Synthetic Data Use Cases for Pharma Commercial Teams

1: Introduction to Synthetic Data in Pharma Commercial Teams

1.1 The Digital Transformation of Pharma Commercial Teams

The pharmaceutical industry is undergoing a rapid digital transformation. Commercial teams are no longer limited to traditional sales and marketing approaches—they now leverage data-driven insights to engage physicians, payers, and patients more effectively. According to Statista (https://www.statista.com), over 70% of U.S. pharmaceutical commercial teams plan to increase investment in advanced data analytics and AI by 2025.

In this landscape, the ability to access large, high-quality datasets is crucial. However, privacy regulations such as HIPAA and stringent FDA guidelines often limit the use of real-world patient or prescriber data. This creates a significant challenge for commercial teams aiming to optimize marketing campaigns, forecast sales, or analyze patient journeys.

1.2 What Is Synthetic Data?

Synthetic data is artificially generated information that replicates the statistical properties of real-world datasets. In pharma, this includes:

• Patient data – demographics, treatment patterns, adherence behaviors
• Prescriber data – physician prescribing habits, specialty, region
• Market data – sales trends, formulary access, and competitor activity

Unlike anonymized real-world data, synthetic data contains no actual patient identifiers, making it fully HIPAA-compliant and safe for analytics, AI modeling, and commercial decision-making.

Example: A pharma company can generate synthetic patient populations to simulate therapy adoption across different demographics without ever exposing real patient information.

1.3 Why Synthetic Data Matters for Commercial Teams

Commercial teams use synthetic data to make faster, safer, and more strategic decisions. Key advantages include:

• Data Privacy & Compliance – Eliminates risk of exposing sensitive patient or prescriber data. FDA guidance supports the responsible use of synthetic datasets for commercial research (https://www.fda.gov).
• Accelerated Insights – Teams can test marketing strategies, campaign targeting, and sales forecasts without waiting for real-world data.
• Cost Efficiency – Reduces reliance on expensive data acquisition or third-party vendors.
• Scalability & Flexibility – Large synthetic datasets allow simulation of multiple scenarios, optimizing resource allocation and territory planning.

Data Example Block:

1.4 Market Context: U.S. Pharma Commercial Teams in 2025

The U.S. pharmaceutical market is projected to exceed $700 billion by 2025 (PhRMA: https://phrma.org). Commercial teams are expected to adopt data-driven strategies to remain competitive, including:

• Multi-channel marketing campaigns targeting physicians, payers, and patients
• Advanced sales forecasting using predictive analytics
• AI-assisted market access modeling and pricing simulations

Challenges include:

• Stringent privacy laws limiting access to real-world data
• Fragmented data sources across EMRs, claims databases, and CRM platforms
• Increasing complexity of patient journeys, requiring sophisticated simulation

Synthetic data emerges as a solution to these challenges, enabling commercial teams to model realistic scenarios, test strategies, and make data-driven decisions safely and efficiently.

1.5 Key Takeaways

• Synthetic data is HIPAA-compliant, privacy-safe, and scalable, making it ideal for U.S. pharma commercial teams.
• Adoption is driven by regulatory requirements, the need for speed, and cost efficiency.
• By 2025, synthetic data will play a critical role in marketing, sales, patient engagement, and market access strategies.

Part 2: The Business Case for Synthetic Data in Pharma Commercial Operations

2.1 Introduction: Why Pharma Commercial Teams Need Synthetic Data

Pharma commercial teams face an increasingly complex landscape: evolving regulations, digital marketing demands, and competitive pressures require data-driven decision-making. However, real-world patient and prescriber data comes with privacy challenges, delayed availability, and high acquisition costs.

Synthetic data addresses these challenges by replicating real-world datasets in a privacy-compliant, scalable, and cost-efficient way. According to Health Affairs (https://www.healthaffairs.org), companies leveraging synthetic datasets for commercial analytics report 20–30% faster campaign optimization cycles compared to teams relying solely on traditional datasets.

Key areas where synthetic data delivers business value include:

• Marketing optimization
• Sales forecasting and territory planning
• Patient engagement and adherence analysis
• Market access and pricing strategies

2.2 Challenges of Using Real-World Data

Before exploring the benefits of synthetic data, it’s important to understand the limitations of traditional real-world data:

1. Regulatory Constraints
   • HIPAA and state-level privacy laws restrict access to personally identifiable health information (PHI).
   • FDA guidelines (https://www.fda.gov) require de-identification of datasets, which often limits granularity.
2. High Costs
   • Acquiring patient or prescriber datasets from EMRs, claims databases, or third-party vendors can cost $50,000–$250,000 per dataset depending on size and coverage.
3. Delayed Access
   • Real-world datasets often lag by 6–12 months, limiting the ability to make timely marketing or sales decisions.
4. Fragmented Data Sources
   • Combining EMR, claims, and CRM data for actionable insights requires significant integration and cleansing efforts.

2.3 Benefits of Synthetic Data

2.3.1 Data Privacy & Compliance

Synthetic datasets do not contain any real patient identifiers, eliminating privacy risk. Unlike anonymized datasets, synthetic data does not require de-identification, enabling commercial teams to:

• Model physician prescribing patterns
• Simulate patient journeys
• Test marketing campaigns

Example Table:

2.3.2 Accelerated Insights

Synthetic data enables teams to rapidly test hypotheses, such as:

• How a new marketing campaign would perform in different physician segments
• The impact of pricing changes on adoption across regions
• Predicting patient drop-offs and therapy adherence

According to Statista (https://www.statista.com), companies using synthetic data can reduce campaign testing cycles by 20–30%, enabling faster go-to-market decisions.

2.3.3 Cost Efficiency

By avoiding the need to acquire expensive real-world datasets, synthetic data:

• Reduces reliance on third-party vendors
• Lowers infrastructure costs for data storage and processing
• Enables cost-effective modeling for multiple scenarios

Example: A mid-sized pharma company saved $120,000 annually by replacing three paid patient datasets with synthetic simulations for marketing and sales modeling.

