of one system rather than multiple disconnected tools, reducing validation effort whilst maintaining compliance.
The demonstration illustrated that the debate presents a false dichotomy. The actual value resides in unified platforms enabling both personas to achieve exceptional productivity whilst maintaining the governance and validation requirements essential for pharmaceutical applications.
Healthcare Applications and Operational Analytics
Life-or-Death Operational Analytics
Heather Hallett, a former ICU nurse and healthcare industry consultant at SAS, presented on improving hospital efficiency, demonstrating analytics applications with direct relevance to pharmaceutical operations and patient care optimisation.
She described the challenge of staffing intensive care units, where having appropriate nurse numbers with correct skills proves critical. Staffing decisions constitute “life and death decisions”. Her team uses forecasting models (such as ARIMA) to predict patient demand and optimisation algorithms (including mixed-integer programming) to create optimal nurse schedules. The optimisation addresses more than headcount; it matches nurses’ specific skills—such as certifications for complex assistive devices like intra-aortic balloon pumps—to forecasted needs of the sickest patients.
For pharmaceutical companies, this approach offers insights applicable to several contexts:
Clinical Trial Site Optimisation: Matching site capabilities and staff expertise to protocol requirements, ensuring sites can handle complex procedures and specialised assessments required by study designs.
Manufacturing Resource Planning: Optimising technical staff deployment across manufacturing facilities, ensuring personnel with specific certifications and expertise are available for critical production steps.
Medical Affairs Deployment: Planning medical science liaison territories and schedules to optimise coverage of high-priority healthcare providers and institutions.
Patient Support Programme Staffing: Forecasting demand for patient support services and optimising nurse educator deployment to meet patient needs whilst controlling costs.
A second use case applied identical operational rigour to community care, using the classic “travelling salesman solver” from optimisation theory to plan efficient daily routes for mobile care vans serving maximum numbers of patients in their homes. This approach translates directly to pharmaceutical field force optimisation, including sales representative routing, home nursing services for speciality pharmaceuticals and mobile clinical trial units.
These applications ground abstract concepts of forecasting and optimisation in deeply tangible human contexts, demonstrating that sophisticated mathematics can serve life preservation and patient care enhancement beyond purely commercial objectives.
User Experience and Productivity
Interface Design as Strategic Differentiator
An examination of the upcoming complete rewrite of SAS Studio illustrated how user experience has evolved beyond aesthetic considerations into a strategic product pillar directly tied to productivity and talent acquisition.
The motivation for the substantial undertaking proved straightforward: the old architecture was slow and becoming a drag on user productivity. The primary goal for the new version involved making a web-based application “feel like a desktop application” regarding speed and responsiveness. Improvements focused on productivity enhancements:
A Modern Editor: Integrating the Monaco editor used in Visual Studio Code, providing familiar and powerful coding experiences that reduce the learning curve for programmers accustomed to modern development environments.
Smarter Assistance: Improving code completion and syntax help to reduce errors and time spent consulting documentation, particularly valuable for complex statistical procedures and regulatory requirements.
Better Navigation: Adding features such as code “mini-maps” enabling programmers to navigate thousands of lines of code instantly, essential for large clinical programming libraries.
For pharmaceutical companies competing for programming and biostatistics talent, providing best-in-class development environments represents key strategy for attracting and retaining exceptional people. The industry competes not only with other pharmaceutical companies but with technology firms offering modern development tools and environments. Analysts and programmers who experience friction and frustration with outdated interfaces may seek opportunities elsewhere.
Moreover, productivity improvements translate directly to business value. Faster code development, easier debugging and reduced time spent fighting tools rather than solving problems accelerates clinical trial timelines, expedites regulatory submissions and reduces the cost of clinical programming operations.
Conclusion
SAS Innovate 2024 demonstrated substantial progress in analytics capabilities relevant to pharmaceutical industry needs. From Shionogi’s transparent approach to real-world evidence generation to digital twin applications in manufacturing, the content illustrated practical applications of advanced analytics whilst maintaining regulatory compliance and quality standards.
The emphasis on unified platforms supporting both citizen analysts and professional programmers, combined with focus on user experience and productivity, addresses pharmaceutical industry requirements for both operational efficiency and analytical rigour. The strategic discussions about platform migration and vendor relationships acknowledge the reality that pharmaceutical companies must balance innovation with risk management, validation requirements and long-term strategic flexibility.
As pharmaceutical companies navigate increasing complexity in clinical development, growing regulatory expectations and mounting pressure to accelerate innovation, the capabilities demonstrated at SAS Innovate 2024 offer practical approaches grounded in real-world implementations rather than theoretical possibilities. The maturation of analytics from experimental tools to production-grade infrastructure supporting life-saving work marks a significant evolution in the discipline’s role within pharmaceutical operations.
See more Trends & Insights