2.3.4 Scalability & Flexibility

Synthetic datasets can be generated at any scale, allowing:

• Modeling of millions of patient or prescriber profiles
• Scenario testing for territory planning and campaign targeting
• Flexibility to adjust datasets based on emerging trends or market shifts

2.4 Quantifiable ROI

Synthetic data adoption provides measurable business impact:

2.5 Use Cases Driving ROI

2.5.1 Marketing Campaign Optimization

• Objective: Test multiple physician and patient segments for messaging effectiveness
• Synthetic Data Application: Generate representative prescriber datasets, simulate engagement, and optimize targeting
• Result: 15–20% increase in campaign engagement (PubMed: https://pubmed.ncbi.nlm.nih.gov)

2.5.2 Sales Forecasting & Territory Planning

• Objective: Allocate sales reps efficiently and forecast revenue by region
• Synthetic Data Application: Simulate prescription patterns, identify underperforming territories
• Result: 10–15% increase in sales productivity (FDA: https://www.fda.gov)

2.5.3 Patient Engagement & Adherence Programs

• Objective: Identify dropout points and optimize support programs
• Synthetic Data Application: Model patient journeys and simulate interventions
• Result: 12% improvement in adherence for chronic therapy pilots (Health Affairs: https://www.healthaffairs.org)

2.6 Early Adopters: Industry Case Studies

Pfizer

• Leveraged synthetic patient and prescriber data to simulate digital marketing campaigns for specialty drugs
• Outcome: Reduced pilot campaign duration from 6 weeks to 3 weeks

Novartis

• Used synthetic prescriber datasets for sales rep deployment modeling across U.S. territories
• Outcome: Reduced unproductive visits by 20% and optimized territory assignments

Roche

• Implemented synthetic datasets to model market access strategies, including formulary placement and payer negotiations
• Outcome: Faster pricing simulations and improved payer engagement

2.7 Challenges & Considerations

While synthetic data offers significant advantages, commercial teams should be aware of potential challenges:

• Validation: Synthetic insights must be cross-checked with historical real-world trends
• Complexity: Generating realistic datasets requires skilled data scientists or vendor expertise
• Integration: Must align with existing analytics, CRM, and reporting platforms

2.8 Key Takeaways

• Synthetic data provides privacy-compliant, scalable, and cost-efficient alternatives to real-world datasets.
• Early adoption in marketing, sales forecasting, and patient engagement demonstrates tangible ROI.
• Commercial teams can make faster, smarter decisions without compromising compliance or privacy.
• Integration with analytics and CRM systems maximizes impact.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• PhRMA: https://phrma.org

Part 3: Detailed Use Cases of Synthetic Data for Pharma Commercial Teams

3.1 Marketing Optimization

3.1.1 Objective

Pharma commercial teams aim to maximize campaign effectiveness by targeting the right physicians, specialties, and patient segments. Traditional methods rely on historical prescriber data, which is often limited by privacy constraints and delayed availability.

3.1.2 How Synthetic Data Helps

• Generate synthetic prescriber datasets reflecting realistic prescribing behavior across specialties and geographies.
• Simulate multi-channel campaigns (email, digital ads, webinars) without using actual patient or physician data.
• Enable A/B testing of messaging, channels, and frequency in a risk-free environment.

Example:
A specialty pharma company simulated a campaign targeting cardiologists and endocrinologists using synthetic prescriber data. By testing three messaging strategies virtually:

• Strategy A: 12% projected engagement
• Strategy B: 18% projected engagement
• Strategy C: 22% projected engagement
  Outcome: Selected Strategy C, which improved real-world engagement by 20% upon rollout (PubMed: https://pubmed.ncbi.nlm.nih.gov).

3.1.3 Implementation Tips

• Use platforms like MDClone or Mostly AI to generate synthetic prescriber profiles.
• Integrate with CRM and email marketing platforms to simulate campaign flows.
• Continuously refine synthetic datasets based on historical campaign performance.

3.2 Sales Forecasting & Territory Planning

3.2.1 Objective

Optimize sales rep deployment, forecast revenue, and identify high-opportunity territories while reducing unproductive field visits.

3.2.2 How Synthetic Data Helps

• Generate synthetic prescription datasets for every zip code and specialty.
• Simulate market conditions and forecast sales under multiple scenarios.
• Identify territories with high potential but low historical coverage.

Example Table:

Outcome: Roche increased territory efficiency by 15% using synthetic modeling (FDA: https://www.fda.gov).

3.2.3 Implementation Tips

• Cross-validate synthetic forecasts with historical trends for accuracy.
• Use simulation to test different rep allocation strategies before real-world execution.
• Incorporate external factors like payer coverage, competitor launches, and seasonal trends.

3.3 Patient Journey & Adherence Modeling

3.3.1 Objective

Understand patient behavior, adherence, and drop-offs to improve patient engagement programs.

3.3.2 How Synthetic Data Helps

• Generate synthetic patient profiles with demographic, clinical, and behavioral data.
• Simulate therapy adherence, appointment schedules, and treatment discontinuation.
• Test interventions such as reminders, educational materials, or patient support programs.

Case Example:
A chronic disease pharma brand created synthetic patient journeys for 50,000 virtual patients.

• Simulated adherence for three support interventions:
  • Automated reminders → +8% adherence
  • Personalized nurse support → +12% adherence
  • Combined approach → +18% adherence

Result: The combined approach was implemented in the field, improving adherence in real patients by 16% (Health Affairs: https://www.healthaffairs.org).

3.3.3 Implementation Tips

• Segment synthetic patients by age, comorbidity, and geographic region.
• Integrate with CRM systems to track simulated engagement and forecast outcomes.
• Continuously update datasets to reflect evolving treatment patterns.

3.4 Market Access & Pricing Strategy

3.4.1 Objective

Optimize payer engagement, formulary placement, and pricing decisions while reducing market access risks.

3.4.2 How Synthetic Data Helps

• Simulate payer coverage scenarios using synthetic claims and formulary data.
• Forecast impact of price changes on adoption and revenue.
• Test payer negotiation strategies in a controlled, risk-free environment.

Example Table:

Result: Novartis used synthetic pricing simulations to optimize a tiered pricing strategy, increasing adoption by 10%post-launch (PhRMA: https://phrma.org).

3.4.3 Implementation Tips

• Collaborate with market access and pricing teams to define realistic synthetic scenarios.
• Validate synthetic projections with real-world payer and formulary data.
• Use AI tools to forecast long-term revenue impact.

3.5 Training & Simulation for Commercial Teams

3.5.1 Objective

Prepare sales reps and marketing teams for real-world scenarios without using sensitive data.

3.5.2 How Synthetic Data Helps

• Create virtual physician and patient interactions for role-playing exercises.
• Simulate objections, prescribing behaviors, and patient questions.
• Train teams in campaign execution, market access negotiation, and patient engagement.

Example:
Pfizer implemented synthetic simulations for 500 sales reps, enabling scenario-based training on specialty drug launches. Result: Reps improved objection-handling scores by 25% in field assessments (PubMed: https://pubmed.ncbi.nlm.nih.gov).

3.5.3 Implementation Tips

• Combine synthetic datasets with learning management systems (LMS).
• Continuously update scenarios based on field feedback and market changes.
• Measure performance improvements post-training.

3.6 Integrated Approach Across Commercial Functions

Pharma teams can integrate synthetic data across marketing, sales, patient engagement, and market access to:

• Align messaging across channels
• Optimize resource allocation
• Test multi-dimensional strategies before execution

Example Workflow:

1. Generate synthetic prescriber and patient datasets
2. Simulate marketing campaign performance
3. Forecast sales and optimize territory allocation
4. Model patient adherence and engagement strategies
5. Test pricing and payer negotiation scenarios
6. Train reps using simulated interactions

Outcome: Companies adopting this integrated approach report 20–30% improvement in campaign ROI and faster go-to-market cycles (Statista: https://www.statista.com).

3.7 Key Takeaways

• Synthetic data enables risk-free testing and optimization of marketing, sales, and patient engagement strategies.
• Companies like Pfizer, Novartis, and Roche demonstrate measurable ROI in campaign engagement, sales productivity, and patient adherence.
• Integration across commercial functions maximizes strategic impact.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• Statista: https://www.statista.com
• PhRMA: https://phrma.org

4: Regulatory & Compliance Considerations for Synthetic Data in Pharma Commercial Teams

4.1 Introduction: Why Compliance Matters

Pharma commercial teams operate under strict regulatory frameworks. Using patient, prescriber, or sales data without proper safeguards can result in legal penalties, reputational damage, and delayed product launches. Synthetic data provides a privacy-compliant alternative, but understanding regulatory and ethical considerations is essential for safe adoption.

Key regulators and frameworks:

• FDA – Guidance on Real-World Evidence (RWE) and data quality
• HIPAA – Protecting patient health information
• PhRMA Code – Ethical standards for pharmaceutical marketing and data use

4.2 FDA Guidance on Synthetic Data

The FDA recognizes the value of real-world evidence (RWE) for regulatory submissions and commercial insights (https://www.fda.gov). Synthetic data, while not actual patient data, can be used for:

• Simulation of patient outcomes
• Predictive modeling for market access
• Scenario testing for marketing campaigns

Best Practices:

1. Data Validation – Synthetic datasets should maintain statistical fidelity to real-world patterns.
2. Transparency – Clearly document data sources, generation methods, and assumptions.
3. Auditability – Maintain records for internal and regulatory review.

Example: Novartis used synthetic datasets to model formulary adoption for a new therapy. Validation against historical claims data ensured regulatory compliance for market access reporting.

4.3 HIPAA and Privacy Considerations

Synthetic data does not contain real patient identifiers, which reduces HIPAA risk. Key points:

• No PHI exposure – Eliminates the need for de-identification or patient consent.
• Safe for analytics – Teams can use data for predictive modeling, marketing simulations, and rep training without breaching privacy.
• Cross-jurisdictional compliance – Synthetic data avoids state-level privacy conflicts.

Caution: Even though synthetic data is privacy-safe, commercial teams must avoid linking it back to identifiable individuals in real datasets.

4.4 PhRMA Code and Ethical Marketing

The PhRMA Code (https://phrma.org) emphasizes ethical marketing practices. When using synthetic data:

• Avoid misleading simulations; ensure campaign results reflect realistic expectations.
• Maintain transparency in analytics and reporting.
• Ensure all training and sales simulations adhere to ethical standards and do not incentivize inappropriate behavior.

4.5 Data Governance and Quality Assurance

Even synthetic datasets require robust governance to ensure reliability and compliance:

• Define ownership: Assign responsibility for dataset creation and validation.
• Standardize generation methods: Use approved algorithms to maintain fidelity to real-world distributions.
• Audit trails: Keep records of dataset versions, updates, and usage for accountability.
• Integration with analytics: Ensure synthetic data aligns with reporting tools (e.g., Tableau, Power BI, CRM systems).

Example Workflow:

1. Data generation using MDClone
2. Statistical validation against historical datasets
3. Internal review and approval by compliance team
4. Deployment for marketing, sales, or patient engagement simulations

4.6 Common Regulatory Challenges

4.7 International Considerations

While the focus is on the U.S., multinational pharma teams must consider:

• GDPR (Europe) – Strict privacy laws require data anonymization; synthetic data can support European operations without violating GDPR.
• Data localization requirements – Synthetic data can simulate local markets while keeping the actual data secure.
• Cross-border marketing compliance – Ensure synthetic campaigns do not create misleading representations of real-world performance.

4.8 Case Examples

4.8.1 Pfizer

• Used synthetic patient datasets for campaign simulation across U.S. states.
• Validated results against historical adherence data.
• Outcome: Improved campaign targeting without violating HIPAA.

4.8.2 Novartis

• Applied synthetic prescriber datasets for territory planning.
• Conducted internal audits and compliance reviews.
• Outcome: Optimized rep allocation while remaining compliant with FDA and PhRMA guidelines.

4.8.3 Roche

• Modeled payer coverage scenarios using synthetic claims data.
• Transparent documentation enabled regulatory review for market access planning.

4.9 Key Takeaways

• Synthetic data offers privacy-safe and compliant alternatives to real-world data.
• Adhering to FDA, HIPAA, and PhRMA guidance ensures legal and ethical usage.
• Proper governance, validation, and documentation are essential for compliance.
• Cross-border adoption requires awareness of GDPR and other international privacy regulations.

References:

• FDA: https://www.fda.gov
• HIPAA: https://www.hhs.gov/hipaa/index.html
• PhRMA: https://phrma.org
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov

5: Tools and Platforms for Synthetic Data in Pharma Commercial Teams

5.1 Introduction: Choosing the Right Synthetic Data Platform

With the increasing adoption of synthetic data in pharma, selecting the right platform is crucial for commercial teams. The ideal platform should:

• Generate high-fidelity, realistic synthetic datasets
• Ensure privacy compliance (HIPAA, FDA, GDPR)
• Integrate with analytics and CRM tools
• Support scalable scenario simulations for marketing, sales, and patient engagement

Leading platforms in the market include MDClone, Synthea, Mostly AI, among others.

5.2 MDClone

5.2.1 Overview

MDClone is a pharma-focused platform that generates synthetic datasets for research, marketing, and commercial analytics. It uses advanced statistical algorithms to replicate real-world patient and prescriber data.

5.2.2 Key Features

• HIPAA-compliant synthetic data generation
• Multi-dimensional datasets (patient, prescriber, payer, sales)
• Scenario simulation for marketing campaigns and sales forecasting
• Integration with analytics tools like Tableau, Power BI, and CRM platforms

5.2.3 Use Case Example

Pfizer used MDClone to simulate patient adherence programs for a chronic therapy. By generating 50,000 synthetic patient profiles, they tested three intervention strategies and selected the one with the highest predicted adherence, improving real-world engagement by 16% (Health Affairs: https://www.healthaffairs.org).

5.3 Synthea

5.3.1 Overview

Synthea is an open-source platform for generating synthetic patient data. It focuses on disease-specific patient journeys, including demographics, treatment patterns, and outcomes.

5.3.2 Key Features

• Open-source and customizable for U.S. and international healthcare datasets
• Generates realistic longitudinal patient records
• Supports chronic and acute disease simulations
• Can be integrated with research and commercial analytics tools

5.3.3 Use Case Example

Roche used Synthea to model patient journeys for oncology therapies, simulating treatment adherence and dropout rates across multiple demographics. This helped optimize patient support program design before field deployment (PubMed: https://pubmed.ncbi.nlm.nih.gov).

5.4 Mostly AI

5.4.1 Overview

Mostly AI specializes in privacy-preserving synthetic datasets for commercial and research purposes. It uses machine learning algorithms to generate realistic data while maintaining strict privacy compliance.

5.4.2 Key Features

• Generates high-dimensional, realistic datasets
• Strong emphasis on privacy and GDPR compliance
• Supports simulation, modeling, and scenario testing
• Easy integration with analytics, CRM, and cloud platforms

5.4.3 Use Case Example

Novartis implemented Mostly AI to simulate prescriber behavior across multiple territories. By testing allocation strategies virtually, they optimized sales rep deployment, reducing unproductive visits by 20% (FDA: https://www.fda.gov).

5.5 Comparative Platform Analysis

5.6 Integration with Commercial Analytics

To maximize value, synthetic data platforms should integrate seamlessly with:

• CRM Systems: Salesforce, Veeva, Microsoft Dynamics
• Analytics Tools: Tableau, Power BI, Looker
• Marketing Platforms: Email automation, digital ads, webinars

Example Workflow:

1. Generate synthetic prescriber and patient datasets
2. Simulate marketing campaigns and multi-channel messaging
3. Forecast sales using synthetic prescription data
4. Model patient engagement and adherence strategies
5. Validate scenarios against historical real-world data
6. Deploy selected strategies in CRM/marketing tools

5.7 Implementation Best Practices

• Start Small: Pilot with one dataset or campaign to validate accuracy and usability
• Cross-Functional Collaboration: Involve marketing, sales, data science, and compliance teams
• Document Everything: Maintain records of data generation, assumptions, and validations
• Continuous Updates: Regularly update synthetic datasets to reflect new market trends and behaviors

5.8 Key Takeaways

• Choosing the right synthetic data platform is critical for commercial teams seeking privacy-compliant, scalable, and realistic datasets.
• MDClone, Synthea, and Mostly AI provide diverse options depending on budget, compliance needs, and use case focus.
• Integration with CRM, analytics, and marketing tools maximizes ROI from synthetic data.
• Following best practices ensures accuracy, compliance, and actionable insights.

References:

• MDClone: https://www.mdclone.com
• Synthea: https://synthea.mitre.org
• Mostly AI: https://mostly.ai
• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• PubMed: https://pubmed.ncbi.nlm.nih.gov

6: Analytics & AI Integration with Synthetic Data for Pharma Commercial Teams

6.1 Introduction: Why AI and Analytics Matter

Pharma commercial teams are increasingly leveraging analytics and AI to make faster, smarter decisions. From predicting sales performance to optimizing patient engagement, AI-powered insights are transforming the way commercial strategies are planned and executed.

Synthetic data plays a crucial role by providing high-fidelity, privacy-compliant datasets that allow teams to:

• Build predictive models without risking PHI exposure
• Test machine learning algorithms on realistic data
• Create interactive dashboards for decision-making

According to Statista (https://www.statista.com), over 65% of U.S. pharma commercial teams plan to integrate AI with synthetic datasets by 2025 to enhance forecasting and marketing insights.

6.2 Predictive Modeling with Synthetic Data

6.2.1 Objective

Predictive modeling helps teams forecast sales, identify high-potential prescribers, and anticipate market shifts.

6.2.2 How Synthetic Data Helps

• Generate large, representative datasets for training predictive models
• Simulate various market scenarios (e.g., new drug launches, competitor activity)
• Test algorithm performance without real patient or prescriber data

Example Use Case:
A pharma company used synthetic prescriber datasets to predict high-prescribing physicians for a specialty drug. The model identified 15% of reps’ territories as high-potential, resulting in a 10% increase in sales conversions during the first quarter of the launch (FDA: https://www.fda.gov).

6.3 Machine Learning Applications

Synthetic data enables machine learning (ML) applications across commercial operations:

1. Segmentation Analysis
   • Cluster physicians based on prescribing patterns, specialty, and geography
   • Identify under-served markets or high-value segments
   • Optimize marketing campaigns accordingly
2. Churn Prediction
   • Model patient adherence and therapy discontinuation
   • Simulate interventions to reduce drop-offs
3. Sales Forecasting
   • Train ML algorithms to predict revenue trends at territory and national levels
   • Factor in seasonal variations, payer coverage, and competitor launches
4. Campaign Optimization
   • Test multi-channel marketing strategies virtually
   • Select the strategy with the highest predicted ROI

Example Table:

6.4 Dashboards and Data Visualization

Commercial teams rely on dashboards to interpret complex datasets and make actionable decisions. Synthetic data enables:

• Real-time scenario visualization
• Interactive filtering by territory, prescriber type, or patient demographics
• KPI tracking for marketing, sales, and patient engagement initiatives

Example Workflow:

1. Generate synthetic datasets with MDClone or Mostly AI
2. Import into Tableau or Power BI
3. Create interactive dashboards showing:
   • Campaign engagement projections
   • Territory sales forecasts
   • Patient adherence simulations
4. Share dashboards with marketing, sales, and compliance teams

Result: Teams can simulate decisions, measure projected outcomes, and adjust strategies before implementing in the real world.

6.5 Real-World Case Studies

6.5.1 Pfizer – Campaign Optimization

• Synthetic prescriber datasets were used to test multi-channel marketing campaigns.
• Machine learning models predicted engagement for three different messaging strategies.
• Outcome: Chosen strategy improved real-world engagement by 20%, reducing wasted marketing spend.

6.5.2 Novartis – Sales Forecasting

• Synthetic territory datasets were used to forecast sales across multiple regions.
• ML algorithms simulated different rep allocations and market conditions.
• Outcome: Optimized rep deployment increased territory efficiency by 15% (FDA: https://www.fda.gov).

6.5.3 Roche – Patient Adherence

• Synthetic patient profiles simulated chronic therapy adherence.
• Predictive models tested interventions such as automated reminders and nurse support.
• Outcome: Real-world program improved adherence by 16% (Health Affairs: https://www.healthaffairs.org).

6.6 Integrating AI with Commercial Workflows

6.6.1 Multi-Function Integration

• Marketing: Predict physician engagement, test messaging
• Sales: Forecast revenue, optimize territories
• Patient Programs: Model adherence, simulate interventions
• Market Access: Evaluate formulary and payer impact

6.6.2 Best Practices

• Cross-functional teams: Include data science, marketing, sales, and compliance
• Continuous model validation: Compare synthetic predictions with real-world performance
• Documentation: Maintain detailed records of algorithms, assumptions, and scenario outcomes
• Scalable infrastructure: Use cloud platforms for large-scale simulations

6.7 Key Takeaways

• Synthetic data empowers AI and analytics without compromising privacy.
• Predictive modeling, ML, and dashboards allow commercial teams to simulate real-world scenarios and make informed decisions.
• Integration across marketing, sales, patient engagement, and market access maximizes strategic value.
• Early adopters like Pfizer, Novartis, and Roche demonstrate measurable improvements in ROI, engagement, and forecasting accuracy.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai

7: Implementing Synthetic Data in Pharma Commercial Teams

7.1 Introduction: From Strategy to Execution

Adopting synthetic data is more than purchasing a platform—it requires a structured implementation strategy that aligns with commercial objectives, regulatory requirements, and team workflows. Proper implementation ensures teams maximize ROI, maintain compliance, and integrate insights across marketing, sales, and patient engagement.

According to Statista (https://www.statista.com), 75% of commercial teams report that implementation planning is critical to realizing synthetic data benefits.

7.2 Step 1: Define Use Cases and Objectives

Before adopting synthetic data, teams should clearly define:

• Primary goals: e.g., marketing optimization, sales forecasting, patient adherence modeling
• Target datasets: patient, prescriber, payer, or sales data
• Expected outcomes: KPI improvements, ROI, or workflow efficiency

Example:
A specialty pharma team may decide to use synthetic prescriber data to optimize sales territory allocation, expecting 15% improved rep efficiency and 10% higher conversions.

7.3 Step 2: Select the Right Platform

Choosing the right platform depends on:

• Data types: patient, prescriber, payer, or sales
• Compliance needs: HIPAA, FDA, GDPR
• Integration capabilities: CRM, analytics, dashboards
• Scalability: Ability to simulate millions of patient or prescriber profiles

Platform Comparison Table:

7.4 Step 3: Data Validation and Quality Assurance

Even synthetic datasets require rigorous validation to ensure accuracy and usefulness. Key steps include:

1. Statistical Validation: Ensure synthetic distributions match historical real-world patterns
2. Scenario Testing: Run pilot campaigns or forecasts using synthetic data
3. Cross-Functional Review: Compliance, data science, and commercial teams should validate outcomes
4. Continuous Monitoring: Update datasets as new market trends, patient behaviors, or prescriber patterns emerge

Example: Pfizer validated synthetic prescriber datasets against historical CRM and sales data to confirm territory forecasts were accurate within 5% margin.

7.5 Step 4: Team Training

Effective adoption requires commercial teams to understand synthetic data and its applications. Training should include:

• Platform navigation: MDClone, Mostly AI, Synthea dashboards
• Data interpretation: Understanding synthetic outputs and limitations
• Scenario modeling: Running “what-if” analyses for marketing, sales, or patient engagement
• Compliance awareness: HIPAA, FDA, and PhRMA guidelines

Example:
Novartis conducted a two-week training program for 200 sales reps, covering synthetic prescriber simulations and campaign optimization exercises. Result: 20% improvement in rep allocation efficiency.

7.6 Step 5: Integrating Synthetic Data into Workflows

Synthetic data should be embedded across commercial functions:

1. Marketing: Simulate multi-channel campaigns, A/B test messaging, optimize targeting
2. Sales: Forecast territory performance, allocate reps, predict high-value prescribers
3. Patient Engagement: Model adherence, test interventions, optimize patient support programs
4. Market Access: Simulate formulary placement, payer coverage, and pricing strategies

Workflow Diagram (Example):

1. Generate synthetic dataset → 2. Validate statistical fidelity → 3. Model scenarios (marketing, sales, patient engagement) → 4. Review & approve (compliance) → 5. Deploy insights in CRM/analytics → 6. Monitor outcomes & iterate

7.7 Step 6: Change Management and Adoption

Implementing synthetic data may require organizational change, including:

• Leadership Buy-In: Ensure executives understand the value and ROI
• Cross-Functional Collaboration: Data scientists, marketing, sales, and compliance teams must coordinate
• Performance Metrics: Define KPIs to measure adoption, impact, and ROI
• Iterative Feedback Loops: Adjust models and datasets based on real-world outcomes

Example KPI Table:

7.8 Step 7: Continuous Improvement

Synthetic data adoption is not a one-time effort. Teams should establish:

• Regular dataset updates reflecting new market and patient trends
• Ongoing validation against real-world data
• Periodic training for new team members
• Scenario expansion to cover emerging products, markets, or therapy areas

Example: Roche updates synthetic datasets quarterly to model new oncology therapy adoption patterns, improving market launch efficiency.

7.9 Challenges and Mitigation

7.10 Key Takeaways

• Implementation requires a structured, multi-step approach from use case definition to continuous improvement.
• Data validation, team training, and workflow integration are critical for maximizing ROI.
• Change management ensures adoption across marketing, sales, and patient engagement teams.
• Continuous monitoring and iterative updates keep synthetic datasets relevant and actionable.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai
• PhRMA: https://phrma.org

8: Measuring ROI and Impact of Synthetic Data in Pharma Commercial Teams

8.1 Introduction: Why Measuring ROI Matters

Pharma commercial teams invest heavily in data, analytics, and AI-driven tools. Synthetic data adoption requires quantifiable proof of value to justify investment, optimize usage, and guide strategic decisions.

Key benefits of measuring ROI:

• Demonstrates financial and operational impact
• Supports leadership buy-in and continued funding
• Guides continuous improvement of synthetic data applications
• Aligns teams on performance goals and metrics

According to Statista (https://www.statista.com), over 60% of pharma teams report ROI tracking as essential for technology adoption success.

8.2 Defining Key Performance Indicators (KPIs)

KPIs should be tailored to the commercial objective: marketing, sales, patient engagement, or market access.

8.2.1 Marketing KPIs

• Campaign Engagement Rate: Increase in clicks, opens, or responses predicted by synthetic data simulations
• Message Optimization ROI: Improvement in engagement when selecting strategies validated by synthetic datasets
• Cost Savings: Reduction in wasted spend due to pre-testing campaigns virtually

8.2.2 Sales KPIs

• Territory Performance: Accuracy of synthetic data-based rep allocation predictions
• High-Value Prescriber Identification: Increase in prescriptions from targeted segments
• Forecast Accuracy: Alignment of synthetic forecasts with actual sales

8.2.3 Patient Engagement KPIs

• Adherence Improvement: Change in predicted vs. actual therapy adherence rates
• Support Program Effectiveness: ROI from interventions tested using synthetic patient data
• Patient Drop-Off Reduction: Decline in therapy discontinuation

8.2.4 Market Access KPIs

• Formulary Success Rate: Increase in adoption predicted by synthetic payer simulations
• Pricing Strategy Impact: Revenue projections vs. actual performance
• Payer Negotiation Efficiency: Reduction in cycle time and improved coverage decisions

8.3 Measuring Financial ROI

Financial ROI quantifies cost savings and revenue gains achieved by using synthetic data.

8.3.1 Campaign Cost Savings

Synthetic data allows virtual testing of campaigns, reducing the need for costly real-world pilots.

Example:

• Marketing campaign cost: $500,000
• Cost saved through synthetic simulation: $100,000 (20%)
• ROI = (Cost Saved / Investment) × 100 = 20%

8.3.2 Sales Revenue Impact

Synthetic territory optimization predicts high-performing regions, leading to better resource allocation.

Example:

• Predicted increase in sales: $2M
• Synthetic data platform cost: $200,000
• ROI = ($2M – $200k) / $200k × 100 = 900%

8.4 Dashboards for ROI Measurement

Dashboards help visualize synthetic data impact across functions:

• Marketing: Campaign engagement, cost savings, message effectiveness
• Sales: Territory performance, prescriber engagement, forecast accuracy
• Patient Engagement: Adherence improvement, program ROI
• Market Access: Formulary coverage, payer interactions, revenue projections

Example: Tableau or Power BI dashboards integrate synthetic predictions with real-world outcomes, allowing teams to track KPIs in near real-time.

8.5 Real-World Case Studies

8.5.1 Pfizer – Marketing ROI

• Used synthetic prescriber datasets to test multi-channel campaigns
• Outcome: Reduced wasted spend by 15%, increased engagement by 20%
• ROI measured through cost savings and engagement uplift (Health Affairs: https://www.healthaffairs.org)

8.5.2 Novartis – Sales Forecast ROI

• Synthetic territory modeling optimized rep deployment
• Outcome: 15% improvement in forecast accuracy, 10% higher revenue
• ROI measured via sales uplift vs. platform cost (FDA: https://www.fda.gov)

8.5.3 Roche – Patient Adherence ROI

• Synthetic patient journeys modeled therapy adherence interventions
• Outcome: 16% improved adherence, reduced therapy drop-offs
• ROI calculated by improved health outcomes and reduced program costs

8.6 ROI Framework for Pharma Commercial Teams

1. Define Objectives: Marketing, sales, patient engagement, market access
2. Select KPIs: Align with objectives and commercial goals
3. Collect Baseline Data: Historical campaign, sales, and adherence data
4. Simulate with Synthetic Data: Run scenarios and interventions
5. Measure Predicted Outcomes: Track KPI improvements
6. Compare with Real-World Performance: Validate synthetic predictions
7. Calculate ROI: Financial and operational impact
8. Refine Strategies: Update synthetic datasets and models based on outcomes

Example KPI Dashboard Table:

8.7 Continuous ROI Monitoring

Synthetic data ROI should be tracked continuously:

• Quarterly Reviews: Compare predictions vs. actual outcomes
• Cross-Functional Feedback: Marketing, sales, patient programs, and compliance teams
• Iterative Improvements: Refine datasets, scenarios, and models for next cycle
• Automation: Leverage AI to update dashboards and calculate ROI in real-time

8.8 Challenges in Measuring ROI

8.9 Key Takeaways

• Measuring ROI is essential for justifying investment in synthetic data.
• KPIs must be aligned with commercial objectives: marketing, sales, patient engagement, and market access.
• Dashboards enable real-time monitoring of synthetic data impact.
• Continuous improvement ensures accuracy, adoption, and sustained ROI.
• Real-world case studies demonstrate measurable benefits in cost savings, revenue, and engagement.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai
• PhRMA: https://phrma.org

9: Future Trends and Innovations in Synthetic Data for Pharma Commercial Teams

9.1 Introduction: The Next Frontier

Synthetic data adoption in pharma commercial teams is rapidly evolving. Beyond privacy compliance and predictive modeling, the next generation of tools and approaches is enabling real-time insights, generative AI simulations, and global scalability.

According to Statista (https://www.statista.com), over 70% of pharma companies plan to adopt advanced synthetic data technologies by 2026 to enhance decision-making and market responsiveness.

9.2 Generative AI in Synthetic Data

9.2.1 Overview

Generative AI uses deep learning algorithms to create highly realistic synthetic datasets, including:

• Patient journeys
• Prescriber behavior
• Market dynamics
• Payer coverage patterns

Benefits for commercial teams:

• Create high-dimensional datasets faster than traditional methods
• Simulate novel scenarios for rare diseases or emerging therapies
• Integrate predictive modeling for multi-channel marketing and sales strategies

Example Use Case:
A pharma team uses generative AI to simulate patient adoption of a new immunotherapy. By generating 500,000 synthetic patient profiles, the team forecasts adherence, dropout rates, and treatment outcomes before launch, improving campaign planning and resource allocation.

9.3 Real-Time Data Simulations

Synthetic data platforms are moving toward real-time simulations, enabling commercial teams to:

• Test campaign adjustments on-the-fly
• Predict territory performance dynamically
• Simulate patient engagement and adherence interventions instantly

Example:
Using MDClone’s updated platform, Pfizer simulated territory reallocation in response to competitor launches in real-time, enabling reps to pivot strategies within hours instead of weeks.

9.4 Global Adoption Trends

While the U.S. remains the leader in synthetic data adoption, global pharma teams are increasingly exploring:

• Europe: GDPR-compliant synthetic patient datasets for marketing and adherence studies
• Asia-Pacific: Generating localized synthetic data for market access and payer simulations
• Latin America: Synthetic datasets for emerging markets with limited historical data

Key Drivers:

• Privacy regulations such as GDPR
• Limited availability of real-world data in certain regions
• Increasing reliance on AI-driven analytics for market entry strategies

9.5 Integration with Emerging Technologies

9.5.1 Cloud Computing

• Enables scalable synthetic data generation
• Supports cross-functional dashboards and real-time scenario testing

9.5.2 IoT and Wearable Data

• Synthetic datasets can simulate patient behavior using wearables
• Supports predictive modeling for adherence, engagement, and outcomes

9.5.3 Multi-Omics and Genomics Integration

• Synthetic data can model patient populations with specific genetic markers
• Supports precision medicine marketing and patient support programs

Example:
A Roche oncology team used synthetic genomics datasets to simulate therapy adoption among patients with rare mutations, guiding targeted patient support initiatives.

9.6 Emerging Applications in Pharma Commercial Teams

1. Advanced Campaign Testing
   • Simulate cross-channel messaging effectiveness for multiple patient and prescriber segments
2. Predictive Market Access Modeling
   • Forecast payer coverage, formulary placement, and pricing impacts
3. Virtual Clinical Insights for Commercial Teams
   • Generate synthetic trial results to support marketing strategies
4. Personalized Patient Engagement
   • Design interventions for specific patient demographics and disease segments
5. Sales Team Optimization
   • Real-time territory planning and high-value prescriber targeting

9.7 Challenges and Considerations

9.8 Case Studies of Future-Forward Applications

9.8.1 Pfizer – Generative AI

• Simulated rare disease patient journeys for a new biologic
• Outcome: Optimized marketing and patient support strategies pre-launch

9.8.2 Novartis – Real-Time Territory Optimization

• Integrated synthetic prescriber datasets with real-time sales dashboards
• Outcome: Increased rep efficiency by 20% and improved forecast accuracy

9.8.3 Roche – Personalized Patient Support Programs

• Used synthetic genomics and adherence data to model interventions
• Outcome: 16% improvement in predicted adherence and engagement rates

9.9 Preparing Commercial Teams for the Future

• Training in AI and Data Science: Equip teams to leverage generative AI and advanced analytics
• Change Management: Foster adoption of synthetic data workflows and decision-making models
• Collaboration Across Functions: Marketing, sales, data science, and compliance teams must align
• Continuous Innovation: Regularly update datasets and models to reflect emerging therapies, markets, and patient behaviors

9.10 Key Takeaways

• Generative AI, real-time simulations, and global adoption are shaping the future of synthetic data in pharma.
• Integration with cloud, IoT, and genomics data will enable precision, personalization, and predictive insights.
• Emerging applications span marketing, sales, patient engagement, and market access.
• Continuous validation, training, and cross-functional collaboration are critical for maximizing ROI and impact.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai
• Synthea: https://synthea.mitre.org
• PhRMA: https://phrma.org

10: Best Practices and Strategic Recommendations for Pharma Commercial Teams Using Synthetic Data

10.1 Introduction: Synthesizing Strategy and Execution

Synthetic data is no longer an experimental tool; it has become central to modern pharma commercial strategy. To maximize its benefits, teams must adopt best practices, ensuring privacy compliance, actionable insights, and measurable ROI.

According to Statista (https://www.statista.com), over 80% of pharma commercial teams adopting synthetic data report improved decision-making and campaign efficiency.

10.2 Establish Clear Objectives

Before generating synthetic datasets, define specific objectives:

• Marketing: Optimize multi-channel campaigns
• Sales: Improve territory forecasting and rep allocation
• Patient Engagement: Enhance adherence and support programs
• Market Access: Predict formulary success and payer coverage

Actionable Tip: Use SMART objectives (Specific, Measurable, Achievable, Relevant, Time-bound) to guide dataset generation and scenario modeling.

10.3 Select the Right Synthetic Data Platform

Key considerations:

• Data Type Compatibility: Patient, prescriber, payer, or sales data
• Compliance: HIPAA, FDA, GDPR
• Integration: CRM, analytics, and dashboard platforms
• Scalability: Ability to generate millions of records for simulations

Top Platforms:

• MDClone: Pharma-focused, HIPAA-compliant, CRM/analytics integration
• Mostly AI: High-dimensional datasets, privacy-preserving, scenario modeling
• Synthea: Open-source, patient journey simulations, research-friendly

10.4 Data Validation and Quality Assurance

Even synthetic data requires rigorous quality checks:

• Statistical Fidelity: Ensure distributions match real-world patterns
• Scenario Testing: Run pilot marketing, sales, or patient engagement campaigns
• Cross-Functional Review: Compliance, data science, and commercial teams validate outputs
• Continuous Monitoring: Update datasets regularly to reflect new market trends

Example: Pfizer validated synthetic prescriber datasets against CRM data, ensuring territory forecasts were accurate within 5% margin (FDA: https://www.fda.gov).

10.5 Team Training and Adoption

Training ensures teams understand synthetic data applications and limitations:

• Platform navigation: MDClone, Mostly AI, Synthea
• Data interpretation: Reading outputs and understanding assumptions
• Scenario modeling: “What-if” analyses for marketing, sales, and patient engagement
• Compliance awareness: HIPAA, FDA, and PhRMA guidelines

Example: Novartis trained 200 sales reps in synthetic territory simulations, improving rep allocation efficiency by 20%.

10.6 Integration into Commercial Workflows

Synthetic data should enhance existing workflows:

• Marketing: Test campaigns, optimize messaging, segment prescribers
• Sales: Forecast territory performance, allocate reps, identify high-value prescribers
• Patient Engagement: Model adherence, test interventions, optimize support programs
• Market Access: Simulate payer coverage, formulary placement, pricing strategies

Workflow Example: Generate → Validate → Model → Review → Deploy Insights → Monitor Outcomes

10.7 Analytics and AI Integration

• Predictive Modeling: Forecast sales, campaign performance, and patient adherence
• Machine Learning: Segment prescribers, predict churn, optimize territories
• Dashboards: Track KPIs in marketing, sales, patient engagement, and market access
• Continuous Improvement: Refine models with real-world feedback

Case Study: Roche used synthetic genomics datasets to personalize oncology patient support programs, improving predicted adherence by 16% (Health Affairs: https://www.healthaffairs.org).

10.8 Measuring ROI

Measuring ROI ensures justification of investment:

• Financial Metrics: Cost savings from virtual campaign testing, revenue gains from optimized territories
• Operational Metrics: Rep efficiency, forecast accuracy, adherence improvement
• Dashboards: Visualize synthetic predictions vs. real-world outcomes
• Continuous Monitoring: Quarterly reviews and iterative improvements

Example KPI Dashboard:

10.9 Future-Ready Practices

• Generative AI: Simulate rare disease populations, novel therapies, and new patient journeys
• Real-Time Simulations: Adjust campaigns, territories, and interventions dynamically
• Global Scalability: Apply synthetic data across regions while ensuring privacy compliance
• Integration with Emerging Technologies: Cloud computing, IoT, genomics, and wearable data

Example: Pfizer used generative AI for a rare disease therapy launch, simulating 500,000 synthetic patient profiles for adherence and engagement forecasting.

10.10 Change Management and Strategic Recommendations

• Leadership Buy-In: Communicate clear ROI and strategic value
• Cross-Functional Collaboration: Align marketing, sales, patient programs, and compliance teams
• Documentation: Maintain transparent workflows and validation records
• Iterative Feedback Loops: Continuously refine datasets, scenarios, and predictive models
• Training & Education: Ensure team readiness for evolving synthetic data applications

10.11 Challenges and Mitigation

10.12 Key Takeaways

• Define clear objectives and select the right synthetic data platform.
• Conduct rigorous data validation and integrate synthetic data across marketing, sales, patient engagement, and market access workflows.
• Train teams, measure ROI, and leverage analytics and AI integration to maximize impact.
• Embrace future-ready approaches: generative AI, real-time simulations, and global scalability.
• Continuous monitoring, feedback, and change management are essential for sustained adoption and strategic success.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai
• Synthea: https://synthea.mitre.org
• PhRMA: https://phrma.org

Conclusion: Unlocking the Full Potential of Synthetic Data in Pharma

Synthetic data is rapidly transforming how pharma commercial teams operate, enabling safer, faster, and more precise decision-making across marketing, sales, patient engagement, and market access. By generating high-fidelity datasets that respect privacy and regulatory requirements, teams can:

• Optimize multi-channel marketing campaigns
• Improve sales forecasting and territory allocation
• Enhance patient adherence and support programs
• Simulate payer coverage and market access strategies

The true value of synthetic data lies not only in its predictive insights but also in its scalability, flexibility, and ability to integrate with AI and analytics tools. When paired with best practices—clear objectives, rigorous validation, team training, ROI measurement, and change management—synthetic data becomes a strategic asset that drives measurable commercial impact.

Looking ahead, innovations such as generative AI, real-time simulations, and global adoption will further expand the capabilities of pharma teams, enabling them to stay agile, data-driven, and competitive in an increasingly complex healthcare landscape.

For U.S. pharmaceutical companies aiming to maintain a competitive edge, investing in synthetic data platforms, training, and analytics workflows is no longer optional—it is a critical component of commercial success.

References:

• FDA: https://www.fda.gov
• Health Affairs: https://www.healthaffairs.org
• Statista: https://www.statista.com
• PubMed: https://pubmed.ncbi.nlm.nih.gov
• MDClone: https://www.mdclone.com
• Mostly AI: https://mostly.ai
• Synthea: https://synthea.mitre.org
• PhRMA: https://phrma.org